# minutes - Doramagic AI Context Pack

> 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。

## 充分原则

- **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。
- **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。

## 给宿主 AI 的使用方式

你正在读取 Doramagic 为 minutes 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。

## Claim 消费规则

- **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。
- **事实最低状态**：`supported`
- `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。
- `weak`：只能作为低置信度线索，必须要求用户继续核实。
- `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。
- `unverified`：不得作为事实使用，应明确说证据不足。
- `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。

## 它最适合谁

- **正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**：README 或插件配置提到多个宿主 AI。 证据：`README.md` Claim：`clm_0004` supported 0.86
- **希望把专业流程带进宿主 AI 的用户**：仓库包含 Skill 文档。 证据：`.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` 等 Claim：`clm_0005` supported 0.86

## 它能做什么

- **AI Skill / Agent 指令资产库**（可做安装前预览）：项目包含可被宿主 AI 读取的 Skill 或 Agent 指令文件，可用于把专业流程带入 Claude、Codex、Cursor 等宿主。 证据：`.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` 等 Claim：`clm_0001` supported 0.86
- **多宿主安装与分发**（需要安装后验证）：项目包含插件或 marketplace 配置，说明它面向一个或多个 AI 宿主的安装和分发。 证据：`.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim：`clm_0002` unverified 0.25
- **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`CLAUDE.md`, `README.md` Claim：`clm_0003` supported 0.86

## 怎么开始

- `npx minutes-mcp` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `npx granola-to-minutes export    # Export to ~/meetings/` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `npm install minutes-sdk` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `npx vitest run                                      # 30 reader.ts unit tests` 证据：`CLAUDE.md` Claim：`clm_0009` supported 0.86

## 继续前判断卡

- **当前建议**：先做研究框架试用
- **为什么**：这个项目面向研究工作流，核心风险是资料可信度和输出质量；先用 Prompt Preview 验证研究框架，再在隔离环境试装。

### 30 秒判断

- **现在怎么做**：先做研究框架试用
- **最小安全下一步**：先用 Prompt Preview 验证研究框架；满意后再隔离试装
- **先别相信**：研究结论、引用和实验结果不能在安装前相信。
- **继续会触碰**：研究判断、命令执行、宿主 AI 配置

### 现在可以相信

- **适合人群线索：正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0004` supported 0.86
- **适合人群线索：希望把专业流程带进宿主 AI 的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`.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` 等 Claim：`clm_0005` supported 0.86
- **能力存在：AI Skill / Agent 指令资产库**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`.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` 等 Claim：`clm_0001` supported 0.86
- **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`CLAUDE.md`, `README.md` Claim：`clm_0003` supported 0.86
- **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0006` supported 0.86

### 现在还不能相信

- **研究结论、引用和实验结果不能在安装前相信。**（unverified）：研究 Skill 可以组织问题和路径，但不能替代真实资料检索、论文核验和实验复现。
- **是否适合你的具体研究领域不能直接相信。**（unverified）：Skill 覆盖很多研究主题，不代表对你的领域、资料要求和可信度标准足够。
- **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。
- **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。
- **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 证据：`.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` 等
- **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。
- **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。 证据：`.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json`
- **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。

### 继续会触碰什么

- **研究判断**：问题拆解、资料路径、实验路径、结论结构和可信度判断。 原因：研究型 Skill 可能让输出看起来更专业，但不能替代真实证据核验。
- **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`CLAUDE.md`, `README.md`
- **宿主 AI 配置**：Claude/Codex/Cursor/Gemini/OpenCode 等宿主的 plugin、Skill 或规则加载配置。 原因：宿主配置会改变 AI 后续工作方式，可能和用户已有规则冲突。 证据：`.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` 等
- **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`.claude-plugin/marketplace.json`, `.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `CLAUDE.md` 等
- **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。

### 最小安全下一步

- **先跑 Prompt Preview**：先验证它能否正确界定研究问题和证据边界，不要先相信研究输出。（适用：任何项目都适用，尤其是输出质量未知时。）
- **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。）
- **先备份宿主 AI 配置**：Skill、plugin、规则文件可能改变 Claude/Cursor/Codex 的默认行为。（适用：存在插件 manifest、Skill 或宿主规则入口时。）
- **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。）

