# https://github.com/starascendin/lifeos-plugin 项目说明书
生成时间：2026-05-18 00:31:52 UTC
## 目录
- [Overview](#overview)
- [Installation Guide](#installation)
- [Skills Overview](#skills-overview)
- [Daily Workflows](#daily-workflows)
- [Habits & Accountability](#habits-accountability)
- [Health Integration (Oura Ring)](#health-integration)
- [Project Management](#project-management)
- [Client Management](#client-management)
- [People & Relationships](#people-relationships)
- [Review Workflows](#review-workflows)
- [Finance Management](#finance-management)
- [Coaching System](#coaching-system)
## Overview
### 相关页面
相关主题：[Installation Guide](#installation), [Skills Overview](#skills-overview)
Relevant Source Files
以下源码文件用于生成本页说明：
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
- [skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
- [skills/weekly-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
- [skills/sprint-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
- [skills/ppv/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/ppv/SKILL.md)
- [skills/health-weekly/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/health-weekly/SKILL.md)
- [skills/daily-training-report/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-training-report/SKILL.md)
- [skills/customer-success-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
- [skills/llm-council/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/llm-council/SKILL.md)
- [skills/blind-spot-finder/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
# Overview
LifeOS Plugin is a universal skills and MCP (Model Context Protocol) integration layer for LifeOS—a personal productivity operating system powered by Convex. The plugin extends AI agents (such as Claude Code and OpenCode) with 37 workflow skills, 126 MCP tools, and 28 MCP prompts, enabling them to interact with personal productivity data including tasks, projects, contacts, health metrics, finances, coaching insights, and life design systems.
## Purpose and Scope
The primary purpose of LifeOS Plugin is to bridge AI agents with LifeOS data, allowing users to leverage AI capabilities for daily planning, project management, client relationship management, health tracking, and personal development through natural language commands.
The plugin provides:
- **Workflow Automation**: Pre-built skills that execute complete workflows (e.g., daily planning, weekly review, sprint planning)
- **Direct Data Access**: MCP tools enabling CRUD operations on all LifeOS entities
- **Multi-Agent Compatibility**: Support for Claude Code, OpenCode, and any MCP-compatible client
- **Mutating and Read Operations**: Both query and modification capabilities across the productivity stack
资料来源：[README.md:1]()
## Architecture
### System Components
```mermaid
graph TD
A[AI Agent
Claude Code / OpenCode] --> B[LifeOS Plugin Skills]
A --> C[MCP Client]
C --> D[lifeos-mcp Server
@starascendin/lifeos-mcp]
D --> E[LifeOS Convex Backend]
E --> F[(Convex Database)]
B -->|"Invokes Skills"| A
C -->|"MCP Protocol
126 Tools, 28 Prompts"| D
style F fill:#e1f5fe
style D fill:#fff3e0
style B fill:#e8f5e9
```
### Data Flow
```mermaid
sequenceDiagram
participant User
participant Agent as AI Agent
participant Skills as Plugin Skills
participant MCP as MCP Server
participant Convex as LifeOS Backend
User->>Agent: /daily-plan "Plan my day"
Agent->>Skills: Invoke daily-plan skill
Skills->>MCP: get_planning_context()
MCP->>Convex: Query tasks, habits, calendar
Convex-->>MCP: Planning data
MCP-->>Skills: Context object
Skills->>Skills: Build day plan
Skills->>MCP: apply_planning_patch(mode="day")
MCP->>Convex: Mutate due dates, priorities
Convex-->>MCP: Confirmation
MCP-->>Skills: Applied changes
Skills-->>Agent: Summary report
Agent-->>User: Today's top 3 + changes
```
## Installation Methods
### Agent-Specific Setup
| Agent | Method | Command/Steps |
|-------|--------|---------------|
| Claude Code | Single command | `claude plugin add github:starascendin/lifeos-plugin` |
| OpenCode | Copy or symlink | `cp -r skills/ .claude/skills/lifeos/` or symlink |
| Manual | Copy directory | Copy `skills/` to agent's skills location |
资料来源：[README.md:16-37]()
### Environment Configuration
Required credentials must be configured via environment variables:
```bash
export LIFEOS_CONVEX_URL=https://your-app.convex.site
export LIFEOS_USER_ID=your-user-id
export LIFEOS_API_KEY=your-api-key
```
| Variable | Description | Source |
|----------|-------------|--------|
| `LIFEOS_CONVEX_URL` | Convex deployment URL (`.convex.site`) | Convex Dashboard |
| `LIFEOS_USER_ID` | LifeOS user identifier | Convex Dashboard > Users |
| `LIFEOS_API_KEY` | API authentication key | LifeOS Settings |
资料来源：[README.md:5-8]()
### MCP Server Configuration
For MCP-compatible clients, configure the server in your MCP settings:
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@latest",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
资料来源：[README.md:31-44]()
## Skills Catalog
The plugin provides 37 workflow skills organized into categories. Each skill is a self-contained workflow that can be invoked via slash commands (e.g., `/daily-plan`).
资料来源：[AGENTS.md:1]()
### Daily Workflows
| Skill | Purpose |
|-------|---------|
| `daily-standup` | Morning briefing with agenda, tasks, and sprint progress |
| `daily-plan` | Plan today with due date, priority, cycle, and Daily Note changes |
| `end-of-day` | EOD wrap-up with completion summary and tomorrow planning |
| `capture` | Quick capture of thoughts, tasks, or notes with auto-routing |
### Reviews
| Skill | Purpose |
|-------|---------|
| `weekly-review` | Review completed work, in-progress items, and sprint health |
| `weekly-plan` | Plan the week with current cycle, due date, priority, and note changes |
| `monthly-review` | Accomplishments, project progress, and next month planning |
| `cycle-review` | Sprint review with rollover options |
| `initiative-review` | Yearly initiative progress by category |
### Project & Client Management
| Skill | Purpose |
|-------|---------|
| `project-status` | Phase breakdown, task stats, and blockers |
| `client-brief` | Full client briefing with projects and communications |
| `client-health` | Health dashboard across all clients |
| `sprint-plan` | Plan the current cycle and apply task/cycle mutations |
### People & Relationships
| Skill | Purpose |
|-------|---------|
| `contact-lookup` | Full contact dossier with AI insights |
| `meeting-prep` | Prepare for meetings with full context |
| `follow-ups` | Track follow-ups needed with people and clients |
| `relationship-pulse` | Check on neglected relationships |
| `context-switch` | Fast context loading for a client or project |
### Inbox & Tasks
| Skill | Purpose |
|-------|---------|
| `inbox-triage` | Process notes into tasks |
| `overdue` | Overdue and slipping items |
### Voice & Notes
| Skill | Purpose |
|-------|---------|
| `voice-notes` | Interactive memo exploration |
| `voice-notes-crystallize` | Save conversation insights |
### Health & Fitness
| Skill | Purpose |
|-------|---------|
| `health-check` | Quick Oura health overview: scores and trends |
| `health-weekly` | Weekly health review with workouts |
| `screentime-report` | Screen time analysis and top apps |
| `habit-check` | Daily habit check-in, streaks, and completions |
| `daily-training-report` | Daily training report with health + habits |
### Finance
| Skill | Purpose |
|-------|---------|
| `finance-overview` | Net worth, accounts, and trends |
| `finance-spending` | Spending analysis and patterns |
### Coaching & Development
| Skill | Purpose |
|-------|---------|
| `coaching-overview` | Coaching profiles, sessions, and action items |
| `coaching-action-items` | Manage coaching action items |
| `coaching-session-review` | Review coaching session insights |
| `coach-memory` | View AI coach's accumulated knowledge |
### Life Design
| Skill | Purpose |
|-------|---------|
| `ppv` | Manage PPV vision, identity, pillars, project links, weekly actions, reflections, and adjustments |
### Advanced AI Workflows
| Skill | Purpose |
|-------|---------|
| `llm-council` | Multi-model deliberation for complex decisions |
| `blind-spot-finder` | Multi-model council to find blind spots and self-deceptions |
| `customer-success-triage` | Triage client requests using workspace, chats, meetings, and tasks |
资料来源：[README.md:15-50](), [AGENTS.md:1-20]()
## MCP Tools (126 Total)
The MCP server exposes 126 tools providing full CRUD operations across LifeOS entities:
### Data Categories
| Category | Operations | Examples |
|----------|------------|----------|
| Projects | CRUD | `get_projects`, `create_project`, `update_project` |
| Tasks/Issues | CRUD | `get_tasks`, `create_issue`, `update_issue`, `schedule_issue` |
| Cycles | CRUD | `get_current_cycle`, `update_cycle_goals` |
| Clients | CRUD | `get_clients`, `create_client`, `update_client` |
| People/Contacts | CRUD | `get_contacts`, `create_person`, `update_person` |
| Notes | CRUD | `get_notes`, `create_note`, `update_client_note` |
| Voice Memos | CRUD | `get_voice_memos`, `create_voice_memo` |
| Meetings | Read | `get_granola_meeting`, `get_fathom_meeting` |
| Health (Oura Ring) | Read | `get_health_sleep`, `get_health_activity`, `get_health_readiness`, `get_health_stress` |
| Finance | Read | `get_finance_net_worth`, `get_finance_transactions` |
| Habits | CRUD | `get_habits`, `get_habits_for_date` |
| Coaching | CRUD | `get_coaching_action_items`, `create_coaching_action_item` |
| PPV Life Design | CRUD | `get_ppv_workspace`, `upsert_ppv_vision`, `create_ppv_pillar` |
资料来源：[AGENTS.md:21-24]()
### Planning Workflow Tools
```mermaid
graph LR
A[get_planning_context] --> B[Build Plan]
B --> C[apply_planning_patch]
C --> D["create_issue"]
C --> E["schedule_issue"]
C --> F["update_issue"]
C --> G["assign_issue_to_current_cycle"]
C --> H["set_top_priority"]
C --> I["update_cycle_goals"]
C --> J["save_daily_note"]
C --> K["save_weekly_note"]
style A fill:#bbdefb
style B fill:#c8e6c9
style C fill:#ffe0b2
```
The `apply_planning_patch` operation supports multiple mutation types depending on the planning mode:
| Mode | Purpose | Common Operations |
|------|---------|-------------------|
| `day` | Daily planning | Schedule tasks, set top 3 priorities, update daily note |
| `week` | Weekly planning | Assign backlog to cycle, update cycle goals, save weekly note |
| `cycle` | Sprint planning | Assign issues, update cycle goals, schedule near-term work |
资料来源：[skills/daily-plan/SKILL.md:1-35](), [skills/weekly-plan/SKILL.md:1-40](), [skills/sprint-plan/SKILL.md:1-35]()
## MCP Prompts (28 Total)
The plugin exposes 28 MCP prompts—same workflows as the skills, but callable via MCP protocol. Any MCP-compatible client can invoke these prompts to trigger comprehensive workflow execution without directly invoking a skill file.
资料来源：[AGENTS.md:25-27]()
## Core Workflow Patterns
### Planning Workflow Pattern
Most planning skills follow a consistent three-step pattern:
```mermaid
graph TD
A[Step 1: Gather Context
get_planning_context] --> B[Step 2: Build Plan
Analyze and decide]
B --> C[Step 3: Apply Changes
apply_planning_patch]
A --> A1["daily=true
weekly=true
currentCycle=true
backlog=true
habits=true
dailyFields=true
calendar=true
voiceMemos=true"]
B --> B1["Pick top 3 priorities
Schedule tasks by dueDate
Assign backlog to cycle
Update cycle goals if needed"]
C --> C1["mode=day|week|cycle
dryRun=false"]
```
### Mutating vs. Read-Only Workflows
The plugin distinguishes between:
| Type | Behavior | Examples |
|------|----------|----------|
| **Mutating** | Modifies LifeOS data | `daily-plan`, `weekly-plan`, `sprint-plan`, `ppv` |
| **Read-Only** | Queries and presents data | `health-weekly`, `finance-overview`, `contact-lookup` |
Mutating workflows execute without asking for confirmation—the user expects the plugin to modify LifeOS data automatically.
资料来源：[skills/daily-plan/SKILL.md:33-36](), [skills/weekly-plan/SKILL.md:37-40](), [skills/sprint-plan/SKILL.md:33-36]()
## PPV Life Design System
The PPV (Purpose, Principles, Values) system is a core component for long-term life design. It connects desired future states to daily execution.
### PPV Data Model
```mermaid
graph TD
V[Vision
Future State] --> I[Identity
Who you are]
V --> P[Pillars
Ongoing Systems]
V --> PR[Projects
Existing LifeOS Projects]
I --> B[Beliefs]
I --> BH[Behaviors]
P --> WA[Weekly Actions
Small, Concrete]
PR --> TASKS[Tasks/Issues]
WA --> R[Reflections
Weekly Energy Check]
R --> AD[Adjustments
Feedback Loop]
AD --> I
AD --> P
AD --> PR
AD --> WA
```
### PPV Operations
| Operation | Tool | Purpose |
|-----------|------|---------|
| View workspace | `get_ppv_workspace` | Get vision, identity, pillars, linked projects, actions |
| View graph | `get_active_vision_graph` | Unified graph of vision + linked entities |
| Create vision | `upsert_ppv_vision` | Set vivid, emotional, directional vision |
| Edit identity | `upsert_ppv_identity` | Update coreIdentities, beliefs, behaviors |
| Manage pillars | `create_ppv_pillar`, `update_ppv_pillar`, `delete_ppv_pillar` | Ongoing systems |
| Execute | `create_ppv_weekly_action`, `update_ppv_weekly_action` | Small, identity-aligned actions |
| Reflect | `create_ppv_reflection` | Capture weekly energy, resistance, alignment |
| Adjust | `create_ppv_adjustment` | Feed insights back into the system |
资料来源：[skills/ppv/SKILL.md:1-80]()
## Health Integration
The plugin integrates with Oura Ring data through dedicated health tools:
### Health Data Points
| Category | Tools | Data Retrieved |
|----------|-------|----------------|
| Sleep | `get_health_sleep` | Scores, durations, bedtime, breath rate, restless periods |
| Activity | `get_health_activity` | Steps, active days, calorie burn |
| Readiness | `get_health_readiness` | Score trends, stress vs recovery |
| Stress | `get_health_stress` | Stress levels, recovery balance |
| Workouts | `get_health_workouts` | Workout history with labels |
| Heart Rate | `get_health_heart_rate` | HR trends |
| Resilience | `get_health_resilience` | Resilience levels and contributors |
| VO2 Max | `get_health_vo2_max` | Cardiovascular fitness estimate |
| Cardio Age | `get_health_cardio_age` | Cardiovascular age |
| SpO2 | `get_health_spo2` | Blood oxygen, breathing disturbance |
资料来源：[skills/health-weekly/SKILL.md:1-50](), [AGENTS.md:23]()
## Advanced AI Workflows
### LLM Council
The `llm-council` skill uses multiple AI models to deliberate on complex decisions:
1. **Round 1**: Individual model responses to the question
2. **Round 2**: Peer review and cross-evaluation
3. **Chairman Synthesis**: Final authoritative answer
Output presentation includes individual responses, rankings table, and chairman's synthesis.
资料来源：[skills/llm-council/SKILL.md:1-60]()
### Blind Spot Finder
The `blind-spot-finder` skill uses multi-model analysis to identify unknown unknowns:
1. Gather context (working memory, habits, health, finances)
2. Build a comprehensive brief
3. Run multi-model council for blind spot detection
4. Analyze patterns and local maxima
5. User selects one blind spot to work on
资料来源：[skills/blind-spot-finder/SKILL.md:1-60]()
## Daily Training Report
The `daily-training-report` skill generates a comprehensive daily briefing combining:
- **Yesterday's Results**: Habit scorecard, streaks, health scores
- **Today's Game Plan**: Top 3 priorities, scheduled habits
- **Initiative Progress**: Yearly goal tracking
- **Coaching Action Items**: Pending homework
Data sources include habits, health metrics, daily agenda, tasks, initiatives, and coaching items.
资料来源：[skills/daily-training-report/SKILL.md:1-60]()
## Customer Success Triage
The `customer-success-triage` skill provides structured triage for client work:
1. Fetch client workspace
2. Review threads, meetings, notes, and open tasks
3. Drill down when needed (Beeper, Fathom, Granola, notes)
4. Classify into: New Requirements, Follow-Ups, Risks/Blockers, Already Tracked
5. Create notes or tasks as appropriate
资料来源：[skills/customer-success-triage/SKILL.md:1-40]()
## Updating the Plugin
```bash
# Update the plugin repository
cd /path/to/lifeos-plugin && git pull
# Update the MCP server (auto-updates with npx @latest)
# Or pin a version in .mcp.json
# "@starascendin/lifeos-mcp@0.7.0"
```
资料来源：[README.md:56-62]()
## Summary
LifeOS Plugin transforms AI agents into comprehensive personal productivity assistants by providing:
1. **37 workflow skills** covering daily planning, reviews, project management, relationships, health, finance, coaching, and life design
2. **126 MCP tools** for direct CRUD operations across all LifeOS entities
3. **28 MCP prompts** for programmatic workflow invocation
4. **Multi-agent support** via Claude Code plugin system and OpenCode native skills
5. **Mutating capabilities** that execute changes without confirmation for automated productivity workflows
The plugin bridges the gap between AI reasoning capabilities and personal productivity data, enabling users to manage complex workflows through natural language commands while maintaining data consistency in their personal operating system.
