# minutes - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for minutes. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0004` supported 0.86 - **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. Claim: `clm_0005` supported 0.86 ## What It Can Do - **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution** (Verify after install): The project contains plugin or marketplace configuration, indicating it targets install and distribution across one or more AI hosts. Evidence: `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim: `clm_0002` supported 0.86 - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `CLAUDE.md`, `README.md` Claim: `clm_0003` supported 0.86 ## How to Start - `npx minutes-mcp` Evidence: `README.md` Claim: `clm_0006` supported 0.86 - `npx granola-to-minutes export # Export to ~/meetings/` Evidence: `README.md` Claim: `clm_0007` supported 0.86 - `npm install minutes-sdk` Evidence: `README.md` Claim: `clm_0008` supported 0.86 - `npx vitest run # 30 reader.ts unit tests` Evidence: `CLAUDE.md` Claim: `clm_0009` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Trial the research framework first - **Why**: This project targets research workflows; the core risk is source credibility and output quality. Verify the research framework with Prompt Preview first, then trial it in an isolated environment. ### 30-Second Read - **What to do now**: Trial the research framework first - **Minimum safe next step**: Verify the research framework with Prompt Preview first; trial in isolation only once satisfied - **Do not trust yet**: Research conclusions, citations, and experiment results cannot be trusted before install. - **Continuing will touch**: Research judgment, Command execution, Host AI configuration ### What You Can Trust Now - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0004` supported 0.86 - **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. Claim: `clm_0005` supported 0.86 - **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Capability exists: Multi-Host Install and Distribution** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim: `clm_0002` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `CLAUDE.md`, `README.md` Claim: `clm_0003` supported 0.86 - **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0006` supported 0.86 ### What You Cannot Trust Yet - **Research conclusions, citations, and experiment results cannot be trusted before install.** (unverified): A research Skill can organize questions and paths, but it cannot replace real literature search, paper verification, and experiment reproduction. - **Whether it fits your specific research field cannot be trusted directly.** (unverified): The Skill covering many research topics does not mean it is sufficient for your field, source requirements, and credibility standards. - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. Evidence: `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. ### What Continuing Will Touch - **Research judgment**: Problem decomposition, source paths, experiment paths, conclusion structure, and credibility judgment. Why: A research Skill can make output look more professional but cannot replace real evidence verification. - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `CLAUDE.md`, `README.md` - **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `.claude-plugin/marketplace.json`, `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `CLAUDE.md` et al. - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Verify whether it can correctly frame the research question and evidence boundaries first; do not trust the research output up front. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state. - **Keep a source and conclusion verification checklist**: If citations or experiment paths later prove unreliable, you can return to the evidence-boundary stage and re-check. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0010` inferred 0.45 - **Host AI plugin or Skill rule conflicts**: New rules may change how the user's existing host AI behaves. Mitigation: Inspect the plugin manifest and Skill files before installing, and test in isolation if needed. Evidence: `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim: `clm_0011` supported 0.86 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `CLAUDE.md`, `README.md` Claim: `clm_0012` supported 0.86, `clm_0013` supported 0.86, `clm_0014` contradicted 0.20 - **Source document conflict: skill_count**: The project documentation states inconsistent counts; the AI Context Pack must warn the user not to treat any single number as a verified fact. Mitigation: Flag it as unverified in both the Human Manual and the AI Context Pack rather than forcing a single number. Evidence: `CLAUDE.md`, `docs/release/notes/v0.8.0.md`, `README.md` Claim: `clm_0012` supported 0.86, `clm_0013` supported 0.86, `clm_0014` contradicted 0.20 - **Source file conflict skill_count**: multiple values `18, 19` found; verify before real use. - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md`, `.agents/skills/minutes/minutes-cleanup/SKILL.md`, `.agents/skills/minutes/minutes-copilot/SKILL.md`, `.agents/skills/minutes/minutes-debrief/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim: `clm_0002` supported 0.86 - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `CLAUDE.md`, `README.md` Claim: `clm_0003` supported 0.86 ### Context Scale - Total files: 887 - Important-file coverage: 40/887 - Evidence index entries: 180 - Role / Skill entries: 161 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for minutes, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat minutes as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for minutes, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 161 role / Skill / project-doc entries. - **minutes-brief** (skill): Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right