### 退出方式

- **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。
- **准备移除宿主 plugin / Skill / 规则入口**：如果试装后行为异常，可以把宿主 AI 恢复到试装前状态。
- **保留资料和结论核验清单**：如果后续发现引用或实验路径不可靠，可以回到证据边界阶段重新校验。
- **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。
- **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。

## 哪些只能预览

- 解释项目适合谁和能做什么
- 基于项目文档演示典型对话流程
- 帮助用户判断是否值得安装或继续研究

## 哪些必须安装后验证

- 真实安装 Skill、插件或 CLI
- 执行脚本、修改本地文件或访问外部服务
- 验证真实输出质量、性能和兼容性

## 边界与风险判断卡

- **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0010` inferred 0.45
- **宿主 AI 插件或 Skill 规则冲突**：新规则可能改变用户现有宿主 AI 的工作方式。 处理方式：安装前先检查插件 manifest 和 Skill 文件，必要时隔离测试。 证据：`.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json` Claim：`clm_0011` inferred 0.45
- **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`CLAUDE.md`, `README.md` Claim：`clm_0012` supported 0.86, `clm_0013` supported 0.86, `clm_0014` contradicted 0.20
- **源文档冲突：skill_count**：项目文档中存在数量表述不一致，AI Context Pack 必须提示用户不要把单一数字当作已验证事实。 处理方式：在 Human Manual 和 AI Context Pack 中共同标记为待核实，而不是强行选择一个数字。 证据：`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
- **源文件冲突 skill_count**：发现多个值 `18, 19`，应在真实使用前核实。
- **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。
- **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。
- **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。

## 开工前工作上下文

### 加载顺序

- 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。
- 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。
- 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。
- 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。
- 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。

### 任务路由

- **AI Skill / Agent 指令资产库**：先基于 role_skill_index / evidence_index 帮用户挑选可用角色、Skill 或工作流。 边界：可做安装前 Prompt 体验。 证据：`.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` 等 Claim：`clm_0001` supported 0.86
- **多宿主安装与分发**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`.claude/plugins/minutes/.claude-plugin/plugin.json`, `.claude/plugins/minutes/plugin.json`, `.claude-plugin/marketplace.json`
- **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`CLAUDE.md`, `README.md` Claim：`clm_0003` supported 0.86

### 上下文规模

- 文件总数：850
- 重要文件覆盖：40/850
- 证据索引条目：180
- 角色 / Skill 条目：161

### 证据不足时的处理

- **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。
- **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。
- **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。
- **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。

## Prompt Recipes

### 适配判断

- 目标：判断这个项目是否适合用户当前任务。
- 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。

```text
请基于 minutes 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。
```

### 安装前体验

- 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。
- 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。

```text
请把 minutes 当作安装前体验资产，而不是已安装工具或真实运行环境。

请严格输出四段：
1. 先问我 3 个必要问题。
2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。
3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。
4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。

硬性边界：
- 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。
- 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。
- 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。
- 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。
- Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。
- 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。

```

### 角色 / Skill 选择

- 目标：从项目里的角色或 Skill 中挑选最匹配的资产。
- 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。

```text
请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。
```

### 风险预检

- 目标：安装或引入前识别环境、权限、规则冲突和质量风险。
- 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。

```text
请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。
```

### 宿主 AI 开工指令

- 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。
- 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。

```text
请基于 minutes 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。
```