---
## Installation Guide
### 相关页面
相关主题：[Overview](#overview)
Relevant Source Files
以下源码文件用于生成本页说明：
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
- [skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
- [skills/weekly-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
- [skills/sprint-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
# Installation Guide
This guide covers the complete installation process for integrating LifeOS Plugin with AI agents, enabling universal skills and MCP (Model Context Protocol) access to your personal productivity OS powered by Convex.
## Overview
The LifeOS Plugin provides 37 workflow skills for project management, contacts, agendas, voice notes, health tracking (Oura Ring), finance, coaching, life direction, and more. The plugin works with multiple AI agent platforms including Claude Code and OpenCode.
| Component | Description |
|-----------|-------------|
| **Skills** | 37 workflow automation skills (daily-plan, weekly-plan, health-check, etc.) |
| **MCP Tools** | 126 full CRUD tools for data operations |
| **MCP Prompts** | 28 prompts exposed via MCP protocol |
| **Supported Agents** | Claude Code, OpenCode |
资料来源：[README.md]()
## Prerequisites
Before installing the LifeOS Plugin, you must obtain three credentials from the LifeOS Convex deployment.
### Required Credentials
| Variable | Description | Where to Find |
|----------|-------------|---------------|
| `LIFEOS_CONVEX_URL` | Your Convex deployment URL (format: `https://*.convex.site`) | Convex dashboard |
| `LIFEOS_USER_ID` | Your LifeOS user ID | Convex dashboard > Users table |
| `LIFEOS_API_KEY` | API key for authentication | Generated in LifeOS settings |
资料来源：[AGENTS.md]()
### Environment Variable Configuration
Set the environment variables in your shell configuration:
```bash
export LIFEOS_CONVEX_URL=https://your-app.convex.site
export LIFEOS_USER_ID=your-user-id
export LIFEOS_API_KEY=your-api-key
```
Alternatively, you can pass these credentials directly to the MCP server via command-line arguments or configuration files.
资料来源：[README.md]()
## Installation Methods
### Claude Code Installation
The simplest installation method for Claude Code users.
```bash
claude plugin add github:starascendin/lifeos-plugin
```
This single command installs both the skills and MCP server automatically. After installation, ensure the environment variables are set for the MCP server to authenticate.
资料来源：[README.md]()
### OpenCode Installation
OpenCode reads `.claude/skills/` natively. Two options are available:
**Option A: Copy skills directory**
```bash
git clone git@github.com:starascendin/lifeos-plugin.git /tmp/life
cp -r /tmp/life/skills .claude/skills/lifeos
```
**Option B: Symlink skills directory**
```bash
ln -s /path/to/lifeos-plugin/skills .claude/skills/lifeos
```
资料来源：[README.md]()
### Manual MCP Server Setup
For custom agent integrations, configure the MCP server manually.
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@latest",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
资料来源：[README.md]()
### Version Pinning
To pin a specific MCP server version, update `.mcp.json`:
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@0.7.0",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
资料来源：[README.md]()
## Plugin Architecture
```mermaid
graph TD
A[AI Agent] --> B[LifeOS Plugin]
B --> C[Skills Directory]
B --> D[MCP Server]
D --> E[Convex Backend]
E --> F[LifeOS Database]
C --> G[37 Workflow Skills]
G --> H[Mutating Workflows]
G --> I[Read-only Workflows]
D --> J[126 MCP Tools]
D --> K[28 MCP Prompts]
J --> L[Projects CRUD]
J --> M[Tasks CRUD]
J --> N[Health Data]
J --> O[Finance Data]
J --> P[Contacts]
```
## Available Skills
After installation, the following skill categories become available:
### Daily Workflows
| Skill | Purpose |
|-------|---------|
| `daily-standup` | Morning briefing with agenda, tasks, and sprint progress |
| `daily-plan` | Plan today with due dates, priorities, cycle assignments, and Daily Note |
| `end-of-day` | EOD wrap-up with completion summary and tomorrow planning |
| `capture` | Quick capture a thought, task, or note with auto-routing |
### Reviews
| Skill | Purpose |
|-------|---------|
| `weekly-review` | Completed work, in-progress items, sprint health |
| `weekly-plan` | Plan the week with cycle, due dates, priorities, and note updates |
| `monthly-review` | Accomplishments, project progress, next month planning |
| `cycle-review` | Sprint review with rollover options |
| `initiative-review` | Yearly initiative progress by category |
### Project & Client Management
| Skill | Purpose |
|-------|---------|
| `project-status` | Phase breakdown, task stats, blockers |
| `client-brief` | Full client briefing with projects and comms |
| `client-health` | Health dashboard across all clients |
| `sprint-plan` | Plan current cycle and apply task/cycle mutations |
### People & Relationships
| Skill | Purpose |
|-------|---------|
| `contact-lookup` | Full contact dossier with AI insights |
| `meeting-prep` | Prepare for meetings with full context |
| `follow-ups` | Track follow-ups needed |
| `relationship-pulse` | Check on neglected relationships |
| `context-switch` | Fast context loading for client/project |
### Health & Fitness
| Skill | Purpose |
|-------|---------|
| `health-check` | Quick Oura health overview: scores, trends |
| `health-weekly` | Weekly health review with workouts |
| `daily-training-report` | Daily training report with health + habits |
### Finance
| Skill | Purpose |
|-------|---------|
| `finance-overview` | Net worth, accounts, trends |
| `finance-spending` | Spending analysis and patterns |
### Personal Development
| Skill | Purpose |
|-------|---------|
| `ppv` | PPV life design: vision, identity, pillars, weekly actions |
| `llm-council` | Multi-model deliberation for complex decisions |
| `blind-spot-finder` | Multi-model analysis for finding blind spots |
资料来源：[README.md]()
## Skill Invocation Patterns
After installation, skills are invoked using slash commands in the agent interface.
### Basic Invocation
```bash
/daily-plan
/weekly-plan "2024-01-15"
/health-check
/finance-overview
```
### Client-Focused Skills
```bash
/project-status "ACME"
/client-brief "Acme Corp"
/meeting-prep "John"
/customer-success-triage "Acme Corp"
```
### Planning Workflows
The planning skills (`daily-plan`, `weekly-plan`, `sprint-plan`) use the same underlying MCP tools:
1. Call `get_planning_context` with relevant include flags
2. Build the plan based on current cycle, backlog, and calendar
3. Call `apply_planning_patch` with `dryRun=false` to apply mutations
资料来源：[skills/daily-plan/SKILL.md]()
资料来源：[skills/weekly-plan/SKILL.md]()
资料来源：[skills/sprint-plan/SKILL.md]()
## Updating the Plugin
### Update Plugin Repository
```bash
cd /path/to/lifeos-plugin && git pull
```
### Update MCP Server
The MCP server auto-updates when using `@latest`:
```bash
npx @starascendin/lifeos-mcp@latest
```
Or pin to a specific version in `.mcp.json` to prevent unexpected updates.
资料来源：[README.md]()
## MCP Tools Overview
The installation provides access to 126 MCP tools for full CRUD operations:
| Category | Operations |
|----------|------------|
| Projects | Create, read, update, delete projects |
| Tasks/Issues | Full task lifecycle management |
| Cycles | Sprint/cycle planning and tracking |
| Phases | Project phase management |
| Clients | Client workspace and communications |
| People/Contacts | Contact management with AI insights |
| Notes | Note creation and retrieval |
| Voice Memos | Voice memo recording and analysis |
| Health | Oura Ring: sleep, activity, readiness, stress, SpO2, heart rate, workouts |
| Finance | Accounts, net worth, transactions, snapshots, daily spending |
| Habits | Habit tracking and streak management |
| Coaching | Session tracking and action items |
| PPV Life Design | Vision, identity, pillars, reflections, adjustments |
资料来源：[AGENTS.md]()
## Troubleshooting
### Environment Variables Not Recognized
Ensure environment variables are exported in the shell where the agent runs:
```bash
# Check if variables are set
echo $LIFEOS_CONVEX_URL
echo $LIFEOS_USER_ID
echo $LIFEOS_API_KEY
```
### MCP Server Connection Issues
Verify the Convex URL format is correct:
- Must be `https://*.convex.site`
- User ID must match an entry in the Convex Users table
- API key must be generated from LifeOS settings
### Skills Not Available
For Claude Code: Re-run the plugin installation command
For OpenCode: Verify the skills directory exists at `.claude/skills/lifeos/`
---
## Skills Overview
### 相关页面
相关主题：[Daily Workflows](#daily-workflows), [Review Workflows](#review-workflows), [Project Management](#project-management), [Health Integration (Oura Ring)](#health-integration), [Coaching System](#coaching-system)
相关源码文件
以下源码文件用于生成本页说明：
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
- [skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
- [skills/weekly-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
- [skills/sprint-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
- [skills/customer-success-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
- [skills/ppv/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/ppv/SKILL.md)
# Skills Overview
## Introduction
Skills are the core building blocks of the LifeOS Plugin, representing 37 pre-defined workflow skills that enable AI agents to interact with LifeOS data and execute productivity operations. Each skill is a structured instruction set that guides an AI agent through a specific workflow using the LifeOS MCP (Model Context Protocol) tools.
资料来源：[README.md:1]()
Skills serve as the human-readable workflow definitions that bridge AI agent reasoning with LifeOS data mutations. They encapsulate domain knowledge about productivity workflows—including planning, reviewing, client management, health tracking, and life design—into reusable, executable units.
## Architecture
```mermaid
graph TD
A[AI Agent] -->|Invokes| B[Skill /slash command]
B -->|Loads| C[SKILL.md Definition]
C -->|Directs| D[MCP Tools]
D -->|CRUD Operations| E[LifeOS Convex Backend]
E -->|Returns Data| D
D -->|Formats Response| F[User-Facing Report]
G[Alternative: MCP Protocol] -->|28 Prompts| H[Direct MCP Invocation]
H -->|Same Tools| E
```
The plugin provides two complementary interfaces:
| Interface Type | Count | Description |
|----------------|-------|-------------|
| Skills | 37 | Human-readable workflow definitions for slash command invocation |
| MCP Prompts | 28 | Same workflows exposed via MCP protocol for programmatic clients |
| MCP Tools | 126 | Full CRUD operations across all LifeOS domains |
资料来源：[AGENTS.md:1]()
## Skill Categories
Skills are organized into functional categories that map to different aspects of personal and professional productivity.
### Daily Workflows
Core daily planning and reflection skills that drive day-to-day execution.
| Skill | Command | Purpose |
|-------|---------|---------|
| daily-standup | `/daily-standup` | Morning briefing with agenda, tasks, and sprint progress |
| daily-plan | `/daily-plan` | Plan today with due dates, priorities, cycle assignments, and Daily Note updates |
| end-of-day | `/end-of-day` | EOD wrap-up with completion summary and tomorrow planning |
| capture | `/capture "thought"` | Quick capture of thoughts, tasks, or notes with auto-routing |
资料来源：[README.md:42-45]()
### Reviews
Periodic reflection and planning skills for maintaining strategic alignment.
| Skill | Command | Purpose |
|-------|---------|---------|
| weekly-review | `/weekly-review` | Completed work, in-progress items, sprint health |
| weekly-plan | `/weekly-plan` | Plan the week with current cycle, due dates, priorities, and note changes |
| monthly-review | `/monthly-review` | Accomplishments, project progress, next month planning |
| cycle-review | `/cycle-review` | Sprint review with rollover options |
| initiative-review | `/initiative-review 2026` | Yearly initiative progress by category |
资料来源：[README.md:46-51]()
### Project & Client Management
Skills for managing client relationships and project execution.
| Skill | Command | Purpose |
|-------|---------|---------|
| project-status | `/project-status ACME` | Phase breakdown, task stats, blockers |
| client-brief | `/client-brief "Acme Corp"` | Full client briefing with projects and comms |
| client-health | `/client-health` | Health dashboard across all clients |
| sprint-plan | `/sprint-plan` | Plan current cycle with goals, backlog pull, due dates, priorities |
| customer-success-triage | `/customer-success-triage "Acme Corp"` | Triage requests using chats, meetings, notes, and open work |
资料来源：[README.md:52-57]()
### People & Relationships
Skills for managing contacts, meetings, and relationship health.
| Skill | Command | Purpose |
|-------|---------|---------|
| contact-lookup | `/contact-lookup "John"` | Full contact dossier with AI insights |
| meeting-prep | `/meeting-prep "John"` | Prepare for meetings with full context |
| follow-ups | `/follow-ups` | Track follow-ups needed with people and clients |
| relationship-pulse | `/relationship-pulse` | Check on neglected relationships |
| context-switch | `/context-switch "Acme"` | Fast context loading for a client or project |
资料来源：[README.md:58-63]()
### Health & Fitness
Skills integrating with Oura Ring data for health monitoring.
| Skill | Command | Purpose |
|-------|---------|---------|
| health-check | `/health-check` | Quick Oura health overview: scores, trends |
| health-weekly | `/health-weekly` | Weekly health review with workouts |
| daily-training-report | `/daily-training-report` | Daily training report with health + habits |
| habit-check | `/habit-check` | Daily habit check-in, streaks, completions |
| screentime-report | `/screentime-report` | Screen time analysis and top apps |
资料来源：[AGENTS.md:1]()
### Finance
Skills for financial tracking and analysis.
| Skill | Command | Purpose |
|-------|---------|---------|
| finance-overview | `/finance-overview` | Net worth, accounts, trends |
| finance-spending | `/finance-spending` | Spending analysis and patterns |
### Coaching & Personal Development
Skills for coaching integration and personal growth tracking.
| Skill | Command | Purpose |
|-------|---------|---------|
| coaching-overview | `/coaching-overview` | Coaching profiles, sessions, action items |
| coaching-action-items | `/coaching-action-items` | Manage coaching action items |
| coaching-session-review | `/coaching-session-review` | Review coaching session insights |
| coach-memory | `/coach-memory` | View AI coach's accumulated knowledge |
| blind-spot-finder | `/blind-spot-finder` | Multi-model council to find blind spots |
| decision-framework | `/decision-framework` | Structured decision-making with experiments |
| llm-council | `/llm-council` | Multi-model deliberation for complex decisions |
### PPV Life Design
Skills for the Purpose, Priority, Vision (PPV) life design system.
| Skill | Command | Purpose |
|-------|---------|---------|
| ppv | `/ppv` | Manage vision, identity, pillars, projects, weekly actions, reflections, adjustments |
资料来源：[skills/ppv/SKILL.md:1]()
## Skill Structure
Each skill follows a standardized structure defined in `SKILL.md` files.
### Anatomy of a SKILL.md File
```yaml
---
name: skill-name
description: One-line description of what the skill does
---
# Detailed instructions follow
```
### Standard Execution Pattern
```mermaid
sequenceDiagram
participant U as User
participant A as AI Agent
participant M as MCP Tools
participant L as LifeOS
U->>A: Invoke skill /slash command
A->>M: Call get_* context tool(s)
M->>L: Query data
L->>M: Return context
M->>A: Context data
A->>A: Analyze & plan
A->>M: Call apply_* or update_* mutations
M->>L: Execute changes
L->>M: Confirmation
M->>A: Results
A->>U: Report summary
```
### Mutating vs. Read-Only Skills
Skills are classified by their effect on LifeOS data:
| Type | Characteristics | Examples |
|------|-----------------|----------|
| **Mutating** | Creates, updates, or deletes data | daily-plan, weekly-plan, sprint-plan, ppv |
| **Read-Only** | Only queries and reports | health-check, finance-overview, contact-lookup |
资料来源：[skills/daily-plan/SKILL.md:1]()
## MCP Tool Integration
Skills leverage the 126 MCP tools for data operations. The tools are organized by domain:
### Planning Tools
Used by daily-plan, weekly-plan, sprint-plan, and similar skills.