befor… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-brief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md` - **minutes-cleanup** (skill): Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-cleanup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-cleanup/SKILL.md` - **minutes-copilot** (skill): Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minut… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-copilot”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-copilot/SKILL.md` - **minutes-debrief** (skill): Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-debrief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-debrief/SKILL.md` - **minutes-graph** (skill): Cross-meeting entity graph — query who/what/when across all your meetings as structured data, with co-occurrence and cross-entity queries that text search can't answer. Use whenever the user says "show me everyone who mentioned X", "all mentions of Y across meetings", "who knows about Z", "graph", "across all meetings", "entity search", "first time we talked about", "trend for X over time", "who's been mentioned alo… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-graph”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-graph/SKILL.md` - **minutes-ideas** (skill): Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ideas”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-ideas/SKILL.md` - **minutes-ingest** (skill): Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ingest”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-ingest/SKILL.md` - **minutes-lint** (skill): Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-lint”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-lint/SKILL.md` - **minutes-list** (skill): List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-list”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-list/SKILL.md` - **minutes-live-sidekick** (skill): Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-live-sidekick”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-live-sidekick/SKILL.md` - **minutes-mirror** (skill): Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and when meetings are tagged via /minutes-tag what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time"… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-mirror”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-mirror/SKILL.md` - **minutes-note** (skill): Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-note”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-note/SKILL.md` - **minutes-prep** (skill): Interactive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me for my call with", "I'm meeting with X", "prepare me for", "what should I bring up with", "meeting prep", "get ready for my call", or wants to review history with someone before a meeting. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-prep”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-prep/SKILL.md` - **minutes-recap** (skill): Generate a daily digest of today's meetings and voice memos — key decisions, action items, and themes across all recordings. Use when the user asks "recap my day", "what happened in my meetings today", "daily summary", "what did I discuss today", "any action items from today", or wants a consolidated view of the day's conversations. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-recap”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-recap/SKILL.md` - **minutes-record** (skill): Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is being recorded. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-record”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-record/SKILL.md` - **minutes-release-notes** (skill): Draft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a changelog for a Minutes version. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-release-notes”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-release-notes/SKILL.md` - **minutes-search** (skill): Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for". Activation hint: When the user's task is highly relevant to the workflow described by “minutes-search”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-search/SKILL.md` - **minutes-seo-wave** (skill): Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro. Use when the user asks for an SEO wave, a group of comparison or use-case pages, a docs or resource hub expansion, or a coordinated batch of search landing pages. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-seo-wave”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-seo-wave/SKILL.md` - **minutes-setup** (skill): Guided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes", or when verify shows missing components. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-setup/SKILL.md` - **minutes-tag** (skill): Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meeti… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-tag”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-tag/SKILL.md` - **minutes-verify** (skill): Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-verify”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-verify/SKILL.md` - **minutes-video-review** (skill): Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames, issues, and next steps. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-video-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-video-review/SKILL.md` - **minutes-weekly** (skill): Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review", or at the end of a work week. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-weekly”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/minutes/minutes-weekly/SKILL.md` - **minutes-brief** (skill): Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right befor… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-brief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-brief/SKILL.md` - **minutes-cleanup** (skill): Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-cleanup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-cleanup/SKILL.md` - **minutes-copilot** (skill): Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minut… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-copilot”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-copilot/SKILL.md` - **minutes-debrief** (skill): Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-debrief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-debrief/SKILL.md` - **minutes-graph** (skill): Cross-meeting entity graph — query who/what/when across all your meetings as structured data, with co-occurrence and cross-entity queries that text search can't answer. Use whenever the user says "show me everyone who mentioned X", "all mentions of Y across meetings", "who knows about Z", "graph", "across all meetings", "entity search", "first time we talked about", "trend for X over time", "who's been mentioned alo… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-graph”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-graph/SKILL.md` - **minutes-ideas** (skill): Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ideas”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-ideas/SKILL.md` - **minutes-ingest** (skill): Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ingest”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-ingest/SKILL.md` - **minutes-lint** (skill): Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-lint”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-lint/SKILL.md` - **minutes-list** (skill): List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-list”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-list/SKILL.md` - **minutes-live-sidekick** (skill): Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-live-sidekick”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-live-sidekick/SKILL.md` - **minutes-mirror** (skill): Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and when meetings are tagged via /minutes-tag what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time"… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-mirror”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-mirror/SKILL.md` - **minutes-note** (skill): Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-note”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-note/SKILL.md` - **minutes-prep** (skill): Interactive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me for my call with", "I'm meeting with X", "prepare me for", "what should I bring up with", "meeting prep", "get ready for my call", or wants to review history with someone before a meeting. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-prep”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-prep/SKILL.md` - **minutes-recap** (skill): Generate a daily digest of today's meetings and voice memos — key decisions, action items, and themes across all recordings. Use when the user asks "recap my day", "what happened in my meetings today", "daily summary", "what did I discuss today", "any action items from today", or wants a consolidated view of the day's conversations. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-recap”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-recap/SKILL.md` - **minutes-record** (skill): Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is being recorded. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-record”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-record/SKILL.md` - **minutes-release-notes** (skill): Draft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a changelog for a Minutes version. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-release-notes”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-release-notes/SKILL.md` - **minutes-search** (skill): Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for". Activation hint: When the user's task is highly relevant to the workflow described by “minutes-search”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-search/SKILL.md` - **minutes-seo-wave** (skill): Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro. Use when the user asks for an SEO wave, a group of comparison or use-case pages, a docs or resource hub expansion, or a coordinated batch of search landing pages. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-seo-wave”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-seo-wave/SKILL.md` - **minutes-setup** (skill): Guided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes", or when verify shows missing components. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-setup/SKILL.md` - **minutes-tag** (skill): Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meeti… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-tag”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-tag/SKILL.md` - **minutes-verify** (skill): Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-verify”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-verify/SKILL.md` - **minutes-video-review** (skill): Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames, issues, and next steps. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-video-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-video-review/SKILL.md` - **minutes-weekly** (skill): Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review", or at the end of a work week. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-weekly”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/plugins/minutes/skills/minutes-weekly/SKILL.md` - **minutes-brief** (skill): Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right befor… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-brief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-brief/SKILL.md` - **minutes-cleanup** (skill): Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-cleanup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-cleanup/SKILL.md` - **minutes-copilot** (skill): Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minut… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-copilot”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-copilot/SKILL.md` - **minutes-debrief** (skill): Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-debrief”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-debrief/SKILL.md` - **minutes-graph** (skill): Cross-meeting entity graph — query who/what/when across all your meetings as structured data, with co-occurrence and cross-entity queries that text search can't answer. Use whenever the user says "show me everyone who mentioned X", "all mentions of