## 角色 / Skill 索引

- 共索引 161 个角色 / Skill / 项目文档条目。

- **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… 激活提示：当用户任务与“minutes-brief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-cleanup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-copilot”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-debrief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-graph”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ideas”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ingest”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-lint”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-list”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-live-sidekick”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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"… 激活提示：当用户任务与“minutes-mirror”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-note”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-prep”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-recap”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-record”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-release-notes”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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". 激活提示：当用户任务与“minutes-search”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-seo-wave”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-setup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-tag”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-verify”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-video-review”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-weekly”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-brief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-cleanup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-copilot”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-debrief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-graph”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ideas”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ingest”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-lint”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-list”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-live-sidekick”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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"… 激活提示：当用户任务与“minutes-mirror”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-note”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-prep”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-recap”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-record”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-release-notes”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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". 激活提示：当用户任务与“minutes-search”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-seo-wave”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-setup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-tag”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-verify”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-video-review”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-weekly”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-brief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-cleanup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-copilot”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-debrief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-graph”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ideas”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-ingest”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-lint”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-list”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-live-sidekick”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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"… 激活提示：当用户任务与“minutes-mirror”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-note”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-prep”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-recap”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-record”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-release-notes”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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". 激活提示：当用户任务与“minutes-search”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-seo-wave”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-setup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-tag”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-verify”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-video-review”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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. 激活提示：当用户任务与“minutes-weekly”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.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… 激活提示：当用户任务与“minutes-brief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-cleanup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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… 激活提示：当用户任务与“minutes-copilot”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-debrief”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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… 激活提示：当用户任务与“minutes-graph”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-ideas”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-ingest”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-lint”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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. 激活提示：当用户任务与“minutes-list”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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… 激活提示：当用户任务与“minutes-live-sidekick”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`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"… 激活提示：当用户任务与“minutes-mirror”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`tooling/skills/goldens/claude/minutes-mirror/SKILL.md`
- 其余 81 个条目见 `AI_CONTEXT_PACK.json`。

## 证据索引

- 共索引 180 条证据。

- **Minutes Documentation Structure**（documentation）：Documentation is organized by purpose under docs/ . This index describes each folder and how to contribute new docs. 证据：`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. 证据：`.beads/README.md`
- **Minutes — Linux Codespace**（documentation）：A GitHub Codespace for testing Minutes on Linux without needing a Linux machine. 证据：`.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 证据：`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. 证据：`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. 证据：`.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 证据：`crates/cli/README.md`
- **Readme**（documentation）：Bundled file: silero vad v5.safetensors 证据：`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. 证据：`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 证据：`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. 证据：`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 . 证据：`examples/mem0/README.md`
- **Minutes Cowork Extension**（documentation）：This is the minimal Cowork-facing extension bundle for Minutes. 证据：`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. 证据：`sidecars/diarize-streaming/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. 证据：`AGENTS.md`
- **CLAUDE.md — Minutes**（documentation）：Your AI remembers every conversation you've had. 证据：`CLAUDE.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… 证据：`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. 证据：`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… 证据：`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… 证据：`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" } } 证据：`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" } } 证据：`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" } } 证据：`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… 证据：`tooling/skills/package.json`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.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. 证据：`.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. 证据：`.agents/skills/minutes/minutes-copilot/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-debrief/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-graph/SKILL.md`
- **/minutes-ideas — Recent Voice Memos & Ideas**（skill_instruction）：/minutes-ideas — Recent Voice Memos & Ideas 证据：`.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. 证据：`.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. 证据：`.agents/skills/minutes/minutes-lint/SKILL.md`
- **/minutes-list**（skill_instruction）：Show recent meetings and voice memos, sorted newest-first. 证据：`.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 . 证据：`.agents/skills/minutes/minutes-live-sidekick/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-mirror/SKILL.md`
- **/minutes-note**（skill_instruction）：Add a timestamped note during a recording, or annotate a past meeting. 证据：`.agents/skills/minutes/minutes-note/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-prep/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-recap/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.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. 证据：`.agents/skills/minutes/minutes-release-notes/SKILL.md`
- **/minutes-search**（skill_instruction）：Find information across all meeting transcripts and voice memos. 证据：`.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. 证据：`.agents/skills/minutes/minutes-seo-wave/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-setup/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-tag/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-verify/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.agents/skills/minutes/minutes-video-review/SKILL.md`
- **Skill Path**（skill_instruction）：Before running helper scripts or opening bundled references, set: 证据：`.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. 证据：`.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. 证据：`.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. 证据：`.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. 证据：`.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. 证据：`.claude/plugins/minutes/skills/minutes-graph/SKILL.md`
- **/minutes-ideas — Recent Voice Memos & Ideas**（skill_instruction）：/minutes-ideas — Recent Voice Memos & Ideas 证据：`.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. 证据：`.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. 证据：`.claude/plugins/minutes/skills/minutes-lint/SKILL.md`
- **/minutes-list**（skill_instruction）：Show recent meetings and voice memos, sorted newest-first. 证据：`.claude/plugins/minutes/skills/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 . 证据：`.claude/plugins/minutes/skills/minutes-live-sidekick/SKILL.md`
- **/minutes-mirror**（skill_instruction）：Self-coaching analysis based on your own meeting transcripts. Two modes: 证据：`.claude/plugins/minutes/skills/minutes-mirror/SKILL.md`
- **/minutes-note**（skill_instruction）：Add a timestamped note during a recording, or annotate a past meeting. 证据：`.claude/plugins/minutes/skills/minutes-note/SKILL.md`
- **/minutes-prep**（skill_instruction）：Interactive meeting preparation that searches your entire conversation history with someone, synthesizes a relationship brief, and produces talking points — before you walk into the room. 证据：`.claude/plugins/minutes/skills/minutes-prep/SKILL.md`
- 其余 120 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。