| Tool | Purpose |
|------|---------|
| `get_planning_context` | Retrieve comprehensive planning context including daily, weekly, current cycle, backlog, habits, and calendar |
| `apply_planning_patch` | Apply batch mutations (mode: "day", "week", or "cycle") |
| `create_issue` | Create new tasks |
| `schedule_issue` | Set due dates and schedules |
| `update_issue` | Modify task properties |
| `assign_issue_to_current_cycle` | Add work to active cycle |
| `set_top_priority` | Set today's top 3 priorities |
| `update_cycle_goals` | Modify current cycle objectives |
资料来源：[skills/daily-plan/SKILL.md:5-15]()
### Planning Patch Operations
The `apply_planning_patch` tool supports multiple operation types:
```json
{
"mode": "day" | "week" | "cycle",
"dryRun": false,
"operations": [
{ "type": "create_issue", "data": {...} },
{ "type": "schedule_issue", "issueId": "...", "dueDate": "..." },
{ "type": "update_issue", "issueId": "...", "changes": {...} },
{ "type": "assign_issue_to_current_cycle", "issueId": "..." },
{ "type": "set_top_priority", "issueIds": [...] },
{ "type": "update_cycle_goals", "goals": "..." },
{ "type": "save_daily_note", "content": "..." },
{ "type": "save_weekly_note", "content": "..." },
{ "type": "add_issue_comment", "issueId": "...", "comment": "..." }
]
}
```
### Domain-Specific Tool Categories
| Domain | Tool Count | Operations |
|--------|------------|------------|
| Projects | 20+ | CRUD, status, phases, statistics |
| Issues/Tasks | 30+ | CRUD, assignment, scheduling, priorities |
| Cycles | 10+ | CRUD, goals, planning |
| Clients | 15+ | Workspace, health, notes |
| People/Contacts | 10+ | Lookup, context graphs |
| Health (Oura) | 30+ | Sleep, activity, readiness, stress, workouts, VO2 max |
| Finance | 15+ | Accounts, net worth, transactions, spending |
| Notes & Memos | 20+ | Voice memos, AI summaries, Beeper/Granola integration |
| Coaching | 10+ | Action items, memories, PPV management |
资料来源：[AGENTS.md:1]()
## Installation & Setup
### Claude Code
```bash
claude plugin add github:starascendin/lifeos-plugin
```
资料来源：[README.md:10]()
### OpenCode
```bash
# Option A: Clone and copy
git clone git@github.com:starascendin/lifeos-plugin.git /tmp/life
# Option B: Symlink
ln -s /path/to/lifeos-plugin/skills .claude/skills/lifeos
```
资料来源：[AGENTS.md:1]()
### MCP Server Configuration
Configure the MCP server in your agent's settings:
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@latest",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
### Environment Variables
| Variable | Description |
|----------|-------------|
| `LIFEOS_CONVEX_URL` | Convex deployment URL (`.convex.site`) |
| `LIFEOS_USER_ID` | LifeOS user ID from Convex dashboard |
| `LIFEOS_API_KEY` | API key for authentication |
资料来源：[README.md:30-39]()
## Example Skill: daily-plan
The `daily-plan` skill demonstrates the typical skill execution flow:
```mermaid
graph TD
A[Invoke /daily-plan] --> B[get_planning_context]
B --> C{Include Options}
C -->|daily=true| D[Today's tasks & agenda]
C -->|weekly=true| E[This week's context]
C -->|currentCycle=true| F[Active cycle data]
C -->|backlog=true| G[Available backlog]
C -->|habits=true| H[Habit data]
C -->|dailyFields=true| I[Daily fields]
C -->|calendar=true| J[Calendar events]
C -->|voiceMemos=true| K[Recent memos]
D --> L[Build Day Plan]
E --> L
F --> L
G --> L
H --> L
I --> L
J --> L
K --> L
L --> M[Select Top 3 Priorities]
L --> N[Schedule Tasks by dueDate]
L --> O[Pull Backlog into Cycle]
L --> P[Update Cycle Goals if Needed]
P --> Q[apply_planning_patch mode=day]
M --> Q
N --> Q
O --> Q
Q --> R[Mutations Applied]
R --> S[Report: Top 3, Changes, Notes]
```
资料来源：[skills/daily-plan/SKILL.md:1]()
## Example Skill: customer-success-triage
The `customer-success-triage` skill shows a domain-specific workflow:
```mermaid
graph TD
A[Invoke /customer-success-triage "Acme Corp"] --> B[get_client_success_workspace]
B --> C{Workspace Contents}
C --> D[recentThreads]
C --> E[recentMeetings]
C --> F[notes]
C --> G[openTasks]
C --> H[projects]
D --> I[Drill Down if Needed]
E --> I
F --> I
G --> I
H --> I
I --> J[get_beeper_thread_messages]
I --> K[get_fathom_meeting]
I --> L[get_granola_meeting]
I --> M[get_client_notes]
J --> N{Classify Findings}
K --> N
L --> N
M --> N
N --> O[New Requirements]
N --> P[Follow-Ups]
N --> Q[Risks / Blockers]
N --> R[Already Tracked]
O --> S[create_client_note]
P --> S
Q --> S
R --> S
S --> T[Report Classification]
```
资料来源：[skills/customer-success-triage/SKILL.md:1]()
## PPV Life Design System
The PPV (Purpose, Priority, Vision) skill implements a comprehensive life design system:
### Data Model
```mermaid
graph TD
A[Vision] --> B[Identity]
A --> C[Pillars]
C --> D[Projects]
C --> E[Weekly Actions]
E --> F[Reflections]
F --> G[Adjustments]
G --> B
G --> C
G --> D
G --> E
```
### Vision Operations
- `get_ppv_workspace` — Retrieve all PPV data plus available LifeOS projects
- `get_active_vision_graph` — Unified graph of vision with linked projects, issues, and memos
- `upsert_ppv_vision` — Create or update vision (vivid, emotional, directional)
### Identity Operations
- `upsert_ppv_identity` — Manage core identities, beliefs, and behaviors
### Pillar Operations
- `create_ppv_pillar`, `update_ppv_pillar`, `delete_ppv_pillar` — Manage ongoing systems
### Execution Operations
- `create_ppv_weekly_action`, `update_ppv_weekly_action`, `delete_ppv_weekly_action` — Weekly concrete actions
### Learning Loop Operations
- `create_ppv_reflection` — Capture weekly energy, resistance, alignment, momentum
- `create_ppv_adjustment` — Update identity, pillars, projects, or actions based on reflection
资料来源：[skills/ppv/SKILL.md:1]()
## Updating
```bash
# Update the plugin repo
cd /path/to/lifeos-plugin && git pull
# Update the MCP server (auto-updates with npx @latest)
# Or pin a version in .mcp.json: "@starascendin/lifeos-mcp@0.7.0"
```
资料来源：[README.md:88-94]()
## Best Practices
1. **Mutating Skills Don't Ask for Confirmation** — Skills like `daily-plan`, `weekly-plan`, and `sprint-plan` are designed to execute immediately when invoked.
2. **Use Appropriate Planning Context** — Always include the relevant context flags when calling `get_planning_context`:
- Daily planning: `daily=true`, `currentCycle=true`, `habits=true`
- Weekly planning: `weekly=true`, `daily=true`, `currentCycle=true`, `backlog=true`
- Cycle planning: `currentCycle=true`, `backlog=true`, `weekly=true`, `daily=true`
3. **Avoid Duplicates** — When triaging or capturing, prefer updating existing notes/tasks over creating new ones.
4. **Link, Don't Duplicate** — PPV pillars should link to existing LifeOS projects via `projectIds` rather than creating parallel systems.
5. **Small, Concrete Weekly Actions** — PPV weekly actions should be identity-aligned and linkable to pillars or projects.
6. **One Useful Mutation** — Keep PPV changes focused; prefer one useful mutation over comprehensive restructuring.
资料来源：[skills/ppv/SKILL.md:10](), [skills/daily-plan/SKILL.md:24]()
## Summary
Skills are the primary interface through which AI agents interact with LifeOS. They provide:
- **37 pre-defined workflows** covering daily planning, reviews, client management, health, finance, coaching, and life design
- **Standardized structure** using SKILL.md files with clear execution patterns
- **MCP tool integration** leveraging 126 CRUD operations across all LifeOS domains
- **Two invocation methods** — slash commands for natural interaction and MCP prompts for programmatic access
- **Mutating and read-only variants** — Some skills only query data, others apply changes directly
The skills system enables AI agents to act as knowledgeable productivity assistants, executing complex multi-step workflows while maintaining consistency and best practices.
---
## Daily Workflows
### 相关页面
相关主题：[Review Workflows](#review-workflows), [Habits & Accountability](#habits-accountability), [Project Management](#project-management)
Relevant Source Files
以下源码文件用于生成本页说明：
- [skills/daily-standup/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-standup/SKILL.md)
- [skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
- [skills/end-of-day/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/end-of-day/SKILL.md)
- [skills/capture/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/capture/SKILL.md)
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
# Daily Workflows
## Overview
Daily Workflows in LifeOS provide a structured, AI-powered approach to managing day-to-day productivity. These four complementary skills form a complete daily rhythm: from morning preparation through execution to end-of-day reflection.
The workflows are designed to be **mutating** operations that directly modify LifeOS data through the MCP (Model Context Protocol) integration with Convex. They require no user confirmation once invoked—the system applies changes automatically based on AI-generated plans.
| Workflow | Purpose | Type |
|----------|---------|------|
| `daily-standup` | Morning briefing with agenda, tasks, and sprint progress | Read-only |
| `daily-plan` | Plan the day and apply mutations to due dates, priorities, cycles, and notes | Mutating |
| `end-of-day` | EOD wrap-up with completion summary and tomorrow planning | Mutating |
| `capture` | Quick capture of thoughts, tasks, or notes with auto-routing | Mutating |
资料来源：[README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
## Architecture
### Integration with LifeOS MCP
Daily Workflows leverage the LifeOS MCP server (`@starascendin/lifeos-mcp`) which exposes 126 tools for full CRUD operations across the LifeOS data model. All workflows communicate exclusively through this MCP interface.
```mermaid
graph TD
A[User/Agent] -->|Invoke Skill| B[Daily Workflow Skill]
B -->|MCP Tool Calls| C[LifeOS MCP Server]
C -->|HTTP/WebSocket| D[Convex Backend]
D -->|Real-time Sync| E[LifeOS Data Store]
F[Oura Ring] -->|Health Data| D
G[Calendar] -->|Schedule Data| D
H[Voice Memos] -->|Audio Data| D
```
资料来源：[AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
### Workflow Data Flow
```mermaid
graph LR
A[daily-standup] -->|Read Context| B[get_daily_agenda]
A -->|Read Tasks| C[get_todays_tasks]
A -->|Read Sprint| D[get_current_cycle]
E[daily-plan] -->|Read Context| F[get_planning_context]
E -->|Write Changes| G[apply_planning_patch]
H[end-of-day] -->|Write Summary| I[save_daily_note]
H -->|Plan Tomorrow| J[schedule_issue]
K[capture] -->|Quick Create| L[create_issue]
K -->|Route| M[assign_issue_to_current_cycle]
```
## Daily Standup
**Skill File:** `skills/daily-standup/SKILL.md`
### Purpose
The `daily-standup` workflow provides a concise morning briefing covering today's agenda, tasks due, and sprint progress. It is a **read-only** operation that does not modify any data.
### MCP Tools Used
| Tool | Purpose |
|------|---------|
| `get_daily_agenda` | Today's tasks, calendar events, top priorities |
| `get_todays_tasks` | Complete task list for today |
| `get_overdue_tasks` | Open tasks that are past their due date |
| `get_current_cycle` | Sprint progress and statistics |
资料来源：[skills/daily-standup/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-standup/SKILL.md)
### Output Format
The workflow synthesizes data into a standup-style briefing:
- **Today's Focus**: Top 3 priorities
- **Tasks Due**: Tasks due today with priority levels
- **Overdue**: Late tasks requiring immediate triage
- **Sprint Progress**: Cycle completion percentage and key statistics
- **Calendar**: Scheduled meetings and events
### Date Parameter
When `$ARGUMENTS` contains a date, the workflow uses that date instead of the current date for historical or future-day standups.
## Daily Plan
**Skill File:** `skills/daily-plan/SKILL.md`
### Purpose
The `daily-plan` workflow plans the day and applies mutations to LifeOS. This is a **mutating workflow** that directly modifies due dates, priorities, cycle assignments, and Daily Notes.
### Execution Steps
```mermaid
graph TD
1[Call get_planning_context] --> 2[Build Day Plan]
2 --> 3[Pick Top 3 Priorities]
2 --> 4[Schedule Tasks by dueDate]
2 --> 5[Pull Backlog into Cycle]
2 --> 6[Update Cycle Goals if Needed]
3 --> 7[Call apply_planning_patch]
4 --> 7
5 --> 7
6 --> 7
7 --> 8[Report Changes]
```
资料来源：[skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
### Planning Context Parameters
When calling `get_planning_context`, the workflow includes:
| Parameter | Value | Purpose |
|-----------|-------|---------|
| `date` | From `$ARGUMENTS` or today | Target planning date |
| `include.daily` | `true` | Daily context |
| `include.weekly` | `true` | Weekly overview |
| `include.currentCycle` | `true` | Sprint/cycle data |
| `include.backlog` | `true` | Available backlog items |
| `include.habits` | `true` | Habit tracking |
| `include.dailyFields` | `true` | Daily field configurations |
| `include.calendar` | `true` | Calendar events |
| `include.voiceMemos` | `true` | Recent voice memos |
### Available Mutations
| Operation | Use Case |
|-----------|----------|
| `create_issue` | New tasks discovered during planning |
| `schedule_issue` | Set due dates for scheduled work |
| `update_issue` | Modify status, priority, estimate, title |
| `assign_issue_to_current_cycle` | Pull backlog into active cycle |
| `set_top_priority` | Designate today's top 3 |
| `update_cycle_goals` | Adjust cycle focus when needed |
| `save_daily_note` | Write readable plan to Agenda Daily Note |
| `add_issue_comment` | Document planning rationale on tasks |
### Post-Execution Report
After applying changes, the workflow reports:
- Today's top 3 priorities
- Tasks created, scheduled, or reassigned
- Current cycle modifications
- Daily Note content saved
## End of Day
**Skill File:** `skills/end-of-day/SKILL.md`
### Purpose
The `end-of-day` workflow provides EOD wrap-up with completion summary and tomorrow planning. This completes the daily productivity loop by reviewing accomplishments and preparing for the next day.
### Core Functions
1. **Completion Review**: Summarize what was accomplished today
2. **Tomorrow Planning**: Schedule and prioritize work for the next day
3. **Daily Note Updates**: Save EOD reflections and plans
4. **Cycle Sync**: Ensure cycle progress is accurately tracked
资料来源：[skills/end-of-day/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/end-of-day/SKILL.md)
## Capture
**Skill File:** `skills/capture/SKILL.md`
### Purpose
The `capture` workflow enables quick capture of thoughts, tasks, or notes with automatic routing. It is designed for rapid input during the day when users encounter items that need to be tracked.
### Auto-Routing Logic
The capture workflow uses AI to determine:
- Whether the capture is a task, note, or reference
- Appropriate project/cycle assignment
- Priority level based on content
- Whether it belongs in the current cycle or backlog
### Available Operations
| Operation | Purpose |
|-----------|---------|
| `create_issue` | Convert capture to tracked task |
| `assign_issue_to_current_cycle` | Route to active sprint |
| `create_note` | Save as reference note |
| `add_issue_comment` | Attach to existing task |
资料来源：[skills/capture/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/capture/SKILL.md)
## MCP Tools Reference
All Daily Workflows depend on these core MCP tools from the 126 available:
### Planning Context
| Tool | Returns |
|------|---------|
| `get_planning_context` | Unified context for day/week/cycle planning |
| `get_daily_agenda` | Today's complete agenda |
| `get_todays_tasks` | Task list filtered for today |
| `get_current_cycle` | Active sprint/cycle details |
### Mutations
| Tool | Parameters |
|------|------------|
| `apply_planning_patch` | `mode`: "day" \| "week" \| "cycle", `dryRun`: boolean |
| `create_issue` | `title`, `projectId`, `priority`, `dueDate`, `estimate` |
| `schedule_issue` | `issueId`, `dueDate` |
| `update_issue` | `issueId`, fields to update |
| `assign_issue_to_current_cycle` | `issueId` |
| `set_top_priority` | Array of issue IDs |
| `save_daily_note` | `date`, `content` |
资料来源：[AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
## Configuration
### Environment Variables
```bash
export LIFEOS_CONVEX_URL=https://your-app.convex.site
export LIFEOS_USER_ID=your-user-id
export LIFEOS_API_KEY=your-api-key
```
### MCP Server Configuration
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@latest",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
资料来源：[README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
## Daily Rhythm Summary
```mermaid
graph LR
subgraph Morning
A[daily-standup] --> B[daily-plan]
end
subgraph Day
C[Execute Tasks]
D[capture] -->|Ad-hoc| C
end
subgraph Evening
E[end-of-day]
end
B --> C
C --> E
E -->|Tomorrow| B
```
| Phase | Workflow | Action |
|-------|----------|--------|
| Morning (start) | `daily-standup` | Read context, understand the day |
| Morning (plan) | `daily-plan` | Mutate tasks, set priorities |
| Throughout day | `capture` | Quick input, auto-routing |
| End of day | `end-of-day` | Review, plan tomorrow |
## Skill Invocation
### Claude Code
```bash
claude plugin add github:starascendin/lifeos-plugin
# Then invoke:
/daily-standup
/daily-plan
/end-of-day
/capture
```
### OpenCode
Skills are read from `.claude/skills/` directory. Symlink or copy:
```bash
ln -s /path/to/lifeos-plugin/skills .claude/skills/lifeos
---
## Habits & Accountability
### 相关页面
相关主题：[Daily Workflows](#daily-workflows), [Health Integration (Oura Ring)](#health-integration), [Coaching System](#coaching-system)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/habit-check/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/habit-check/SKILL.md)
- [skills/daily-training-report/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-training-report/SKILL.md)
# Habits & Accountability
## Overview
The **Habits & Accountability** system in LifeOS is a core productivity feature that enables users to track daily habits, maintain streaks, and stay accountable to their personal commitments. This system integrates with the broader LifeOS ecosystem, connecting habit data to health metrics, coaching insights, and daily planning workflows.
The habit system serves three primary purposes:
1. **Tracking** — Recording habit completions on a daily basis
2. **Streaks** — Motivating consistent behavior through streak counters
3. **Accountability** — Providing direct, actionable feedback when habits are missed or at risk
资料来源：[skills/habit-check/SKILL.md:1-3]()
## Architecture
The Habits & Accountability system consists of three interconnected layers:
```mermaid
graph TD
A[User Actions] --> B[Habit Check-in]
B --> C[Streak Calculator]
C --> D{Streak Status}
D -->|3+ days| E[Streak Alert]
D -->|Broken| F[Streak Broken Alert]
D -->|Safe| G[Normal Tracking]
H[get_habits] --> I[Habit Dashboard]
J[get_habits_for_date] --> I
K[check_in_habit] --> B
I --> L[Daily Training Report]
I --> M[Weekly Planning]
I --> N[Blind Spot Finder]
style E fill:#ff6b6b
style F fill:#ee5a24
```
### Core Components
| Component | Purpose | Source File |
|-----------|---------|-------------|
| Habit Check-in | Mark habits as completed for a specific date | `habit-check/SKILL.md` |
| Habit Dashboard | Display all habits, statuses, and streaks | `habit-check/SKILL.md` |
| Daily Training Report | Aggregate habit data with health metrics | `daily-training-report/SKILL.md` |
| Streak Alerts | Warn users when streaks are at risk | `habit-check/SKILL.md` |
资料来源：[skills/habit-check/SKILL.md:1-40]()
## Habit Check Skill
The `habit-check` skill is the primary interface for daily habit management. It provides an interactive daily check-in experience with direct accountability messaging.