Y across meetings", "who knows about Z", "graph", "across all meetings", "entity search", "first time we talked about", "trend for X over time", "who's been mentioned alo… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-graph”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-graph/SKILL.md` - **minutes-ideas** (skill): Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ideas”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-ideas/SKILL.md` - **minutes-ingest** (skill): Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ingest”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-ingest/SKILL.md` - **minutes-lint** (skill): Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-lint”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-lint/SKILL.md` - **minutes-list** (skill): List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-list”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-list/SKILL.md` - **minutes-live-sidekick** (skill): Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-live-sidekick”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-live-sidekick/SKILL.md` - **minutes-mirror** (skill): Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and when meetings are tagged via /minutes-tag what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time"… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-mirror”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-mirror/SKILL.md` - **minutes-note** (skill): Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-note”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-note/SKILL.md` - **minutes-prep** (skill): Interactive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me for my call with", "I'm meeting with X", "prepare me for", "what should I bring up with", "meeting prep", "get ready for my call", or wants to review history with someone before a meeting. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-prep”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-prep/SKILL.md` - **minutes-recap** (skill): Generate a daily digest of today's meetings and voice memos — key decisions, action items, and themes across all recordings. Use when the user asks "recap my day", "what happened in my meetings today", "daily summary", "what did I discuss today", "any action items from today", or wants a consolidated view of the day's conversations. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-recap”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-recap/SKILL.md` - **minutes-record** (skill): Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is being recorded. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-record”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-record/SKILL.md` - **minutes-release-notes** (skill): Draft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a changelog for a Minutes version. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-release-notes”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-release-notes/SKILL.md` - **minutes-search** (skill): Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for". Activation hint: When the user's task is highly relevant to the workflow described by “minutes-search”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-search/SKILL.md` - **minutes-seo-wave** (skill): Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro. Use when the user asks for an SEO wave, a group of comparison or use-case pages, a docs or resource hub expansion, or a coordinated batch of search landing pages. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-seo-wave”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-seo-wave/SKILL.md` - **minutes-setup** (skill): Guided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes", or when verify shows missing components. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-setup/SKILL.md` - **minutes-tag** (skill): Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meeti… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-tag”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-tag/SKILL.md` - **minutes-verify** (skill): Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-verify”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-verify/SKILL.md` - **minutes-video-review** (skill): Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames, issues, and next steps. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-video-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-video-review/SKILL.md` - **minutes-weekly** (skill): Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review", or at the end of a work week. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-weekly”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/minutes-weekly/SKILL.md` - **minutes-brief** (skill): Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right befor… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-brief”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-brief/SKILL.md` - **minutes-cleanup** (skill): Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-cleanup”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-cleanup/SKILL.md` - **minutes-copilot** (skill): Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minut… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-copilot”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-copilot/SKILL.md` - **minutes-debrief** (skill): Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-debrief”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-debrief/SKILL.md` - **minutes-graph** (skill): Cross-meeting entity graph — query who/what/when across all your meetings as structured data, with co-occurrence and cross-entity queries that text search can't answer. Use whenever the user says "show me everyone who mentioned X", "all mentions of Y across meetings", "who knows about Z", "graph", "across all meetings", "entity search", "first time we talked about", "trend for X over time", "who's been mentioned