### Workflow
```mermaid
graph LR
A[Call get_habits_for_date] --> B[Call get_habits]
B --> C[Build Dashboard]
C --> D{Habits Complete?}
D -->|Yes| E[Celebrate]
D -->|No| F[Flag Pending]
F --> G{Streak >= 3?}
G -->|Yes| H[Streak At Risk Alert]
G -->|No| I[Normal Reminder]
```
### Data Fetching
The skill retrieves habit data through two parallel calls:
| API Call | Parameters | Purpose |
|----------|------------|---------|
| `get_habits_for_date` | `date` (today or `$ARGUMENTS`) | Scheduled habits and their completion status |
| `get_habits` | none | Full habit list with streak data |
资料来源：[skills/habit-check/SKILL.md:14-20]()
### Dashboard Output
The habit dashboard presents information in four sections:
**1. Today's Habits**
Each habit displays:
- Icon + Name
- Status: `completed` / `pending` / `skipped` / `incomplete`
- Current streak (e.g., "🔥 12 days")
**2. Completion Rate**
Format: `X/Y habits completed today (percentage)`
**3. Streak Alerts**
| Condition | Action |
|-----------|--------|
| Active streak (3+ days) + pending | Flag as "streak at risk" |
| Streak broken yesterday | Call out explicitly |
**4. Never Skip a Rep**
When habits are pending:
- Direct accountability message: "You haven't done X yet today. Your streak is at Y days. Don't break it."
When all habits are done:
- Celebration message: "All habits completed. No reps skipped."
资料来源：[skills/habit-check/SKILL.md:22-38]()
### Interactive Features
Users can mark habits completed during the check-in by specifying habit names in `$ARGUMENTS`:
```
Input: "mark meditation done"
Action: Calls check_in_habit for today's date
```
## Daily Training Report Integration
The `daily-training-report` skill aggregates habit data as part of a comprehensive personal performance overview. This demonstrates how habit tracking connects to the broader productivity system.
### Habit Data Sources
The daily training report pulls habit data from three endpoints:
| API Call | Date Parameter | Data Retrieved |
|----------|----------------|----------------|
| `get_habits_for_date` | yesterday's date | Yesterday's completion status |
| `get_habits_for_date` | today's date | Today's scheduled habits |
| `get_habits` | none | Streak overview for all habits |
资料来源：[skills/daily-training-report/SKILL.md:8-11]()
### Report Structure
The habit component of the daily training report follows this structure:
```mermaid
graph TD
A[Daily Training Report] --> B[YESTERDAY'S RESULTS]
A --> C[TODAY'S GAME PLAN]
B --> B1[Habit Scorecard: X/Y]
B --> B2[Streaks Maintained]
B --> B3[Streaks Broken]
B --> B4[Health Scores]
B --> B5[Day Rating]
C --> C1[Top 3 Priorities]
C --> C2[Today's Scheduled Habits]
C --> C3[Streak Counts]
```
**Yesterday's Results Section:**
- Habit scorecard: `X/Y completed` with list of each habit and status
- Streaks maintained or broken (broken streaks called out explicitly)
- Health scores from Oura integration
- Day rating based on habit completion + health scores
**Today's Game Plan Section:**
- Top 3 priorities from agenda + top priority tasks
- Habits scheduled for today with streak counts
资料来源：[skills/daily-training-report/SKILL.md:13-24]()
## MCP Tools Reference
The following MCP tools are used for habit management:
| Tool | Purpose | Used In |
|------|---------|---------|
| `get_habits` | Retrieve all habits with streak data | habit-check, daily-training-report |
| `get_habits_for_date` | Get habits scheduled for a specific date | habit-check, daily-training-report |
| `check_in_habit` | Mark a habit as completed | habit-check |
### get_habits_for_date Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `date` | string | Yes | The date to check habits for (ISO format or "today"/"yesterday") |
### get_habits Response
The `get_habits` call returns:
- All defined habits
- Completion status for the queried date
- Streak counters for each habit
- Scheduled frequency (daily, specific days, etc.)
## Accountability Philosophy
The Habits & Accountability system follows a "personal trainer" philosophy:
| Principle | Implementation |
|-----------|----------------|
| Direct messaging | No fluff or excessive encouragement |
| Streak protection | Explicit alerts when streaks are at risk |
| Immediate feedback | Real-time status updates during check-in |
| Celebration | Acknowledgment when all habits are completed |
| Accountability | Call out missed reps directly |
The tone is described as: "Direct, like a personal trainer. No fluff. Celebrate wins, call out misses."
资料来源：[skills/habit-check/SKILL.md:38-40]()
## Related Skills
The habit system integrates with several other LifeOS skills:
| Skill | Integration Point |
|-------|-------------------|
| `daily-plan` | Habits included in planning context via `include.habits=true` |
| `weekly-plan` | Habits included in weekly planning context |
| `sprint-plan` | Habit compliance affects energy/focus capacity |
| `blind-spot-finder` | Uses habit completion rates to identify patterns |
| `health-weekly` | Habit data complements health metrics |
资料来源：[skills/daily-plan/SKILL.md:9](), [skills/weekly-plan/SKILL.md:9](), [skills/blind-spot-finder/SKILL.md:10]()
## Data Flow
```mermaid
sequenceDiagram
participant User
participant habit-check
participant MCP Tools
participant LifeOS
User->>habit-check: Invoke skill
habit-check->>MCP Tools: get_habits_for_date(today)
MCP Tools->>LifeOS: Query habit table
LifeOS->>MCP Tools: Habit status array
MCP Tools->>habit-check: Response
habit-check->>MCP Tools: get_habits
MCP Tools->>LifeOS: Query all habits with streaks
LifeOS->>MCP Tools: Full habit list
MCP Tools->>habit-check: Response
habit-check->>habit-check: Build dashboard
habit-check->>User: Display results
alt User marks complete
User->>habit-check: "mark X done"
habit-check->>MCP Tools: check_in_habit(habitId, today)
MCP Tools->>LifeOS: Update completion record
LifeOS->>MCP Tools: Success
MCP Tools->>habit-check: Confirmation
habit-check->>User: Updated dashboard
end
```
## Best Practices
1. **Daily Check-in** — Run `habit-check` each morning to review and update habit status
2. **Streak Awareness** — Pay attention to "streak at risk" alerts to maintain momentum
3. **Comprehensive View** — Use `daily-training-report` weekly to see habit patterns in context
4. **Integration** — Reference habit data in planning sessions for realistic scheduling
---
## Health Integration (Oura Ring)
### 相关页面
相关主题：[Habits & Accountability](#habits-accountability), [Daily Workflows](#daily-workflows), [Review Workflows](#review-workflows)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/health-check/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/health-check/SKILL.md)
- [skills/health-weekly/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/health-weekly/SKILL.md)
- [skills/daily-training-report/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-training-report/SKILL.md)
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
# Health Integration (Oura Ring)
## Overview
The Health Integration system in LifeOS plugin provides comprehensive biometric data synchronization with Oura Ring devices. This integration aggregates sleep analysis, activity tracking, readiness scoring, stress measurement, and cardiovascular health metrics into a unified health dashboard accessible through MCP (Model Context Protocol) tools.
The system serves as the health data layer for 37 workflow skills, enabling AI agents to make informed recommendations based on real-time biometric data. It transforms raw Oura Ring measurements into actionable health insights for daily planning, coaching, and personal optimization workflows.
## Architecture
```mermaid
graph TD
subgraph "Data Sources"
OR[Oura Ring Device]
end
subgraph "LifeOS MCP Server"
HMC[Health MCP Tools]
SK[Skills Layer]
end
subgraph "Health Data Categories"
SL[Sleep]
AC[Activity]
RD[Readiness]
ST[Stress]
HR[Heart Rate]
RS[Resilience]
FT[Fitness]
OX[Oxygen]
end
subgraph "Consuming Skills"
HC[health-check]
HW[health-weekly]
DT[daily-training-report]
end
OR --> HMC
HMC --> SK
SK --> HC
SK --> HW
SK --> DT
HMC --> SL
HMC --> AC
HMC --> RD
HMC --> ST
HMC --> HR
HMC --> RS
HMC --> FT
HMC --> OX
```
资料来源：[README.md:1-40]()
## Available Health MCP Tools
The plugin exposes 10 dedicated health MCP tools that retrieve Oura Ring data. All tools accept a `days` parameter to specify the lookback window.
### Health Data Retrieval Tools
| Tool Name | Purpose | Key Metrics |
|-----------|---------|-------------|
| `get_health_sleep` | Sleep quality analysis | Scores, durations, bedtime, breath rate, restless periods |
| `get_health_activity` | Physical activity tracking | Activity scores, steps, active calories |
| `get_health_readiness` | Daily readiness assessment | Readiness scores, trends |
| `get_health_stress` | Stress and recovery balance | Stress levels, recovery data |
| `get_health_workouts` | Exercise history | Workout type, duration, intensity |
| `get_health_heart_rate` | Cardiovascular metrics | Resting HR, HRV trends |
| `get_health_resilience` | Resilience levels | Daily resilience, contributors |
| `get_health_vo2_max` | Aerobic capacity | VO2 max estimates |
| `get_health_cardio_age` | Cardiovascular age | Cardiovascular age vs actual |
| `get_health_spo2` | Blood oxygen | SpO2 levels, breathing disturbance index |
资料来源：[skills/health-check/SKILL.md:1-30]()
## Available Health Skills
### Health Check
A quick daily health overview that pulls 7 days of biometric data.
**Invocation:** `health-check [days]`
**Data Sources Called:**
1. `get_health_sleep` — 7 days
2. `get_health_activity` — 7 days
3. `get_health_readiness` — 7 days
4. `get_health_heart_rate` — 7 days
5. `get_health_resilience` — 7 days
6. `get_health_vo2_max` — 7 days
7. `get_health_cardio_age` — 7 days
资料来源：[skills/health-check/SKILL.md:1-35]()
**Output Structure:**
| Section | Content |
|---------|---------|
| Overall Status | Quick assessment (great / good / needs attention) |
| Sleep | Average score, duration trend, bedtime consistency, breath rate |
| Activity | Average score, daily steps, active calories |
| Readiness | Average score, trend direction |
| Heart Rate | Resting HR trend, HRV |
| Resilience | Current level and trend |
| Fitness | VO2 max trend, cardiovascular age comparison |
| Insights | 2-3 actionable observations |
```mermaid
graph LR
A[health-check] --> B[7-Day Window]
B --> C[Aggregate Data]
C --> D[Trend Analysis]
D --> E[Concise Dashboard]
E --> F[Actionable Insights]
```
### Health Weekly
A comprehensive 7-day rolling health review that analyzes 14 days of data for deeper trend analysis.
**Invocation:** `health-weekly`
**Data Sources Called:**
1. `get_health_sleep` — 14 days
2. `get_health_activity` — 14 days
3. `get_health_readiness` — 14 days
4. `get_health_stress` — 14 days
5. `get_health_workouts` — 14 days
6. `get_health_heart_rate` — 14 days
7. `get_health_resilience` — 14 days
8. `get_health_vo2_max` — 14 days
9. `get_health_cardio_age` — 14 days
10. `get_health_spo2` — 14 days
资料来源：[skills/health-weekly/SKILL.md:1-45]()
**Output Structure:**
| Section | Metrics |
|---------|--------|
| Sleep Quality | Weekly averages, best/worst nights, deep/REM balance, bedtime consistency, breath rate |
| Activity Patterns | Step averages, active vs rest days, calorie burn |
| Readiness & Recovery | Score trends, stress vs recovery balance |
| Resilience | Daily levels trend, contributor breakdown (sleep recovery, daytime recovery, stress) |
| Fitness | VO2 max trend, cardiovascular age, week-over-week changes |
| Workouts | Workout history with display names |
```mermaid
graph TD
A[health-weekly] --> B[14-Day Window]
B --> C[Multi-Source Aggregation]
C --> D[Category Analysis]
D --> E[Trend Detection]
E --> F[Weekly Report]
F --> G[Recovery Insights]
F --> H[Fitness Assessment]
```
### Daily Training Report
A comprehensive daily briefing that combines health data with habit tracking and task management.
**Invocation:** `daily-training-report`
**Workflow:**
```mermaid
graph TD
subgraph "Data Collection"
A1[Yesterday's Habits] --> D[Synthesize Report]
A2[Today's Habits] --> D
A3[All Habits] --> D
A4[Sleep 1 day] --> D
A5[Readiness 1 day] --> D
A6[Activity 1 day] --> D
A7[Today's Agenda] --> D
A8[Today's Tasks] --> D
A9[Initiatives] --> D
A10[Coaching Items] --> D
end
subgraph "Synthesis"
D --> E[YESTERDAY'S RESULTS]
D --> F[TODAY'S GAME PLAN]
D --> G[HABIT SCORECARD]
D --> H[STREAK STATUS]
end
```
**Report Sections:**
| Section | Content |
|---------|---------|
| Yesterday's Results | Habit scorecard, streaks, health scores, day rating |
| Today's Game Plan | Top 3 priorities, scheduled habits with streak counts |
| Health Integration | Sleep/Readiness/Activity scores from Oura Ring |
资料来源：[skills/daily-training-report/SKILL.md:1-50]()
## Data Flow
```mermaid
sequenceDiagram
participant User
participant Skill
participant MCP_Tools
participant Convex
participant Oura
User->>Skill: Invoke health skill
Skill->>MCP_Tools: Call get_health_*
MCP_Tools->>Convex: Fetch data
Convex->>Oura: Request sync
Oura-->>Convex: Biometric data
Convex-->>MCP_Tools: Processed metrics
MCP_Tools-->>Skill: Health data array
Skill->>Skill: Aggregate & analyze
Skill-->>User: Formatted report
```
## Health Metrics Reference
### Sleep Metrics
| Metric | Description | Used By |
|--------|-------------|---------|
| Sleep score | Overall 0-100 quality score | health-check, health-weekly |
| Duration | Total sleep time in hours | health-check, health-weekly |
| Bedtime | Sleep onset time | health-weekly |
| Breath rate | Average breathing during sleep | health-check, health-weekly |
| Deep sleep | Deep sleep duration | health-weekly |
| REM sleep | REM duration | health-weekly |
| Restless periods | Wake episodes during sleep | health-weekly |
### Activity Metrics
| Metric | Description | Used By |
|--------|-------------|---------|
| Activity score | Daily activity rating | health-check, health-weekly |
| Steps | Daily step count | health-check, health-weekly |
| Active calories | Calories burned through activity | health-check, health-weekly |
| Active vs rest days | Day type classification | health-weekly |
### Readiness Metrics
| Metric | Description | Used By |
|--------|-------------|---------|
| Readiness score | Overall readiness 0-100 | health-check, health-weekly, daily-training-report |
| Trend direction | Improving/declining/stable | health-check |
| Temperature trend | Body temperature patterns | health-weekly |
### Cardiovascular Metrics
| Metric | Description | Used By |
|--------|-------------|---------|
| Resting heart rate | Minimum HR during rest | health-check, health-weekly |
| HRV | Heart rate variability | health-check |
| VO2 max | Maximum oxygen uptake | health-check, health-weekly |
| Cardiovascular age | Estimated cardiovascular age | health-check, health-weekly |
| SpO2 | Blood oxygen saturation | health-weekly |
### Resilience Metrics
| Metric | Description | Used By |
|--------|-------------|---------|
| Resilience level | Daily resilience score | health-check, health-weekly |
| Sleep recovery contribution | Sleep's role in resilience | health-weekly |
| Daytime recovery contribution | Activity's role in resilience | health-weekly |
| Stress contribution | Stress's impact on resilience | health-weekly |
资料来源：[skills/health-check/SKILL.md:15-30]()
## Configuration
Health data requires the standard LifeOS MCP server connection configured with:
```json
{
"mcpServers": {
"lifeos": {
"command": "npx",
"args": [
"@starascendin/lifeos-mcp@latest",
"--url", "YOUR_CONVEX_URL",
"--user-id", "YOUR_USER_ID",
"--api-key", "YOUR_API_KEY"
]
}
}
}
```
Or environment variables:
```bash
export LIFEOS_CONVEX_URL=https://your-app.convex.site
export LIFEOS_USER_ID=your-user-id
export LIFEOS_API_KEY=your-api-key
```
资料来源：[README.md:45-60]()
## Usage Patterns
### Quick Health Check
```
User: health-check
→ Returns 7-day health dashboard with scores, trends, and 2-3 insights
```
### Extended Health Review
```
User: health-check 14
→ Returns 14-day health overview instead of default 7 days
```
### Weekly Deep Dive
```
User: health-weekly
→ Returns comprehensive 14-day analysis with recovery insights and fitness trends
```
### Training Integration
```
User: daily-training-report
→ Combines health data with habits, tasks, and coaching items for complete daily briefing
```
## Skill Comparison
| Feature | health-check | health-weekly | daily-training-report |
|---------|--------------|---------------|----------------------|
| Data window | 7 days (default) | 14 days | 1 day |
| Sleep analysis | ✓ | ✓✓ | ✓ |
| Activity analysis | ✓ | ✓✓ | ✓ |
| Readiness tracking | ✓ | ✓✓ | ✓ |
| Stress metrics | - | ✓ | - |
| Heart rate | ✓ | ✓ | - |
| Resilience | ✓ | ✓✓ | - |
| VO2 max | ✓ | ✓ | - |
| Cardio age | ✓ | ✓ | - |
| SpO2 | - | ✓ | - |
| Workouts | - | ✓ | - |
| Habit integration | - | - | ✓✓ |
| Task integration | - | - | ✓ |
| Initiative tracking | - | - | ✓ |
## Integration with Other Systems
Health data flows into multiple LifeOS subsystems:
```mermaid
graph LR
subgraph "Health Data"
H[Oura Ring]
end
subgraph "Integrated Systems"
D[Daily Planning]
C[Coaching]
PP[PPV Life Design]
T[Task Management]
end
H --> D
H --> C
H --> PP
H --> T
D -->|Affects| D1[Priority Setting]
D -->|Affects| D2[Due Dates]
C -->|Drives| C1[Action Items]
PP -->|Influences| PP1[Energy Levels]
T -->|Adjusts| T1[Capacity Planning]
```
### Daily Training Report Integration
The `daily-training-report` skill demonstrates deep integration, combining:
- **Habit compliance** data with health scores
- **Streak tracking** synchronized with biometric trends
- **Initiative progress** aligned with energy levels
- **Coaching action items** based on health patterns
资料来源：[skills/daily-training-report/SKILL.md:1-50]()
## Best Practices
1. **Use health-check for daily standups** — Quick 7-day snapshot provides context without overwhelming detail
2. **Reserve health-weekly for planning sessions** — The 14-day window reveals trends better suited for strategic decisions
3. **Incorporate health data into daily-training-report** — Biometric context enhances habit coaching effectiveness
4. **Review resilience metrics weekly** — Sleep recovery, daytime recovery, and stress contributions reveal optimization opportunities
5. **Monitor VO2 max trends monthly** — Cardiovascular fitness changes slowly but meaningfully over 4-week periods
---
## Project Management
### 相关页面
相关主题：[Client Management](#client-management), [Review Workflows](#review-workflows), [Daily Workflows](#daily-workflows)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/sprint-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
- [skills/weekly-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
- [skills/daily-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
- [skills/daily-standup/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-standup/SKILL.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
# Project Management
Project Management in LifeOS is a comprehensive framework for managing work across projects, sprints (cycles), initiatives, and clients. It integrates with the Convex-powered personal productivity OS to provide full CRUD operations for projects, tasks/issues, cycles, phases, clients, and people/contacts through 126 MCP tools.