alo… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-graph”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-graph/SKILL.md` - **minutes-ideas** (skill): Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ideas”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-ideas/SKILL.md` - **minutes-ingest** (skill): Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-ingest”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-ingest/SKILL.md` - **minutes-lint** (skill): Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-lint”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-lint/SKILL.md` - **minutes-list** (skill): List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching. Activation hint: When the user's task is highly relevant to the workflow described by “minutes-list”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-list/SKILL.md` - **minutes-live-sidekick** (skill): Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-live-sidekick”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-live-sidekick/SKILL.md` - **minutes-mirror** (skill): Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and when meetings are tagged via /minutes-tag what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time"… Activation hint: When the user's task is highly relevant to the workflow described by “minutes-mirror”, use it for a pre-install experience first, then decide whether to install. Evidence: `tooling/skills/goldens/claude/minutes-mirror/SKILL.md` - The remaining 81 entries are in `AI_CONTEXT_PACK.json`. ## Evidence Index - Indexed 180 evidence entries. - **Minutes Documentation Structure** (documentation): Documentation is organized by purpose under docs/ . This index describes each folder and how to contribute new docs. Evidence: `docs/README.md` - **Beads - AI-Native Issue Tracking** (documentation): Welcome to Beads! This repository uses Beads for issue tracking - a modern, AI-native tool designed to live directly in your codebase alongside your code. Evidence: `.beads/README.md` - **Minutes — Linux Codespace** (documentation): A GitHub Codespace for testing Minutes on Linux without needing a Linux machine. Evidence: `.devcontainer/README.md` - **minutes** (documentation): ! GitHub stars https://img.shields.io/github/stars/silverstein/minutes?style=social https://github.com/silverstein/minutes ! License: MIT https://img.shields.io/badge/License-MIT-blue.svg LICENSE ! crates.io https://img.shields.io/crates/v/minutes-cli.svg https://crates.io/crates/minutes-cli Evidence: `README.md` - **Minutes Reference Adapters** (documentation): Small working adapters that pipe Minutes markdown output into third-party agent-memory platforms. Each one demonstrates that the Minutes frontmatter contract ../docs/architecture/frontmatter-schema.md interoperates with the rest of the agent-memory ecosystem at a baseline level. The filesystem is the integration contract; these adapters are runnable proof sketches, not production-grade integrations. Evidence: `examples/README.md` - **Minutes Skill Packs** (documentation): Skill packs are small JSON bundles that group existing Minutes plugin skills into a named workflow package. The point is not to invent a second plugin system. The point is to make the existing skill graph installable, recommendable, and checkable by agents without guessing. Evidence: `.claude/plugins/minutes/packs/README.md` - **minutes** (documentation): ! Crates.io https://img.shields.io/crates/v/minutes-cli https://crates.io/crates/minutes-cli ! License: MIT https://img.shields.io/badge/License-MIT-blue.svg https://github.com/silverstein/minutes/blob/main/LICENSE ! GitHub stars https://img.shields.io/github/stars/silverstein/minutes?style=social https://github.com/silverstein/minutes Evidence: `crates/cli/README.md` - **Readme** (documentation): Bundled file: silero vad v5.safetensors Evidence: `crates/cli/assets/parakeet/README.md` - **minutes-sdk** (documentation): Conversation memory for AI agents. Query meeting transcripts, decisions, action items, and people from any AI agent or application. Evidence: `crates/sdk/README.md` - **whisper-guard** (documentation): ! Crates.io https://img.shields.io/crates/v/whisper-guard.svg https://crates.io/crates/whisper-guard ! Docs.rs https://docs.rs/whisper-guard/badge.svg https://docs.rs/whisper-guard ! License: MIT https://img.shields.io/badge/license-MIT-blue.svg license Evidence: `crates/whisper-guard/README.md` - **Minutes → Graphiti Adapter** (documentation): Reference implementation. Pipes Minutes meetings into Graphiti https://github.com/getzep/graphiti , Zep's OSS temporal knowledge graph for agent memory. Evidence: `examples/graphiti/README.md` - **Minutes → Mem0 Adapter** (documentation): Reference implementation. Walks your Minutes meetings folder, parses frontmatter, and pushes structured memories into Mem0 https://mem0.ai . Evidence: `examples/mem0/README.md` - **Minutes Cowork Extension** (documentation): This is the minimal Cowork-facing extension bundle for Minutes. Evidence: `integrations/claude-cowork-extension/README.md` - **minutes-diarize-sidecar** (documentation): Persistent streaming speaker-diarization sidecar for Minutes' live path. NVIDIA Sortformer streaming, 4-speaker via parakeet-rs https://crates.io/crates/parakeet-rs + ONNX ort . No Python at runtime. Evidence: `sidecars/diarize-streaming/README.md` - **Marketplace** (structured_config): { "name": "minutes", "owner": { "name": "Mat Silverstein", "email": "mat@businessvacation.com" }, "plugins": { "name": "minutes", "source": "./.claude/plugins/minutes", "description": "19 skills + 1 agent + 2 hooks for the full meeting lifecycle: brief, prep, record, tag, debrief, mirror, weekly synthesis, entity graph, video review, and cross-device voice memo recall", "version": "0.20.0", "author": { "name": "Mat Silverstein" }, "homepage": "https://useminutes.app", "repository": "https://github.com/silverstein/minutes", "license": "MIT", "keywords": "meeting", "transcription", "memory", "voice-memo", "whisper", "conversation", "ai-memory" , "category": "productivity" } } Evidence: `.claude-plugin/marketplace.json` - **Copilot eval corpus v1** (documentation): Every transcript in this directory is synthetic. No private meeting content, customer data, or copied conversation text is included. Evidence: `crates/core/tests/fixtures/copilot_eval/v1/README.md` - **Live-sidekick eval corpus v1** (documentation): Every JSON fixture in this directory is synthetic and authored from scratch. The corpus contains no copied, redacted, anonymized, or name-swapped meeting text. Speaker identity is represented only by the role tokens documented in each fixture's privacy.approved role tokens list. Evidence: `crates/core/tests/fixtures/live_sidekick_eval/v1/README.md` - **Agent Instructions** (documentation): This project uses bd beads for issue tracking. Run bd onboard to get started. In this repo, beads is local-only : use it for structured issue tracking on your machine, but do not expect a shared Dolt remote. Evidence: `AGENTS.md` - **CLAUDE.md — Minutes** (documentation): Your AI remembers every conversation you've had. Evidence: `CLAUDE.md` - **Minutes Frontmatter Schema** (documentation): This page is the interop contract. Any tool, agent, or context graph that reads meeting files written by Minutes can rely on the schema below. Any tool that wants to produce Minutes-compatible output should emit the same shape. Evidence: `docs/architecture/frontmatter-schema.md` - **Package** (package_manifest): { "name": "minutes-site", "version": "0.1.0", "private": true, "scripts": { "generate:llms": "node ../scripts/generate llms txt.mjs", "check:llms": "node ../scripts/generate llms txt.mjs --check", "dev": "next dev --turbopack", "build": "next build", "start": "next start" }, "dependencies": { "@react-three/drei": "^10.7.7", "@react-three/fiber": "^9.5.0", "@remotion/player": "^4.0.446", "@types/three": "^0.183.1", "@vercel/analytics": "^2.0.1", "geist": "^1.4.1", "next": "^16.2.3", "react": "^19.2.5", "react-dom": "^19.2.5", "remotion": "^4.0.446", "three": "^0.183.2" }, "devDependencies": { "@types/node": "^22.15.0", "@types/react": "^19.2.14", "@types/react-dom": "^19.2.3", "postcss": "^8… Evidence: `site/package.json` - **Contributing to Minutes** (documentation): Thanks for your interest in contributing! Minutes is a solo project that welcomes contributors — whether it's a bug fix, a feature, a docs improvement, or just filing an issue. Evidence: `CONTRIBUTING.md` - **Package** (package_manifest): { "name": "minutes-mcp", "version": "0.22.1", "description": "MCP server for minutes — conversation memory for AI assistants. Works with Claude Desktop, Mistral Vibe, Cursor, Windsurf, and any MCP client.", "main": "dist/index.js", "type": "module", "bin": { "minutes-mcp": "dist/index.js" }, "files": "dist/", "dist-ui/", "fixtures/", "LICENSE" , "keywords": "mcp", "meeting", "transcription", "ai", "claude", "memory", "conversation", "whisper" , "repository": { "type": "git", "url": "git+https://github.com/silverstein/minutes.git" }, "license": "MIT", "author": "Mat Silverstein", "scripts": { "build": "tsc && vite build", "build:ui": "vite build", "test": "npm run build && node test/mcp tool… Evidence: `crates/mcp/package.json` - **Package** (package_manifest): { "name": "minutes-sdk", "version": "0.22.1", "description": "Conversation memory SDK — query meeting transcripts, decisions, and action items from any AI agent or application", "main": "dist/index.js", "types": "dist/index.d.ts", "type": "module", "files": "dist/", "README.md" , "keywords": "meeting", "transcription", "memory", "ai", "agent", "mcp", "claude", "langchain", "conversation", "whisper" , "repository": { "type": "git", "url": "git+https://github.com/silverstein/minutes.git" }, "license": "MIT", "author": "Mat Silverstein", "scripts": { "build": "tsc", "test": "vitest run", "prepublishOnly": "npm run build" }, "dependencies": { "yaml": "^2.8.3" }, "devDependencies": { "@types/nod… Evidence: `crates/sdk/package.json` - **Package** (package_manifest): { "name": "demo-video", "version": "1.0.0", "description": "", "main": "index.js", "scripts": { "test": "echo \"Error: no test specified\" && exit 1" }, "keywords": , "author": "", "license": "ISC", "dependencies": { "@remotion/cli": "^4.0.446", "@remotion/player": "^4.0.446", "@types/react": "^19.2.14", "@types/react-dom": "^19.2.3", "react": "^19.2.4", "react-dom": "^19.2.4", "remotion": "^4.0.446", "typescript": "^6.0.2" } } Evidence: `docs/demo-video/package.json` - **Package** (package_manifest): { "name": "demo", "version": "1.0.0", "description": "", "main": "index.js", "scripts": { "test": "echo \"Error: no test specified\" && exit 1" }, "keywords": , "author": "", "license": "ISC", "type": "commonjs", "dependencies": { "@remotion/cli": "^4.0.446", "@remotion/renderer": "^4.0.446", "react": "^19.2.4", "react-dom": "^19.2.4", "remotion": "^4.0.446" }, "devDependencies": { "@types/react": "^19.2.14", "typescript": "^5.9.3" } } Evidence: `docs/demo/package.json` - **Package** (package_manifest): { "name": "minutes-cowork-extension", "version": "0.1.0", "private": true, "type": "module", "description": "Cowork / Claude Desktop extension bundle for Minutes MCP tools", "main": "server/index.js", "license": "MIT", "dependencies": { "@modelcontextprotocol/sdk": "^1.29.0", "zod": "^4.3.6" } } Evidence: `integrations/claude-cowork-extension/package.json` - **Package** (package_manifest): { "name": "minutes-skill-tooling", "private": true, "type": "module", "scripts": { "build": "tsc -p tsconfig.json", "test": "node --test dist/compiler/ .test.js", "compile": "node dist/compiler/compile.js", "compile:dry": "node dist/compiler/compile.js --dry-run --host claude --host codex --host opencode", "resolvable": "node dist/compiler/resolver.js", "routing": "node dist/compiler/routing.js", "routing:agents": "node dist/compiler/agent-routing.js", "skill-audit": "node dist/compiler/skill-audit.js", "surface-audit": "node dist/compiler/surface-audit.js", "check": "node dist/compiler/check.js && npm run resolvable && npm run routing && npm run surface-audit", "golden": "node dist/compile… Evidence: `tooling/skills/package.json` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-brief/SKILL.md` - **/minutes-cleanup** (skill_instruction): Help the user manage disk space and organize old recordings. Minutes is transcript-first: markdown notes and structured memory are