## Overview
The Project Management system operates on multiple levels:
| Level | Scope | Tools Available |
|-------|-------|-----------------|
| **Initiative** | Yearly goals by category | Progress tracking, initiative review |
| **Cycle/Sprint** | Current sprint planning and execution | Cycle goals, backlog pull, due dates, priorities |
| **Weekly** | Week planning across projects | Task scheduling, cycle assignments, note updates |
| **Daily** | Day-to-day execution | Top priorities, due dates, daily notes |
| **Project** | Phase breakdown, task stats, blockers | Status reporting, project metrics |
| **Client** | Client projects, communications, health | Briefs, health dashboards, triage |
## Core Architecture
```mermaid
graph TD
A[LifeOS Plugin] --> B[Planning Context API]
A --> C[Planning Patch API]
B --> D[Convex Backend]
C --> D
E[get_planning_context] --> F[daily
weekly
currentCycle
backlog
habits
calendar
voiceMemos]
G[apply_planning_patch] --> H[mode: day|week|cycle]
H --> I[Mutations]
I --> J[create_issue
schedule_issue
update_issue
assign_to_cycle
set_top_priority
update_cycle_goals
save_daily_note
save_weekly_note]
```
## Planning Workflow
### Step 1: Gather Planning Context
The foundation of all project management operations is `get_planning_context`. This single API call aggregates data across multiple dimensions:
| Parameter | Values | Description |
|-----------|--------|-------------|
| `date` | ISO date string | Target date for daily planning |
| `weekStartDate` | ISO date string | Week start for weekly planning |
| `include.daily` | `true` | Include daily agenda and tasks |
| `include.weekly` | `true` | Include weekly view |
| `include.currentCycle` | `true` | Include active sprint/cycle data |
| `include.backlog` | `true` | Include backlog items |
| `include.habits` | `true` | Include habit data |
| `include.dailyFields` | `true` | Include daily custom fields |
| `include.calendar` | `true` | Include calendar events |
| `include.voiceMemos` | `true` | Include voice memos |
资料来源：[skills/daily-plan/SKILL.md:8-18]()
### Step 2: Apply Planning Mutations
After analyzing the context, mutations are applied via `apply_planning_patch` with three modes:
| Mode | Use Case | Scope |
|------|----------|-------|
| `day` | Daily execution planning | Today's top 3, due dates, daily note |
| `week` | Week planning | Schedule across week, cycle assignments |
| `cycle` | Sprint planning | Cycle goals, backlog pull, capacity |
## Project Management Skills
### Sprint Planning (`/sprint-plan`)
The sprint-plan skill manages the current cycle with mutating operations:
1. Fetch planning context with current cycle and backlog
2. Build cycle plan with goal updates and backlog prioritization
3. Apply mutations with `mode="cycle"`
**Key Mutations:**
```javascript
// Assign work to current cycle
assign_issue_to_current_cycle(issueId, cycleId)
// Update cycle goals
update_cycle_goals(cycleId, goals)
// Schedule work with due dates
schedule_issue(issueId, dueDate)
// Set immediate priorities
set_top_priority([issueId1, issueId2, issueId3])
```
资料来源：[skills/sprint-plan/SKILL.md:1-45]()
### Weekly Planning (`/weekly-plan`)
Weekly planning operates at a broader scope, scheduling work across multiple days:
```mermaid
graph LR
A[Week Start] --> B[Update Cycle Goals]
B --> C[Pull Backlog Items]
C --> D[Schedule Due Dates]
D --> E[Set Top Priorities]
E --> F[Save Weekly Note]
```
**Workflow:**
1. Call `get_planning_context` with `weekStartDate`
2. Update active cycle goals when needed
3. Assign backlog tasks to current cycle
4. Schedule work across the week using `dueDate`
5. Set near-term top priorities
6. Call `apply_planning_patch` with `mode="week"` and `dryRun=false`
资料来源：[skills/weekly-plan/SKILL.md:1-40]()
### Daily Planning (`/daily-plan`)
Daily planning focuses on immediate execution:
| Priority Level | Description |
|----------------|-------------|
| Top 3 | Must-complete items for today |
| Due Today | Tasks with today's due date |
| Overdue | Late tasks requiring triage |
| Scheduled | Pre-scheduled calendar work |
**Mutations Available:**
- `create_issue` - New tasks
- `schedule_issue` - Due date changes
- `update_issue` - Status, priority, estimate, title
- `assign_issue_to_current_cycle` - Cycle reassignment
- `set_top_priority` - Today's focus
- `update_cycle_goals` - Active cycle changes
- `save_daily_note` - Write to Agenda Daily Note
- `add_issue_comment` - Planning rationale
资料来源：[skills/daily-plan/SKILL.md:1-45]()
### Daily Standup (`/daily-standup`)
Quick briefing for daily synchronization:
```mermaid
graph TD
A[Daily Standup] --> B[get_daily_agenda]
A --> C[get_todays_tasks]
A --> D[get_overdue_tasks]
A --> E[get_current_cycle]
B --> F[Today's Focus]
C --> G[Tasks Due]
D --> H[Overdue Items]
E --> I[Sprint Progress]
```
**Output Sections:**
- **Today's Focus**: Top 3 priorities
- **Tasks Due**: Tasks due today with priority
- **Overdue**: Late tasks needing triage
- **Sprint Progress**: Cycle completion percentage and stats
- **Calendar**: Meetings and events
资料来源：[skills/daily-standup/SKILL.md:1-35]()
## Client & Project Reporting
### Project Status (`/project-status`)
Provides phase breakdown, task statistics, and blocker identification:
```mermaid
graph TD
A[Project Status] --> B[Phase Breakdown]
A --> C[Task Statistics]
A --> D[Blocker Analysis]
B --> E[Active Phases]
C --> F[Completion %]
D --> G[Risk Items]
```
资料来源：[AGENTS.md:1-30]()
### Client Brief (`/client-brief`)
Full client briefing combining projects and communications:
| Component | Data Source |
|-----------|-------------|
| Projects | Active client projects |
| Communications | Beeper threads, meetings |
| Open Tasks | Client-related issues |
| Notes | Recent client notes |
### Client Health (`/client-health`)
Dashboard across all clients for relationship health tracking.
### Customer Success Triage (`/customer-success-triage`)
Workflow for triaging client requests:
1. Call `get_client_success_workspace` with client name
2. Review workspace output:
- `recentThreads` - Business chats
- `recentMeetings` - Fathom and Granola meetings
- `notes` - Client notes
- `openTasks` - Active issues
- `projects` - Client projects
3. Drill down as needed:
- Chat detail: `get_beeper_thread_messages`
- Meeting detail: `get_fathom_meeting`, `get_granola_meeting`
- Transcript: `get_fathom_transcript`, `get_granola_transcript`
- Note history: `get_client_notes`
4. Classify findings:
- **New Requirements**: Net-new asks
- **Follow-Ups**: Items waiting on response
- **Risks/Blockers**: Scope ambiguity, overdue work, churn risk
- **Already Tracked**: Existing notes or tasks
资料来源：[skills/customer-success-triage/SKILL.md:1-40]()
## Initiative & Cycle Review
### Initiative Review (`/initiative-review`)
Yearly goal progress by category. Tracks progress against annual initiatives with configurable year (e.g., `/initiative-review 2026`).
### Cycle Review (`/sprint-review`)
Sprint review with rollover options for managing incomplete work between cycles.
## Data Model Relationships
```mermaid
graph TD
I[Initiative] -->|1:N| C[Cycle]
I -->|1:N| P[Project]
C -->|1:N| T[Task/Issue]
P -->|1:N| T
C -->|has| G[Cycle Goals]
P -->|has| Ph[Phases]
T -->|assigned to| C
T -->|scheduled on| D[Due Date]
C -->|1:N| C2[Next Cycle]
Cl[Client] -->|1:N| P
Cl -->|1:N| Co[Contact]
Cl -->|1:N| N[Notes]
```
## MCP Tools Summary
| Category | Tools | Operations |
|----------|-------|------------|
| Projects | `get_project`, `create_project`, `update_project`, `delete_project` | Full CRUD |
| Issues/Tasks | `get_issue`, `create_issue`, `update_issue`, `delete_issue`, `schedule_issue` | Full CRUD + scheduling |
| Cycles | `get_current_cycle`, `get_cycle_goals`, `update_cycle_goals`, `assign_issue_to_current_cycle` | Cycle management |
| Clients | `get_client_success_workspace`, `create_client_note`, `update_client_note` | Client workspace |
| Planning | `get_planning_context`, `apply_planning_patch` | Context + mutations |
资料来源：[README.md:1-50]()
资料来源：[AGENTS.md:1-60]()
## Best Practices
1. **Always fetch context first** - Use `get_planning_context` before any planning mutation to ensure you have the latest data
2. **Set dryRun=true initially** - Preview changes before applying mutations
3. **Use appropriate mode** - Match the mutation mode (day/week/cycle) to your planning scope
4. **Save notes as artifacts** - Use `save_daily_note` and `save_weekly_note` to create readable plan artifacts
5. **Link existing projects** - When using PPV or other systems, prefer linking to existing projects over creating duplicates
---
## Client Management
### 相关页面
相关主题：[Project Management](#project-management), [People & Relationships](#people-relationships)
Relevant Source Files
以下源码文件用于生成本页说明：
- [skills/client-brief/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/client-brief/SKILL.md)
- [skills/client-health/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/client-health/SKILL.md)
- [skills/customer-success-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
- [skills/inbox-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/inbox-triage/SKILL.md)
# Client Management
Client Management in LifeOS provides a comprehensive system for managing client relationships, tracking customer-success work, and maintaining client health across your entire portfolio. It leverages the LifeOS MCP tools to aggregate data from multiple sources including Beeper threads, Fathom/Granola meetings, notes, and open tasks into unified client workspaces.
## Overview
The Client Management system consists of four primary skills that work together to provide complete client visibility and actionable workflows:
| Skill | Purpose | Invocation |
|-------|---------|------------|
| `client-brief` | Full client briefing with projects and communications | `/client-brief "Acme Corp"` |
| `client-health` | Health dashboard across all clients | `/client-health` |
| `customer-success-triage` | Triage requests using chats, meetings, notes, and open work | `/customer-success-triage "Acme Corp"` |
| `inbox-triage` | Process notes into tasks | `/inbox-triage` |
资料来源：[README.md:28-32](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
## Architecture
```mermaid
graph TD
A[User Request] --> B{Client Management Skills}
B --> C[client-brief]
B --> D[client-health]
B --> E[customer-success-triage]
B --> F[inbox-triage]
C --> G[get_client_success_workspace]
D --> H[get_all_clients]
E --> G
E --> I[Meeting Tools]
E --> J[Communication Tools]
G --> K[Projects, Tasks, Notes, Threads]
I --> L[get_fathom_meeting, get_granola_meeting]
J --> M[get_beeper_thread_messages]
K --> N[apply_planning_patch]
L --> N
M --> N
N --> O[LifeOS Convex Backend]
```
## Core Skills
### Client Brief
The `client-brief` skill generates a comprehensive client briefing that includes all projects, communications, and current status information for a specific client. It is invoked with the client name or ID as an argument.
资料来源：[AGENTS.md:24](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
**Workflow:**
1. Call `get_client_success_workspace` with the client identifier
2. Aggregate all related data: projects, open tasks, notes, recent threads, meetings
3. Present a structured briefing with actionable insights
### Client Health Dashboard
The `client-health` skill provides a health dashboard across all clients, allowing you to quickly identify which client relationships need attention and which are performing well.
资料来源：[README.md:29](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
**Key Metrics Tracked:**
- Communication frequency
- Open task counts
- Blocked or overdue items
- Recent meeting activity
- Note activity and recency
### Customer Success Triage
The `customer-success-triage` skill is designed for reviewing customer asks, checking whether work is already tracked, capturing requirement summaries, and deciding what should become a task.
资料来源：[skills/customer-success-triage/SKILL.md:1-6](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
**Input Format:**
```
$ARGUMENTS should contain the client name or ID, plus an optional focus area
```
## Customer Success Triage Workflow
```mermaid
graph TD
A[Start Triage: Client Name/ID] --> B[Call get_client_success_workspace]
B --> C{Workspace Data}
C --> D[recentThreads]
C --> E[recentMeetings]
C --> F[notes]
C --> G[openTasks]
C --> H[projects]
D --> I{Drill Down Needed?}
E --> I
F --> I
G --> I
H --> I
I -->|Threads| J[get_beeper_thread_messages]
I -->|Fathom| K[get_fathom_meeting
get_fathom_transcript]
I -->|Granola| L[get_granola_meeting
get_granola_transcript]
I -->|Notes| M[get_client_notes]
J --> N{Classification}
K --> N
L --> N
M --> N
N --> O[New Requirements]
N --> P[Follow-Ups]
N --> Q[Risks / Blockers]
N --> R[Already Tracked]
O --> S[create_issue
update_issue]
P --> S
Q --> S
R --> S
S --> T[create_client_note
update_client_note]
T --> U[Present Triage Results]
```
资料来源：[skills/customer-success-triage/SKILL.md:7-28](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
## Classification Framework
When triaging customer-success work, findings should be classified into four categories:
| Classification | Description | Action |
|----------------|-------------|--------|
| **New Requirements** | Net-new asks or requested changes | Create issues or capture in notes |
| **Follow-Ups** | Things waiting on you or the team | Track and schedule follow-ups |
| **Risks / Blockers** | Scope ambiguity, overdue work, delivery risk, churn risk | Prioritize and escalate |
| **Already Tracked** | Notes or tasks that already cover the request | Link and reference existing work |
资料来源：[skills/customer-success-triage/SKILL.md:17-20](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
## MCP Tools Reference
### Client Workspace Tools
| Tool | Purpose | Source |
|------|---------|--------|
| `get_client_success_workspace` | Retrieve comprehensive workspace for a client | [customer-success-triage/SKILL.md:8](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
| `get_client_notes` | Retrieve existing note history for a client | [customer-success-triage/SKILL.md:16](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
### Meeting Integration Tools
| Tool | Purpose | Source |
|------|---------|--------|
| `get_fathom_meeting` | Retrieve Fathom meeting details | [customer-success-triage/SKILL.md:14](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
| `get_fathom_transcript` | Get full Fathom meeting transcript | [customer-success-triage/SKILL.md:14](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
| `get_granola_meeting` | Retrieve Granola meeting details | [customer-success-triage/SKILL.md:15](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
| `get_granola_transcript` | Get full Granola meeting transcript | [customer-success-triage/SKILL.md:15](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
### Communication Tools
| Tool | Purpose | Source |
|------|---------|--------|
| `get_beeper_thread_messages` | Retrieve Beeper thread communications | [customer-success-triage/SKILL.md:13](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md) |
### Write Operations
| Tool | Purpose | When to Use |
|------|---------|-------------|
| `create_client_note` | Save durable account memory | New insights, decisions, context |
| `update_client_note` | Update existing client notes | Refine or extend existing notes |
| `create_issue` | Create execution work items | New requirements that need action |
| `update_issue` | Modify existing issues | Status changes, priority updates |
资料来源：[skills/customer-success-triage/SKILL.md:21-25](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
## Inbox Triage Integration
The `inbox-triage` skill works in conjunction with Client Management to process notes into actionable tasks. When client communications result in notes that need to be converted into work items, this skill provides the bridge between captured information and tracked work.
资料来源：[AGENTS.md:21](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
**Typical Flow:**
1. Customer-success triage identifies new requirements
2. Client notes are created or updated with requirements
3. Inbox triage converts notes into issues
4. Issues are linked to relevant projects and cycles
## Best Practices
### Write Operations
Based on the triage workflow design, follow these guidelines for write operations:
1. **Save durable account memory** with `create_client_note` or `update_client_note` for insights, decisions, and context
2. **Use `create_issue` or `update_issue`** only for execution work that requires tracking
3. **Prefer updating existing notes/tasks** over creating duplicates
4. **Do not delete anything** — maintain complete audit trails of client interactions
资料来源：[skills/customer-success-triage/SKILL.md:22-25](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
### Drill-Down Strategy
When triaging, follow this prioritized approach:
1. **Review the workspace output first** — examine `recentThreads`, `recentMeetings`, `notes`, `openTasks`, and `projects`
2. **Drill down only when needed** — not every piece of information requires deep investigation
3. **Match the drill-down tool to the source** — use the appropriate tool for the data type being investigated
资料来源：[skills/customer-success-triage/SKILL.md:8-16](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
## Usage Examples
### Generate a Client Brief
```bash
/client-brief "Acme Corp"
```
### Check Client Health Across Portfolio
```bash
/client-health
```
### Triage Customer Success Work
```bash
/customer-success-triage "Acme Corp"
```
### Triage with Focus Area
```bash
/customer-success-triage "Acme Corp" --focus "billing issues"
```
## Data Flow Summary
```mermaid
graph LR
A[Beeper Threads] --> D[Client Workspace]
B[Fathom Meetings] --> D
C[Granola Meetings] --> D
E[Open Tasks] --> D
F[Projects] --> D
G[Notes] --> D
D --> H{Triage Classification}
H --> I[New Requirements]
H --> J[Follow-Ups]
H --> K[Risks/Blockers]
H --> L[Already Tracked]
I --> M[Issues + Notes]
J --> M
K --> M
L --> N[Reference Link]
M --> O[LifeOS Backend]
N --> O
```
## Related Skills
- **Project Management** — Link client work to specific projects and phases
- **Sprint Plan** — Assign client work to current cycles
- **Weekly Review** — Include client health in periodic reviews
- **Follow-ups** — Track outstanding client communications
---
## People & Relationships
### 相关页面
相关主题：[Client Management](#client-management)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/contact-lookup/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/contact-lookup/SKILL.md)
- [skills/relationship-pulse/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/relationship-pulse/SKILL.md)
- [skills/inbox-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/inbox-triage/SKILL.md)
- [skills/blind-spot-finder/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
# People & Relationships
The People & Relationships module within LifeOS Plugin provides a comprehensive system for managing contacts, tracking interactions, preparing for meetings, and maintaining meaningful professional and personal relationships. This module serves as the social intelligence layer of the productivity OS, connecting human interaction data with actionable workflow skills.
## Overview
The People & Relationships system integrates with multiple data sources to build complete dossiers on contacts, including Beeper messaging threads, Granola meeting records with AI-generated notes, voice memos, and calendar events. The system enables agents to perform relationship maintenance tasks such as identifying neglected contacts, tracking follow-up obligations, and rapidly switching context between different clients or people.
资料来源：[skills/contact-lookup/SKILL.md:1-5]()
The core philosophy treats relationships as first-class productivity assets. Rather than siloing contact information in a traditional CRM, LifeOS weaves relationship data into daily workflows, enabling proactive relationship maintenance alongside task and project management.
## Core Skills
### Contact Lookup
The `contact-lookup` skill provides a complete dossier on any person in the system.
**Entry Point**: `get_contact_dossier` with a name query
**Dossier Components**:
| Component | Data Source | Description |
|-----------|-------------|-------------|
| Person Info | LifeOS database | Name, relationship type, contact info, system notes |
| AI Insights | AI-generated | Communication style, personality indicators, relationship tips |
| Beeper Threads | Beeper API | Messaging history linked to this contact |
| Granola Meetings | Granola API | Meeting records with AI notes and calendar events |
| Voice Memos | Voice memo system | Audio recordings involving or mentioning this person |
资料来源：[skills/contact-lookup/SKILL.md:10-25]()
**Workflow**:
```mermaid
graph TD
A[User Query: Contact Name] --> B[Call get_contact_dossier]
B --> C{Contact Found?}
C -->|Yes| D[Extract Data Sources]
C -->|No| E[Request Valid Name]
D --> F[Fetch Beeper Threads]
D --> G[Fetch Granola Meetings]
D --> H[Fetch Voice Memos]
F --> I[Aggregate Dossier]
G --> I
H --> I
I --> J[Present Structured Output]
```
**Output Structure**:
```markdown
- **Profile**: Name, relationship type, contact info, notes
- **AI Insights**: Communication style, personality, relationship tips
- **Recent Interactions**: Last voice memos, meetings, messages sorted by recency
- **Meeting History**: Granola meetings with key takeaways
- **Chat Threads**: Beeper conversation threads
```
资料来源：[skills/contact-lookup/SKILL.md:12-25]()
### Meeting Preparation
The `meeting-prep` skill aggregates relevant context before scheduled meetings with contacts.
**Data Pulled**:
- Contact dossier from `get_contact_dossier`
- Recent Beeper threads with the person
- Granola meeting notes from previous encounters
- Open tasks or projects related to the person
- Any pending follow-ups or commitments
**Purpose**: Ensures agents enter meetings with full context, avoiding the need to re-explain background or rediscover relationship history.
### Follow-ups Tracking
The `follow-ups` skill identifies communication obligations across the network.
**Tracking Criteria**:
| Category | Threshold | Priority |
|----------|-----------|----------|
| Active threads | Unreplied messages | High |
| Scheduled meetings | Confirmed but unheld | Medium |
| Promised responses | Past commitment date | High |
| Project updates | Stale status | Medium |
**Output**: Prioritized list of contacts requiring responses, grouped by urgency and relationship type.
资料来源：[AGENTS.md:25-28]()
### Relationship Pulse
The `relationship-pulse` skill proactively monitors relationship health by analyzing interaction frequency against relationship type expectations.
**Data Sources**:
- `get_people` — All contacts with relationship classifications
- `get_beeper_threads` — Message activity and recency
- `get_granola_meetings` — Meeting history
资料来源：[skills/relationship-pulse/SKILL.md:1-10]()
**Neglect Thresholds**:
| Relationship Type | Threshold | Priority Level |
|-------------------|-----------|----------------|
| Family / Close friends | 14+ days no contact | Critical |
| Friends | 30+ days no contact | High |
| Colleagues / Mentors | 60+ days no contact | Medium |
| Acquaintances | 90+ days no contact | Low (optional) |
资料来源：[skills/relationship-pulse/SKILL.md:22-28]()
**Output Categories**:
- **Reach out soon**: Prioritized by relationship closeness
- **Consider reconnecting**: Re-engagement opportunities
- **Suggested touchpoints**: Quick actions like replying to old threads or scheduling catch-ups
```mermaid
graph TD
A[get_people] --> B[Classify Each Contact]
A --> C[get_beeper_threads]
A --> D[get_granola_meetings]
C --> E[Calculate Last Interaction]
D --> E
E --> F{Compare to Thresholds}
F -->|Exceeded| G[Add to Neglected List]
F -->|Within bounds| H[Mark as Active]
G --> I[Prioritize by Relationship]
I --> J[Generate Action Suggestions]
```
### Context Switch
The `context-switch` skill enables rapid context loading for a specific client or person, useful when switching between active workstreams.
**Usage**: When working on multiple clients or projects, agents can invoke context-switch to immediately load relevant data without manual retrieval.
**Loaded Data**:
- Recent client notes
- Active projects and tasks
- Meeting history
- Outstanding communications
- Project-specific context
资料来源：[AGENTS.md:30-31]()
## Data Models
### Person Entity
| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Unique identifier |
| `name` | string | Full name |
| `relationshipType` | enum | Family, Friend, Colleague, Mentor, Client, Acquaintance |
| `contactInfo` | object | Email, phone, social links |
| `notes` | string | Agent-added notes |
| `createdAt` | timestamp | Creation date |
| `updatedAt` | timestamp | Last modification |
### Interaction Record
| Field | Type | Description |
|-------|------|-------------|
| `personId` | string | Foreign key to person |
| `type` | enum | Message, Meeting, VoiceMemo, Note |
| `timestamp` | timestamp | When interaction occurred |
| `source` | string | Beeper, Granola, VoiceNotes, etc. |
| `summary` | string | AI-generated summary |
| `metadata` | object | Source-specific data |
### Relationship Health Score
| Level | Criteria | Action |
|-------|----------|--------|
| Active | Recent interaction within threshold | Maintain |
| Needs Attention | Approaching threshold | Schedule contact |
| Neglected | Exceeded threshold | Prioritize outreach |
| At Risk | Significantly exceeded + commitments pending | Immediate action |
## MCP Tool Integration
The People & Relationships module leverages the LifeOS MCP server for data operations:
### Read Operations
| Tool | Purpose |
|------|---------|
| `get_contact_dossier` | Full person dossier with all data sources |
| `get_people` | List all contacts |
| `get_beeper_threads` | Messaging threads, optionally filtered by person |
| `get_granola_meetings` | Meeting records with AI notes |
| `get_granola_meeting` | Single meeting details |
| `get_granola_transcript` | Full meeting transcript |
| `get_voice_memos_by_labels` | Voice memos filtered by labels |
| `get_client_notes` | Client-specific notes history |
资料来源：[skills/contact-lookup/SKILL.md:16-22]()
### Write Operations
| Tool | Purpose |
|------|---------|
| `create_client_note` | Save durable account memory |
| `update_client_note` | Update existing note |
| `link_memo_to_person` | Connect voice memo to contact |
资料来源：[skills/contact-lookup/SKILL.md:25-27]()
## Workflow Integration
The People & Relationships module connects with other LifeOS workflow skills:
### Integration with Planning
During daily and weekly planning, the system can surface:
- Pending follow-ups requiring attention
- Meeting preparations needed
- Relationship pulse alerts
```mermaid
graph LR
A[Daily Planning] --> B[get_planning_context]
B --> C{Include People Data?}
C -->|Yes| D[Fetch Follow-ups]
C -->|Yes| E[Fetch Relationship Pulse]
D --> F[Surface in Day Plan]
E --> F
```
### Integration with Reviews
During cycle and initiative reviews, contact data informs:
- Client health across projects
- Communication patterns with stakeholders
- Meeting frequency analysis
### Integration with Capture
The `inbox-triage` skill uses person data for:
- Linking captured notes to contacts via `link_memo_to_person`
- Suggesting contacts when notes mention people
- Creating tasks tied to relationship obligations
资料来源：[skills/inbox-triage/SKILL.md:10-18]()
## Relationship Intelligence
### AI-Generated Insights
The system uses AI to generate relationship intelligence:
- **Communication style**: How the person prefers to communicate
- **Personality indicators**: Extracted from interaction patterns
- **Relationship tips**: Customized advice for maintaining the relationship
These insights are generated during `get_contact_dossier` calls and stored as part of the person record.
### Blind Spot Detection
The `blind-spot-finder` skill incorporates relationship data to identify patterns:
- Screening time analysis vs. relationship investment
- Say-do gaps in stated priorities vs. actual relationship maintenance
- Patterns the user cannot see from inside their own behavior
资料来源：[skills/blind-spot-finder/SKILL.md:5-12]()
## Best Practices
### Regular Maintenance
1. Run `relationship-pulse` weekly to identify neglected contacts
2. Review `follow-ups` daily during planning
3. Use `contact-lookup` before any significant meeting
### Data Quality
1. Ensure relationship types are accurately set for proper threshold calculation
2. Add notes during interactions for future context
3. Link voice memos and meeting notes to relevant contacts
### Avoiding Duplication
- Prefer updating existing notes over creating duplicates
- Use `update_client_note` instead of `create_client_note` when history exists
- Link to existing contacts rather than creating new person records
资料来源：[skills/contact-lookup/SKILL.md:26-27]()
## Summary
The People & Relationships module provides a holistic approach to relationship management within LifeOS. By integrating messaging, meetings, voice notes, and AI-generated insights, it enables proactive relationship maintenance alongside productivity work. The system treats relationships as living data that requires regular attention, not static contacts to be occasionally referenced.
Key capabilities include:
- Complete contact dossiers aggregating all interaction data
- Proactive neglect detection with customizable thresholds
- Meeting preparation with full historical context
- Follow-up tracking across multiple communication channels
- Rapid context switching for multi-client workflows
---
## Review Workflows
### 相关页面
相关主题：[Daily Workflows](#daily-workflows), [Project Management](#project-management), [Finance Management](#finance-management)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/weekly-review/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-review/SKILL.md)
- [skills/weekly-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
- [skills/monthly-review/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/monthly-review/SKILL.md)
- [skills/cycle-review/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/cycle-review/SKILL.md)
- [skills/initiative-review/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/initiative-review/SKILL.md)
- [skills/customer-success-triage/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
- [skills/blind-spot-finder/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
- [skills/sprint-plan/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
# Review Workflows
## Overview
Review Workflows are periodic assessment and reflection skills that enable users to systematically evaluate their progress across different time horizons—from daily standups to yearly initiative reviews. These workflows pull data from LifeOS via MCP (Model Context Protocol) tools, present structured insights, and in some cases apply mutations to the system.
The review system follows a temporal hierarchy aligned with typical sprint and goal-setting cadences:
```mermaid
graph TB
subgraph "Review Hierarchy"
DR[Daily Review
daily-plan]
WR[Weekly Review
weekly-review]
CR[Cycle Review
cycle-review]
MR[Monthly Review
monthly-review]
IR[Initiative Review
initiative-review]
end
subgraph "Specialized Reviews"
CST[Customer Success
Triage]
BSF[Blind Spot
Finder]
end
DR --> WR
WR --> CR
CR --> MR
MR --> IR
WR -.-> CST
WR -.-> BSF
```
Each review type serves a distinct purpose in the feedback loop of planning, execution, and reflection.
资料来源：[skills/weekly-review/SKILL.md:1-6](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-review/SKILL.md)
资料来源：[skills/cycle-review/SKILL.md:1-6](https://github.com/starascendin/lifeos-plugin/blob/main/skills/cycle-review/SKILL.md)
---
## Review Workflow Types
### Comparison Table
| Review Type | Time Horizon | Mutating | Primary Data Sources | Skill File |
|-------------|--------------|----------|---------------------|------------|
| Daily Plan | Today | Yes | Planning context, calendar, habits | `daily-plan/SKILL.md` |
| Weekly Review | This week | No | Weekly agenda, cycle, tasks | `weekly-review/SKILL.md` |
| Weekly Plan | This week | Yes | Planning context, backlog | `weekly-plan/SKILL.md` |
| Cycle Review | Current sprint | Partial | Current cycle, tasks | `cycle-review/SKILL.md` |
| Sprint Plan | Current sprint | Yes | Planning context, backlog | `sprint-plan/SKILL.md` |
| Monthly Review | This month | No | Monthly agenda, cycles, projects | `monthly-review/SKILL.md` |
| Initiative Review | This year | No | Yearly initiative rollup | `initiative-review/SKILL.md` |
| Customer Success Triage | Per client | Partial | Client workspace, threads, meetings | `customer-success-triage/SKILL.md` |
| Blind Spot Finder | Ad-hoc | Partial | Working memory, health, habits | `blind-spot-finder/SKILL.md` |
资料来源：[skills/weekly-review/SKILL.md:1-20](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-review/SKILL.md)
资料来源：[skills/monthly-review/SKILL.md:1-25](https://github.com/starascendin/lifeos-plugin/blob/main/skills/monthly-review/SKILL.md)
资料来源：[skills/initiative-review/SKILL.md:1-15](https://github.com/starascendin/lifeos-plugin/blob/main/skills/initiative-review/SKILL.md)
---
## Weekly Review
The **weekly-review** skill provides a comprehensive assessment of the current week's work, sprint health, and upcoming priorities.
### Purpose
> "Run weekly review with completed work, in-progress items, sprint health, and blockers"
资料来源：[skills/weekly-review/SKILL.md:1-2](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-review/SKILL.md)
### Data Gathering Flow
```mermaid
graph LR
A[get_weekly_agenda] --> B[Present Weekly Review]
C[get_current_cycle] --> B
D[get_tasks status=done] --> B
E[get_tasks status=in_progress] --> B
F[get_tasks status=todo] --> B
```
### MCP Tools Used
| Tool | Purpose |
|------|---------|
| `get_weekly_agenda` | Week's agenda and AI summary |
| `get_current_cycle` | Sprint progress |
| `get_tasks` (status: done) | Completed work this week |
| `get_tasks` (status: in_progress) | Active work |
| `get_tasks` (status: todo) | Upcoming work |
### Output Structure
The weekly review presents:
- **Completed**: What got done this week
- **In Progress**: What's still being worked on
- **Sprint Health**: Cycle progress, burndown status
- **Blockers**: Anything overdue or stuck
- **Next Week**: Key items to tackle
The skill optionally accepts a date argument to review a specific week.