durable, while raw audio is a temporary recovery/reprocessing layer unless pinned. Evidence: `.agents/skills/minutes/minutes-cleanup/SKILL.md` - **/minutes-copilot** (skill_instruction): Use the real Minutes copilot runtime to start or control Coach. Do not build a transcript reader, event poller, prompt loop, or shell tailer in this skill. Evidence: `.agents/skills/minutes/minutes-copilot/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-debrief/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-graph/SKILL.md` - **/minutes-ideas — Recent Voice Memos & Ideas** (skill_instruction): /minutes-ideas — Recent Voice Memos & Ideas Evidence: `.agents/skills/minutes/minutes-ideas/SKILL.md` - **/minutes-ingest** (skill_instruction): Process meetings through the knowledge extraction pipeline to update person profiles, append to the knowledge log, and maintain the index. Evidence: `.agents/skills/minutes/minutes-ingest/SKILL.md` - **/minutes-lint** (skill_instruction): Run a consistency check across all meetings to find decision conflicts and stale commitments. Evidence: `.agents/skills/minutes/minutes-lint/SKILL.md` - **/minutes-list** (skill_instruction): Show recent meetings and voice memos, sorted newest-first. Evidence: `.agents/skills/minutes/minutes-list/SKILL.md` - **/minutes-live-sidekick** (skill_instruction): Act as the live meeting sidekick in the current terminal agent session. Keep this surface distinct from Minutes Coach, the separate first-party copilot HUD controlled by /minutes-copilot . Evidence: `.agents/skills/minutes/minutes-live-sidekick/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-mirror/SKILL.md` - **/minutes-note** (skill_instruction): Add a timestamped note during a recording, or annotate a past meeting. Evidence: `.agents/skills/minutes/minutes-note/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-prep/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-recap/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-record/SKILL.md` - **/minutes-release-notes** (skill_instruction): Draft release notes that explain why a Minutes release matters without making users decode the commit history. Produce a draft only. Do not create, edit, or publish a GitHub release unless the user explicitly asks. Evidence: `.agents/skills/minutes/minutes-release-notes/SKILL.md` - **/minutes-search** (skill_instruction): Find information across all meeting transcripts and voice memos. Evidence: `.agents/skills/minutes/minutes-search/SKILL.md` - **/minutes-seo-wave** (skill_instruction): Produce one coherent SEO content wave, not a pile of disconnected pages. Keep the method reusable across comparison pages, use-case or resource pages, and docs hubs. Evidence: `.agents/skills/minutes/minutes-seo-wave/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-setup/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-tag/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-verify/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-video-review/SKILL.md` - **Skill Path** (skill_instruction): Before running helper scripts or opening bundled references, set: Evidence: `.agents/skills/minutes/minutes-weekly/SKILL.md` - **/minutes-brief** (skill_instruction): Fast, non-interactive briefing that synthesizes your relationship history with someone into a one-page brief — designed so you can read it in 60 seconds before walking into a call. Evidence: `.claude/plugins/minutes/skills/minutes-brief/SKILL.md` - **/minutes-cleanup** (skill_instruction): Help the user manage disk space and organize old recordings. Minutes is transcript-first: markdown notes and structured memory are durable, while raw audio is a temporary recovery/reprocessing layer unless pinned. Evidence: `.claude/plugins/minutes/skills/minutes-cleanup/SKILL.md` - **/minutes-copilot** (skill_instruction): Use the real Minutes copilot runtime to start or control Coach. Do not build a transcript reader, event poller, prompt loop, or shell tailer in this skill. Evidence: `.claude/plugins/minutes/skills/minutes-copilot/SKILL.md` - **/minutes-debrief** (skill_instruction): Post-meeting analysis that reads your latest recording, compares what happened to what you planned, and surfaces decision evolution — so nothing falls through the cracks. Evidence: `.claude/plugins/minutes/skills/minutes-debrief/SKILL.md` - **/minutes-graph** (skill_instruction): Cross-meeting entity graph that lets you query your meeting history as structured data — people and topics out of the box, with companies and products as an opt-in deep-extraction path. Evidence: `.claude/plugins/minutes/skills/minutes-graph/SKILL.md` - **/minutes-ideas — Recent Voice Memos & Ideas** (skill_instruction): /minutes-ideas — Recent Voice Memos & Ideas Evidence: `.claude/plugins/minutes/skills/minutes-ideas/SKILL.md` - **/minutes-ingest** (skill_instruction): Process meetings through the knowledge extraction pipeline to update person profiles, append to the knowledge log, and maintain the index. Evidence: `.claude/plugins/minutes/skills/minutes-ingest/SKILL.md` - **/minutes-lint** (skill_instruction): Run a consistency check across all meetings to find decision conflicts and stale commitments. Evidence: `.claude/plugins/minutes/skills/minutes-lint/SKILL.md` - **/minutes-list** (skill_instruction): Show recent meetings and voice memos, sorted newest-first. Evidence: `.claude/plugins/minutes/skills/minutes-list/SKILL.md` - The remaining 120 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `docs/README.md`, `.beads/README.md`, `.devcontainer/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `docs/README.md`, `.beads/README.md`, `.devcontainer/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Project Overview & Architecture**: importance `high` - source_paths: README.md, crates/core/src/lib.rs, crates/core/src/pipeline.rs, crates/core/src/markdown.rs, docs/architecture/frontmatter-schema.md - **Audio Capture, Transcription & Live Pipelines**: importance `high` - source_paths: crates/core/src/capture.rs, crates/core/src/transcribe.rs, crates/core/src/streaming.rs, crates/core/src/streaming_whisper.rs, crates/core/src/streaming_diarize.rs - **AI Agent Surfaces, MCP Server & Skills**: importance `high` - source_paths: crates/mcp/src/index.ts, crates/mcp/src/capabilities.ts, crates/mcp/src/paths.ts, crates/mcp/src/autoInstall.ts, crates/mcp/src/captureRelay.ts - **Platform Operations, Permissions & Known Failure Modes**: importance `high` - source_paths: crates/core/src/macos_permissions.rs, crates/core/src/device_monitor.rs, crates/core/src/config.rs, crates/core/src/health.rs, crates/core/src/hotkey_macos.rs ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `87eff6010e949a8a9264b6966ec95631f019f2bf` - inspected_files: `README.md`, `docs/README.md`, `docs/architecture/apple-foundation-models.md`, `docs/architecture/apple-speech.md`, `docs/architecture/audio-devices.md`, `docs/architecture/coach-model-selection.md`, `docs/architecture/config.md`, `docs/architecture/consent-enforcement.md`, `docs/architecture/context-store.md`, `docs/architecture/core-audio-process-tap.md`, `docs/architecture/frontmatter-schema.md`, `docs/architecture/multi-source-capture.md`, `docs/architecture/parakeet.md`, `docs/architecture/sherpa-engine.md`, `docs/checklists/call-capture-regression-checklist.md`, `docs/checklists/compatibility-checklist.md`, `docs/checklists/desktop-context-runtime-checklist.md`, `docs/checklists/pre-commit.md`, `docs/coach.md`, `docs/demo/package-lock.json` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Security or permission risk requires verification - Trigger: Developers should check this security_permissions risk before relying on the project: CGEventTap leak: long-running app accumulates 512+ disabled taps, exhausting the system tap table (breaks screenshots system-wide) - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: CGEventTap leak: long-running app accumulates 512+ disabled taps, exhausting the system tap table (breaks screenshots system-wide). Context: Observed when using macos - Why it matters: Developers may expose sensitive permissions or credentials: CGEventTap leak: long-running app accumulates 512+ disabled taps, exhausting the system tap table (breaks screenshots system-wide) - Evidence: failure_mode_cluster:github_issue | https://github.com/silverstein/minutes/issues/488 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Security or permission risk requires verification - Trigger: Developers should check this security_permissions risk before relying on the project: Input Monitoring probe: don't cache a transient first-probe timeout as a false "restart needed" - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Input Monitoring probe: don't cache a transient first-probe timeout as a false "restart needed". Context: Observed when using macos - Why it matters: Developers may expose sensitive permissions or credentials: Input Monitoring probe: don't cache a transient first-probe timeout as a false "restart needed" - Evidence: failure_mode_cluster:github_issue | https://github.com/silverstein/minutes/issues/501 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: Recall chat panel text is not selectable or copyable (inherits body `user-select: none`) - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Recall chat panel text is not selectable or copyable (inherits body `user-select: none`). Context: Observed during installation or first-run setup. - Why it matters: Developers may fail before the first successful local run: Recall chat panel text is not selectable or copyable (inherits body `user-select: none`) - Evidence: failure_mode_cluster:github_issue | https://github.com/silverstein/minutes/issues/490 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: system_audio_record in Minutes 0.22.0 is built for macOS 26 and crashes on macOS 15 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: system_audio_record in Minutes 0.22.0 is built for macOS 26 and crashes on macOS 15. Context: Observed when using macos - Why it matters: Developers may fail before the first successful local run: system_audio_record in Minutes 0.22.0 is built for macOS 26 and crashes on macOS 15 - Evidence: failure_mode_cluster:github_issue | https://github.com/silverstein/minutes/issues/494 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: v0.18.13 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.18.13. Context: Observed when using windows, macos - Why it matters: Upgrade or migration may change expected behavior: v0.18.13 - Evidence: failure_mode_cluster:github_release | https://github.com/silverstein/minutes/releases/tag/v0.18.13 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 6: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: v0.18.14 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.18.14. Context: Observed when using windows, macos - Why it matters: Upgrade or migration may change expected behavior: v0.18.14 - Evidence: failure_mode_cluster:github_release | https://github.com/silverstein/minutes/releases/tag/v0.18.14 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 7: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: v0.19.0: Sherpa SOTA engine + sensitivity enforcement - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.19.0: Sherpa SOTA engine + sensitivity enforcement. Context: Observed when using python, windows, macos, linux - Why it matters: Upgrade or migration may change expected behavior: v0.19.0: Sherpa SOTA engine + sensitivity enforcement - Evidence: failure_mode_cluster:github_release | https://github.com/silverstein/minutes/releases/tag/v0.19.0 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 8: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: v0.20.0: Dictation at your cursor, in-app Documents, honest degradation - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.20.0: Dictation at your cursor, in-app Documents, honest degradation. Context: Observed when using windows, macos - Why it matters: Upgrade or migration may change expected behavior: v0.20.0: Dictation at your cursor, in-app Documents, honest degradation - Evidence: failure_mode_cluster:github_release | https://github.com/silverstein/minutes/releases/tag/v0.20.0 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.