资料来源：[skills/weekly-review/SKILL.md:1-25](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-review/SKILL.md)
---
## Monthly Review
The **monthly-review** skill provides a broader perspective on accomplishments, project progress, and themes across an entire month.
### Purpose
> "Run monthly review with accomplishments, project progress, and next month planning"
资料来源：[skills/monthly-review/SKILL.md:1-2](https://github.com/starascendin/lifeos-plugin/blob/main/skills/monthly-review/SKILL.md)
### Data Gathering Flow
```mermaid
graph TB
A[get_monthly_agenda] --> Z[Monthly Review Output]
B[get_cycles] --> Z
C[get_tasks status=done] --> Z
D[get_projects] --> Z
E[get_clients] --> Z
F[get_recent_notes limit=20] --> Z
```
### MCP Tools Used
| Tool | Purpose | Data Retrieved |
|------|---------|----------------|
| `get_monthly_agenda` | Month overview and AI summary | Full month's context |
| `get_cycles` | All sprints this month | Completion rates |
| `get_tasks` (status: done) | Everything completed | Accomplishments |
| `get_projects` | Project progress and health | Status tracking |
| `get_clients` | Client relationship status | Health of client relationships |
| `get_recent_notes` (limit: 20) | Captured thoughts | Themes and patterns |
### Output Structure
The monthly review presents:
- **Accomplishments**: Major wins and completed work
- **Projects Progress**: Status of each active project
- **Sprint Performance**: Average completion rate across cycles
- **Client Health**: Relationship status per client
- **Themes**: Patterns from notes and completed work
- **Carried Forward**: What's rolling into next month
- **Reflections**: What worked, what didn't
- **Next Month Focus**: Top 3 priorities
Supports optional month argument (e.g., "january" or "2024-01").
资料来源：[skills/monthly-review/SKILL.md:1-30](https://github.com/starascendin/lifeos-plugin/blob/main/skills/monthly-review/SKILL.md)
---
## Cycle Review
The **cycle-review** skill focuses on the current sprint/iteration, providing progress metrics and rollover options for incomplete work.
### Purpose
> "Review the current cycle/sprint with progress, incomplete items, and rollover options"
资料来源：[skills/cycle-review/SKILL.md:1-2](https://github.com/starascendin/lifeos-plugin/blob/main/skills/cycle-review/SKILL.md)
### Data Gathering
| Tool | Purpose |
|------|---------|
| `get_current_cycle` | Active cycle with progress stats |
| `get_cycles` (status: upcoming) | What's next |
| `get_tasks` (status: in_progress) | Active work |
| `get_tasks` (status: backlog or todo) | Incomplete items in cycle |
### Output Structure
- **Cycle Summary**: Name, dates, days remaining
- **Progress**: Completion %, issues done vs total
- **Incomplete Items**: All non-done/non-cancelled issues with status and priority
- **Next Cycle**: The upcoming cycle (if any)
- **Recommendations**: Closing suggestions, reprioritization advice
### Cycle Management Actions
| Argument | Action | MCP Call |
|----------|--------|----------|
| `close` | Close cycle WITHOUT rollover | `close_cycle` |
| `rollover` | Close cycle WITH rollover | `close_cycle` with `rolloverIncomplete=true` |
| None | Prompt user for action | — |
资料来源：[skills/cycle-review/SKILL.md:1-35](https://github.com/starascendin/lifeos-plugin/blob/main/skills/cycle-review/SKILL.md)
---
## Initiative Review
The **initiative-review** skill provides a yearly perspective on goals, tracking progress across multiple initiative categories.
### Purpose
> "Review yearly initiative progress with stats per category and highlight stalled initiatives"
资料来源：[skills/initiative-review/SKILL.md:1-2](https://github.com/starascendin/lifeos-plugin/blob/main/skills/initiative-review/SKILL.md)
### Data Gathering Flow
```mermaid
graph TB
A[get_initiative_yearly_rollup] --> B{Low Progress?}
B -->|Yes| C[get_initiative_with_stats]
B -->|No| D[Present Review]
C --> D
```
### Output Structure
- **Year Overview**: Total initiatives, active vs completed, average progress
- **By Category**: Group by (career, health, learning, etc.) with progress
- **Each Initiative**: Title, status, progress %, tasks completed/total, linked projects, habits
- **Highlights**: Initiatives at 80%+ progress
- **Concerns**: Flag 0% progress, no linked projects, or "paused" status
- **Recommendations**: Next actions
Supports optional year argument (e.g., "2025").
资料来源：[skills/initiative-review/SKILL.md:1-30](https://github.com/starascendin/lifeos-plugin/blob/main/skills/initiative-review/SKILL.md)
---
## Customer Success Triage
The **customer-success-triage** skill is a specialized review for customer-facing work, synthesizing communications and tracking across multiple channels.
### Purpose
> "Triage client requests and customer-success work using the client workspace, business chats, Fathom and Granola meetings, notes, and open tasks."
资料来源：[skills/customer-success-triage/SKILL.md:1-5](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
### Data Gathering Flow
```mermaid
graph TB
A[get_client_success_workspace] --> B[Review Workspace]
B --> C[recentThreads]
B --> D[recentMeetings]
B --> E[notes]
B --> F[openTasks]
B --> G[projects]
C --> H[Drill Down Options]
D --> H
E --> H
H --> I[get_beeper_thread_messages]
H --> J[get_fathom_meeting/transcript]
H --> K[get_granola_meeting/transcript]
H --> L[get_client_notes]
```
### Classification Framework
| Category | Description |
|----------|-------------|
| **New Requirements** | Net-new asks or requested changes |
| **Follow-Ups** | Things waiting on you or the team |
| **Risks / Blockers** | Scope ambiguity, overdue work, delivery risk, churn risk |
| **Already Tracked** | Notes or tasks that already cover the request |
### Write Operations
| Operation | When to Use |
|-----------|-------------|
| `create_client_note` | Save durable account memory |
| `update_client_note` | Update existing account memory |
| `create_issue` | New execution work only |
| `update_issue` | Modify existing tasks |
**Guidelines**: Prefer updating existing notes/tasks over creating duplicates. Do not delete anything.
资料来源：[skills/customer-success-triage/SKILL.md:1-35](https://github.com/starascendin/lifeos-plugin/blob/main/skills/customer-success-triage/SKILL.md)
---
## Blind Spot Finder
The **blind-spot-finder** skill uses multi-model AI evaluation to identify self-deceptions, local maxima, and blind spots that the user cannot see from within their own perspective.
### Purpose
> "Use multiple AI models to find what I'm NOT seeing. This is about the unknown unknowns."
资料来源：[skills/blind-spot-finder/SKILL.md:1-3](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
### Data Gathering (Parallel Calls)
```mermaid
graph TB
subgraph "Context Gathering"
A[get_working_memory]
B[get_coaching_action_items]
C[get_habits]
D[get_screentime_summary]
E[get_health_sleep]
F[get_finance_net_worth]
end
A & B & C & D & E & F --> G[Build Blind Spot Brief]
G --> H[Multi-Model Council]
H --> I[Synthesized Insights]
```
### Multi-Model Council Process
| Round | Focus | Purpose |
|-------|-------|---------|
| Round 1 | Blind Spot Detection | Identify top 3-5 blind spots, self-deceptions, local maxima |
| Round 2 | Peer Evaluation | Models review each other's responses |
| Round 3 | Synthesis | Chairman's final synthesized perspective |
### Focus Areas for Blind Spot Detection
- Self-deceptions they're maintaining
- Local maxima they're stuck in
- Assumptions they haven't questioned
- Patterns they can't see because they're inside them
- Things they SAY they want but systematically avoid
资料来源：[skills/blind-spot-finder/SKILL.md:1-50](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
---
## Planning Integration
Review workflows connect to planning workflows to close the feedback loop between reflection and action.
### Review → Plan Flow
```mermaid
graph LR
WR[Weekly Review] --> WP[Weekly Plan]
CR[Cycle Review] --> SP[Sprint Plan]
MR[Monthly Review] --> WP
WP --> AP[apply_planning_patch]
SP --> AP
AP -->|Creates| NI[new_issue]
AP -->|Schedules| SI[scheduled_issue]
AP -->|Assigns| ACI[assign_issue_to_current_cycle]
AP -->|Updates| UG[update_cycle_goals]
```
### Mutating Operations Available
| Operation | Purpose | Available In |
|-----------|---------|---------------|
| `create_issue` | New work | Weekly Plan, Sprint Plan |
| `schedule_issue` | Due date changes | Weekly Plan, Sprint Plan |
| `update_issue` | Status, priority, estimate, title | Weekly Plan, Sprint Plan |
| `assign_issue_to_current_cycle` | Cycle assignment | Weekly Plan, Sprint Plan |
| `set_top_priority` | Immediate focus | Weekly Plan, Sprint Plan |
| `update_cycle_goals` | Cycle focus changes | Weekly Plan, Sprint Plan |
| `save_weekly_note` | Readable weekly plan artifact | Weekly Plan |
| `save_daily_note` | Concrete execution plan | Weekly Plan |
资料来源：[skills/weekly-plan/SKILL.md:1-30](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
资料来源：[skills/sprint-plan/SKILL.md:1-30](https://github.com/starascendin/lifeos-plugin/blob/main/skills/sprint-plan/SKILL.md)
---
## MCP Tool Reference
### Commonly Used Tools Across Reviews
| Tool | Returns | Review Types |
|------|---------|--------------|
| `get_weekly_agenda` | Week's agenda, AI summary | Weekly Review, Weekly Plan |
| `get_monthly_agenda` | Month overview, AI summary | Monthly Review |
| `get_current_cycle` | Active cycle stats | Weekly Review, Cycle Review, Sprint Plan |
| `get_cycles` | All cycles with status | Cycle Review, Monthly Review |
| `get_tasks` | Tasks filtered by status | All reviews |
| `get_projects` | Project list with status | Monthly Review |
| `get_clients` | Client relationships | Monthly Review |
| `get_initiative_yearly_rollup` | Initiative stats by year | Initiative Review |
| `get_working_memory` | User's working memory | Blind Spot Finder |
### Planning Context Tool
The `get_planning_context` tool is fundamental to planning workflows:
| Parameter | Type | Purpose |
|-----------|------|---------|
| `date` | string | Specific date for daily planning |
| `weekStartDate` | string | Week start for weekly planning |
| `include.daily` | boolean | Include daily fields |
| `include.weekly` | boolean | Include weekly context |
| `include.currentCycle` | boolean | Include current cycle |
| `include.backlog` | boolean | Include backlog items |
| `include.habits` | boolean | Include habit data |
| `include.dailyFields` | boolean | Include daily field values |
| `include.calendar` | boolean | Include calendar events |
| `include.voiceMemos` | boolean | Include voice memos |
资料来源：[skills/daily-plan/SKILL.md:1-25](https://github.com/starascendin/lifeos-plugin/blob/main/skills/daily-plan/SKILL.md)
资料来源：[skills/weekly-plan/SKILL.md:1-30](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
---
## Best Practices
### When to Use Each Review Type
| Scenario | Recommended Review |
|----------|-------------------|
| Start of week planning | Weekly Plan + Weekly Review (if previous week ended) |
| Mid-sprint check | Cycle Review |
| End of sprint | Cycle Review + Sprint Plan (for next) |
| Month transition | Monthly Review |
| Quarterly planning | Initiative Review + Monthly Review |
| New client engagement | Customer Success Triage |
| Feeling stuck or plateaued | Blind Spot Finder |
### Review Cadence
```mermaid
gantt
title Review Cadence
dateFormat X
axisFormat %j
section Weekly
Weekly Review :active, r1, 0, 1d
Weekly Plan :active, r2, 1, 1d
section Monthly
Monthly Review :active, m1, 30, 1d
section Cycle
Cycle Review :active, c1, 14, 1d
Sprint Plan :active, c2, 14, 1d
```
### Output Expectations
- **Non-mutating reviews** (Weekly Review, Monthly Review, Initiative Review) present data without changes
- **Mutating workflows** (Weekly Plan, Sprint Plan) automatically apply changes—do not ask for confirmation
- **Partial mutating** (Cycle Review, Customer Success Triage) offer options but require user input for destructive actions
资料来源：[skills/cycle-review/SKILL.md:25-35](https://github.com/starascendin/lifeos-plugin/blob/main/skills/cycle-review/SKILL.md)
资料来源：[skills/weekly-plan/SKILL.md:28-32](https://github.com/starascendin/lifeos-plugin/blob/main/skills/weekly-plan/SKILL.md)
---
## See Also
- [Daily Workflows](README.md#daily-workflows) - Daily planning and standup skills
- [Project & Client Management](README.md#project--client-management) - Project status and client briefing skills
- [Skills Index](AGENTS.md) - Complete list of all 37 skills
---
## Finance Management
### 相关页面
相关主题：[Review Workflows](#review-workflows), [Health Integration (Oura Ring)](#health-integration)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/finance-overview/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-overview/SKILL.md)
- [skills/finance-spending/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-spending/SKILL.md)
- [README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
- [AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
# Finance Management
The Finance Management module within LifeOS provides a comprehensive suite of tools for tracking, analyzing, and understanding personal finances. It integrates directly with Convex-powered backend services to deliver real-time financial insights through 126 MCP (Model Context Protocol) tools available to AI agents.
## Overview
The Finance Management system consists of two primary skill workflows that enable users to:
- Monitor net worth, account balances, and financial trends
- Analyze spending patterns with detailed transaction data
- Track daily income versus spending
- Identify financial patterns and anomalies
资料来源：[README.md](https://github.com/starascendin/lifeos-plugin/blob/main/README.md)
## Architecture
The Finance Management module operates within the broader LifeOS ecosystem, leveraging MCP tools to communicate with the Convex backend. All monetary values are stored in cents and converted to dollars for display.
```mermaid
graph TD
A[User Request] --> B[Finance Skill Workflow]
B --> C[MCP Tool Calls]
C --> D[Convex Backend]
D --> E[(Financial Data)]
C --> F[get_finance_net_worth]
C --> G[get_finance_accounts]
C --> H[get_finance_snapshots]
C --> I[get_finance_daily_spending]
C --> J[get_finance_transactions]
F --> K[Net Worth Dashboard]
G --> L[Account Breakdown]
H --> M[90-Day Trend]
I --> N[Daily Spending Pattern]
J --> O[Transaction History]
```
资料来源：[skills/finance-overview/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-overview/SKILL.md) & [skills/finance-spending/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-spending/SKILL.md)
## Available Skills
### Finance Overview
The `finance-overview` skill provides a comprehensive financial dashboard including net worth summary, account balances, and net worth trends.
| Component | Description |
|-----------|-------------|
| Net Worth | Current total with change over the period |
| Assets | Total assets by account type (checking, savings, investments, retirement) |
| Liabilities | Total liabilities by type (credit cards, loans) |
| Trend | Net worth direction over 90 days (growing/declining/stable) |
| Accounts | Individual account listing with name, type, and balance |
| Insights | Notable changes or patterns |
资料来源：[skills/finance-overview/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-overview/SKILL.md)
**Usage:**
```bash
/finance-overview
```
**Custom Days Parameter:**
```bash
/finance-overview 30
```
When a number is provided as an argument, it overrides the default 90-day trend period.
### Finance Spending
The `finance-spending` skill analyzes spending patterns with daily income/spending aggregation and recent transaction details.
| Component | Description |
|-----------|-------------|
| Summary | Total income, total spending, net for the period |
| Daily Average | Average daily spending calculation |
| Spending Pattern | High-spending days and behavioral patterns |
| Recent Transactions | Most notable recent transactions |
| Insights | Spending trends, unusual activity, suggestions |
资料来源：[skills/finance-spending/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/finance-spending/SKILL.md)
**Usage:**
```bash
/finance-spending
```
**Custom Days Parameter:**
```bash
/finance-spending 14
```
When a number is provided, it overrides the default 30-day analysis period.
## MCP Tool Reference
The Finance Management system exposes the following MCP tools for programmatic access:
| Tool | Purpose |
|------|---------|
| `get_finance_net_worth` | Current net worth and account breakdown |
| `get_finance_accounts` | All account details |
| `get_finance_snapshots` | Net worth trend data with configurable days |
| `get_finance_daily_spending` | Daily income/spending aggregation |
| `get_finance_transactions` | Recent transaction details |
资料来源：[AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
## Data Models
### Financial Data Types
| Field | Type | Description |
|-------|------|-------------|
| `balance` | integer | Monetary value stored in cents |
| `accountType` | string | Type of account (checking, savings, investment, retirement, credit_card, loan) |
| `netWorth` | integer | Total net worth in cents |
| `snapshotDate` | date | Date of the financial snapshot |
> **Note:** All monetary amounts are stored in cents and must be converted to dollars for display purposes.
## Workflow Diagram
```mermaid
graph LR
A[Start: /finance-overview] --> B[get_finance_net_worth]
A --> C[get_finance_accounts]
A --> D[get_finance_snapshots days=90]
B --> E[Aggregate Data]
C --> E
D --> E
E --> F[Build Dashboard]
F --> G[Net Worth Display]
F --> H[Assets Breakdown]
F --> I[Liabilities Breakdown]
F --> J[90-Day Trend]
F --> K[Insights]
```
## Integration Points
The Finance Management module integrates with:
- **PPV (Purpose, Pillar, Vision) System** - For linking financial goals to life design
- **Coaching System** - Financial coaching insights and action items
- **Habits Tracking** - Financial habit compliance
- **Initiatives** - Yearly financial goals tracked as initiatives
资料来源：[AGENTS.md](https://github.com/starascendin/lifeos-plugin/blob/main/AGENTS.md)
## Quick Reference
| Command | Description | Default Period |
|---------|-------------|----------------|
| `/finance-overview` | Net worth dashboard | 90-day trend |
| `/finance-spending` | Spending analysis | 30-day analysis |
All commands support numeric arguments to override default periods (e.g., `/finance-overview 30` or `/finance-spending 14`).
---
## Coaching System
### 相关页面
相关主题：[Habits & Accountability](#habits-accountability)
相关源码文件
以下源码文件用于生成本页说明：
- [skills/coaching-overview/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/coaching-overview/SKILL.md)
- [skills/coaching-action-items/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/coaching-action-items/SKILL.md)
- [skills/coaching-session-review/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/coaching-session-review/SKILL.md)
- [skills/coach-memory/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/coach-memory/SKILL.md)
- [skills/blind-spot-finder/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/blind-spot-finder/SKILL.md)
- [skills/llm-council/SKILL.md](https://github.com/starascendin/lifeos-plugin/blob/main/skills/llm-council/SKILL.md)
# Coaching System
## Overview
The Coaching System is an integrated personal development framework within LifeOS that leverages multiple AI models to provide structured coaching, track action items, maintain coach memory, and help users identify blind spots. The system operates as a multi-layered coaching layer that sits atop the core LifeOS data, utilizing the MCP (Model Context Protocol) interface to access user data and apply mutations.
The coaching system serves as the "meta-layer" for personal growth, distinguishing itself from task management by focusing on identity, behavioral patterns, and sustained development rather than discrete deliverables. It coordinates with other LifeOS features like health data, habits, and finance to provide contextually-aware coaching insights.
**资料来源：** [skills/coaching-overview/SKILL.md:1-4]()
## Architecture
The Coaching System architecture consists of three primary layers:
```mermaid
graph TD
A[Coaching System] --> B[Skill Layer]
A --> C[Memory Layer]
A --> D[Multi-Model Layer]
B --> B1[coaching-overview]
B --> B2[coaching-action-items]
B --> B3[coaching-session-review]
B --> B4[coach-memory]
C --> C1[Working Memory]
C --> C2[Session Summaries]
C --> C3[Action Items]
D --> D1[llm-council]
D --> D2[blind-spot-finder]
C1 --> E[LifeOS Data]
C2 --> E
C3 --> E
```
### Skill Layer
The skill layer consists of discrete workflow skills that can be invoked individually:
| Skill | Purpose | Mutating |
|-------|---------|----------|
| `coaching-overview` | Dashboard of coaches, sessions, and action items | No |
| `coaching-action-items` | Manage coaching action items | Yes |
| `coaching-session-review` | Review session summaries and insights | No |
| `coach-memory` | View and update AI coach's working memory | Yes |
**资料来源：** [skills/coaching-overview/SKILL.md:1-18]()
### Memory Layer
The memory layer maintains persistent knowledge about the user across coaching interactions:
- **Core Struggles**: Consistent challenges the user faces
- **Values**: Deeply held principles
- **Triggers**: Causes of spirals, procrastination, or withdrawal
- **Breakthroughs**: Moments of clarity or growth
- **Personality**: Cognitive patterns and characteristics
- **Communication Style**: Coaching delivery preferences
- **Patterns**: Recurring behavioral patterns
- **Energy Sources**: What energizes vs drains
- **Relationships**: Key relationship dynamics
- **Context**: Current life circumstances
**资料来源：** [skills/coach-memory/SKILL.md:8-25]()
### Multi-Model Layer
The multi-model layer employs multiple AI models for deliberation and insight generation:
- **LLM Council**: Structured deliberation with peer review and synthesis
- **Blind Spot Finder**: Multi-model analysis to identify unknown unknowns
**资料来源：** [skills/llm-council/SKILL.md:1-5]()
## MCP Tools
The Coaching System exposes its functionality through the following MCP tools:
### Query Tools
| Tool | Returns | Source |
|------|---------|--------|
| `get_coaching_profiles` | All coach personas with names, focus areas, session cadence | 资料来源：[skills/coaching-overview/SKILL.md:8]() |
| `get_coaching_sessions` | Recent sessions grouped by coach | 资料来源：[skills/coaching-session-review/SKILL.md:6]() |
| `get_coaching_session` | Full session details including summary and action items | 资料来源：[skills/coaching-session-review/SKILL.md:9]() |
| `get_coaching_action_items` | Action items with status filtering | 资料来源：[skills/coaching-overview/SKILL.md:9]() |
| `get_working_memory` | All memory sections with confidence levels | 资料来源：[skills/coach-memory/SKILL.md:7]() |
### Mutation Tools
| Tool | Purpose | Source |
|------|---------|--------|
| `create_coaching_action_item` | Create new coaching homework/experiments | 资料来源：[skills/blind-spot-finder/SKILL.md:28]() |
| `update_coaching_action_item` | Update status or content of action items | 资料来源：[skills/coaching-action-items/SKILL.md]() |
| `update_working_memory` | Update coach's accumulated knowledge | 资料来源：[skills/blind-spot-finder/SKILL.md:29]() |
## Coaching Workflows
### Dashboard Overview
The `coaching-overview` skill provides a consolidated dashboard by executing three parallel queries:
1. `get_coaching_profiles` — List all coach personas
2. `get_coaching_sessions` with `limit=10` — Recent sessions across all coaches
3. `get_coaching_action_items` with `status="pending"` — Outstanding action items
**资料来源：** [skills/coaching-overview/SKILL.md:5-13]()
The dashboard presents:
- **Coaches**: Each coach profile with name, focus areas, and session cadence
- **Recent Sessions**: Grouped by coach with title, date, and status
- **Pending Action Items**: Count per coach with top 3 most urgent items shown
- **Insights**: Active coaches, overdue items, suggested next sessions
```mermaid
graph LR
A[coaching-overview] --> B[get_coaching_profiles]
A --> C[get_coaching_sessions]
A --> D[get_coaching_action_items]
B --> E[Dashboard Output]
C --> E
D --> E
```
**资料来源：** [skills/coaching-overview/SKILL.md:13-18]()
### Session Review
The `coaching-session-review` skill provides in-depth review of coaching sessions:
1. Find sessions via `get_coaching_sessions` with `limit=5`
2. Resolve session ID from arguments or find most recent
3. Fetch full details via `get_coaching_session`
**资料来源：** [skills/coaching-session-review/SKILL.md:4-11]()
The session review displays:
- **Session Info**: Coach name, date, duration, mood at start
- **Summary**: AI-generated session summary
- **Key Insights**: All key insights from the session
- **Action Items**: All action items with current status
- **Follow-up**: Suggested next session topics based on insights and pending items
**资料来源：** [skills/coaching-session-review/SKILL.md:11-18]()
### Action Item Management
The `coaching-action-items` skill manages the coaching homework cycle:
```mermaid
graph TD
A[Create Action Item] --> B[Pending Status]
B --> C[In Progress]
C --> D{Complete?}
D -->|Yes| E[Completed]
D -->|No| F[Update/Extend]
F --> C
E --> G[Review in Session]
G --> A
```
Action items should be:
- Specific experiments to test hypotheses
- Linked to insights from sessions or blind spot discovery
- Tracked with clear status progression
**资料来源：** [skills/blind-spot-finder/SKILL.md:27-28]()
### Coach Memory Management
The `coach-memory` skill provides visibility into the AI coach's accumulated knowledge:
```mermaid
graph TD
A[get_working_memory] --> B{All Sections}
B --> C[Core Struggles]
B --> D[Values]
B --> E[Triggers]
B --> F[Breakthroughs]
B --> G[Personality]
B --> H[Communication Style]
B --> I[Patterns]
B --> J[Energy Sources]
B --> K[Relationships]
B --> L[Context]
M[Offer Update] --> N[update_working_memory]
```
For each section, the skill displays:
- Content of the section
- Confidence level
- Flagged sections that are empty or stale
**资料来源：** [skills/coach-memory/SKILL.md:7-25]()
## Multi-Model Deliberation
### LLM Council
The `llm-council` skill implements a structured multi-model deliberation process:
```mermaid
graph TD
A[Start Council] --> B[Stage 1: Individual Responses]
B --> C[Each Model Responds]
C --> D[Stage 2: Peer Review]
D --> E[Models Evaluate Each Other]
E --> F[Rankings Generated]
F --> G[Stage 3: Chairman Synthesis]
G --> H[Final Authoritative Answer]
H --> I[Optional: Save Summary]
```
**Execution flow:**
1. **Stage 1** — Each council member provides an individual response
2. **Stage 2** — Peer review with rankings table showing average rank per model
3. **Stage 3** — Chairman synthesizes all perspectives into a final answer
**资料来源：** [skills/llm-council/SKILL.md:35-50]()
The council uses the `zen consensus` tool for deliberation. Estimated completion:
- Normal tier: 2-5 minutes
- Pro tier: 5-10 minutes
**资料来源：** [skills/llm-council/SKILL.md:33-34]()
### Blind Spot Finder
The `blind-spot-finder` skill uses multi-model council to identify unknown unknowns:
```mermaid
graph TD
A[Context Gathering] --> B[Working Memory]
A --> C[Pending Action Items]
A --> D[Habits Completion]
A --> E[Screen Time 3 Days]
A --> F[Sleep 14 Days]
A --> G[Finance Net Worth]
B --> H[Blind Spot Brief]
C --> H
D --> H
E --> H
F --> H
G --> H
H --> I[Multi-Model Council]
I --> J[3-5 Blind Spots Identified]
J --> K[User Chooses ONE]
K --> L[create_coaching_action_item]
L --> M[update_working_memory]
```
**资料来源：** [skills/blind-spot-finder/SKILL.md:8-28]()
The blind spot brief includes:
- Working memory patterns and triggers
- Say-do gaps between stated goals and actual behavior
- Incomplete action items
- Screen time vs stated priorities
- Any visible self-deceptions
**资料来源：** [skills/blind-spot-finder/SKILL.md:15-25]()
The council focuses on:
- Self-deceptions being maintained
- Local maxima being stuck in
- Unquestioned assumptions
- Invisible patterns from inside them
- Things systematically avoided despite stated desire
**资料来源：** [skills/blind-spot-finder/SKILL.md:25-31]()
## Integration with LifeOS
The Coaching System integrates with other LifeOS modules to provide contextually-aware coaching:
| Module | Integration Point | Purpose |
|--------|-------------------|---------|
| Health | Sleep, readiness data via Oura | Correlate well-being with patterns |
| Habits | Habit completion rates | Track behavior change consistency |
| Finance | Net worth tracking | Ground goals in financial reality |
| Projects | Initiative progress | Connect coaching to execution |
| Working Memory | All memory sections | Persistent coach knowledge |
**资料来源：** [skills/blind-spot-finder/SKILL.md:9-14]()
## Skill Invocation
### Via MCP Protocol
All coaching skills are exposed as MCP prompts, allowing any MCP client to invoke them:
```bash
/coaching-overview # Dashboard view
/coaching-action-items # Manage action items
/coaching-session-review # Review session
/coach-memory # View/manage memory
/blind-spot-finder # Find blind spots
/llm-council # Multi-model deliberation
```
**资料来源：** [AGENTS.md:1-45]()
### Via Claude Code
```bash
claude plugin add github:starascendin/lifeos-plugin
```
Skills are then accessible through the Claude Code agent's skill system.
**资料来源：** [README.md:1-35]()
## Data Models
### Coaching Profile
| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Unique profile identifier |
| `name` | string | Coach persona name |
| `focusAreas` | string[] | Coaching specializations |
| `sessionCadence` | string | Recommended session frequency |
### Coaching Session
| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Session identifier |
| `coachId` | string | Reference to coach profile |
| `title` | string | Session title/topic |
| `date` | datetime | Session date |
| `duration` | number | Duration in minutes |
| `moodAtStart` | string | Mood indicator |
| `summary` | string | AI-generated summary |
| `keyInsights` | string[] | List of key insights |
| `status` | string | Session status |
**资料来源：** [skills/coaching-session-review/SKILL.md:11-15]()
### Working Memory Section
| Field | Type | Description |
|-------|------|-------------|
| `sectionName` | string | Memory section identifier |
| `content` | string | Section content |
| `confidenceLevel` | string | AI confidence in accuracy |
| `lastUpdated` | datetime | Last modification timestamp |
**资料来源：** [skills/coach-memory/SKILL.md:20-25]()
### Coaching Action Item
| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Action item identifier |
| `title` | string | Brief description |
| `status` | enum | pending, in_progress, completed |
| `linkedInsight` | string | Source insight or blind spot |
| `createdAt` | datetime | Creation timestamp |
| `dueDate` | datetime | Target completion date |
**资料来源：** [skills/blind-spot-finder/SKILL.md:27-28]()
## Best Practices
### Coach Memory Maintenance
- Review memory sections regularly for accuracy
- Flag stale sections that need updating
- Update memory after breakthrough insights
- Use memory to inform coaching delivery style
**资料来源：** [skills/coach-memory/SKILL.md:24-26]()
### Action Item Creation
- Create specific experiments, not vague goals
- Link items to identified blind spots or insights
- Use `create_coaching_action_item` for durable tracking
- Update working memory when genuinely new insight emerges
**资料来源：** [skills/blind-spot-finder/SKILL.md:28-29]()
### Multi-Model Council Usage
- Be patient for deliberation results (2-10 minutes)
- Present all three stages for transparency
- Highlight individual model perspectives of value
- Offer to save insights via `create_ai_convo_summary`
**资料来源：** [skills/llm-council/SKILL.md:46-52]()
### Session Review
- Always check for pending action items
- Ground insights in user's specific context
- Suggest forward-looking next steps
- Reference working memory for continuity
**资料来源：** [skills/coaching-session-review/SKILL.md:15-18]()
---
---
## Doramagic Pitfall Log
Project: starascendin/lifeos-plugin
Summary: Found 7 potential pitfall items; 0 are high/blocking. Highest priority: configuration - 可能修改宿主 AI 配置.
## 1. configuration · 可能修改宿主 AI 配置
- Severity: medium
- Evidence strength: source_linked
- Finding: 项目面向 Claude/Cursor/Codex/Gemini/OpenCode 等宿主，或安装命令涉及用户配置目录。
- User impact: 安装可能改变本机 AI 工具行为，用户需要知道写入位置和回滚方法。
- Suggested check: 列出会写入的配置文件、目录和卸载/回滚步骤。
- Guardrail action: 涉及宿主配置目录时必须给回滚路径，不能只给安装命令。
- Evidence: capability.host_targets | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | host_targets=mcp_host, claude, claude_code
## 2. capability · 能力判断依赖假设
- Severity: medium
- Evidence strength: source_linked
- Finding: README/documentation is current enough for a first validation pass.
- User impact: 假设不成立时，用户拿不到承诺的能力。
- Suggested check: 将假设转成下游验证清单。
- Guardrail action: 假设必须转成验证项；没有验证结果前不能写成事实。
- Evidence: capability.assumptions | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | README/documentation is current enough for a first validation pass.
## 3. maintenance · 维护活跃度未知
- Severity: medium
- Evidence strength: source_linked
- Finding: 未记录 last_activity_observed。
- User impact: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
- Suggested check: 补 GitHub 最近 commit、release、issue/PR 响应信号。
- Guardrail action: 维护活跃度未知时，推荐强度不能标为高信任。
- Evidence: evidence.maintainer_signals | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | last_activity_observed missing
## 4. security_permissions · 下游验证发现风险项
- Severity: medium
- Evidence strength: source_linked
- Finding: no_demo
- User impact: 下游已经要求复核，不能在页面中弱化。
- Suggested check: 进入安全/权限治理复核队列。
- Guardrail action: 下游风险存在时必须保持 review/recommendation 降级。
- Evidence: downstream_validation.risk_items | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | no_demo; severity=medium
## 5. security_permissions · 存在评分风险
- Severity: medium
- Evidence strength: source_linked
- Finding: no_demo
- User impact: 风险会影响是否适合普通用户安装。
- Suggested check: 把风险写入边界卡，并确认是否需要人工复核。
- Guardrail action: 评分风险必须进入边界卡，不能只作为内部分数。
- Evidence: risks.scoring_risks | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | no_demo; severity=medium
## 6. maintenance · issue/PR 响应质量未知
- Severity: low
- Evidence strength: source_linked
- Finding: issue_or_pr_quality=unknown。
- User impact: 用户无法判断遇到问题后是否有人维护。
- Suggested check: 抽样最近 issue/PR，判断是否长期无人处理。
- Guardrail action: issue/PR 响应未知时，必须提示维护风险。
- Evidence: evidence.maintainer_signals | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | issue_or_pr_quality=unknown
## 7. maintenance · 发布节奏不明确
- Severity: low
- Evidence strength: source_linked
- Finding: release_recency=unknown。
- User impact: 安装命令和文档可能落后于代码，用户踩坑概率升高。
- Suggested check: 确认最近 release/tag 和 README 安装命令是否一致。
- Guardrail action: 发布节奏未知或过期时，安装说明必须标注可能漂移。
- Evidence: evidence.maintainer_signals | github_repo:1156470663 | https://github.com/starascendin/lifeos-plugin | release_recency=unknown