## 宿主 AI 必须遵守的规则

- **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`docs/README.md`, `.beads/README.md`, `.devcontainer/README.md`
- **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`docs/README.md`, `.beads/README.md`, `.devcontainer/README.md`

## 用户开工前应该回答的问题

- 你准备在哪个宿主 AI 或本地环境中使用它？
- 你只是想先体验工作流，还是准备真实安装？
- 你最在意的是安装成本、输出质量、还是和现有规则的冲突？

## 验收标准

- 所有能力声明都能回指到 evidence_refs 中的文件路径。
- AI_CONTEXT_PACK.md 没有把预览包装成真实运行。
- 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。

---

## Doramagic Context Augmentation

下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。

## Human Manual 骨架

使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。

宿主 AI 硬性规则：
- 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。
- 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。
- 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。

- **项目概览与多端入口**：importance `high`
  - source_paths: README.md, Cargo.toml, crates/cli/README.md, crates/cli/src/main.rs, crates/mcp/src/index.ts
- **音频采集、转写与说话人分离流水线**：importance `high`
  - source_paths: crates/core/src/capture.rs, crates/core/src/pipeline.rs, crates/core/src/transcribe.rs, crates/core/src/parakeet.rs, crates/core/src/parakeet_sidecar.rs
- **LLM 摘要、说话人身份与人际关系记忆**：importance `high`
  - source_paths: crates/core/src/summarize.rs, crates/core/src/ollama.rs, crates/core/src/apple_fm.rs, crates/core/src/copilot/mod.rs, crates/core/src/copilot/provider.rs
- **桌面应用、代理技能生态与平台故障模式**：importance `high`
  - source_paths: tauri/src-tauri/src/main.rs, tauri/src-tauri/src/commands.rs, tauri/src-tauri/src/call_capture.rs, tauri/src-tauri/src/call_detect.rs, tauri/src-tauri/src/pty.rs

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `3b13375e14897a575ddfcdd9cbcc6367f709b73d`
- 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`

宿主 AI 硬性规则：
- 没有 repo_clone_verified=true 时，不得声称已经读过源码。
- 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。
- 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。

## Doramagic Pitfall Constraints / 踩坑约束

这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。

### Constraint 1: 失败模式：security_permissions: CGEventTap leak: long-running app accumulates 512+ disabled taps, exhausting the system tap t...

- 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 | CGEventTap leak: long-running app accumulates 512+ disabled taps, exhausting the system tap table (breaks screenshots system-wide)
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 2: 失败模式：security_permissions: Input Monitoring probe: don't cache a transient first-probe timeout as a false "restart needed"

- 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 | Input Monitoring probe: don't cache a transient first-probe timeout as a false "restart needed"
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 3: 来源证据：Native in-app chat panel for Recall (replace embedded terminal for non-developer users)

- Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Native in-app chat panel for Recall (replace embedded terminal for non-developer users)
- Why it matters: 可能影响授权、密钥配置或安全边界。
- Evidence: community_evidence:github | https://github.com/silverstein/minutes/issues/362 | 来源讨论提到 windows 相关条件，需在安装/试用前复核。
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 4: 涉及密钥、隐私或敏感领域

- Trigger: 项目文本出现 secret/private key/privacy/trading/finance 等敏感关键词。
- Host AI rule: 补敏感数据流、密钥存储和权限边界审查。
- Why it matters: 金融、交易、隐私和密钥场景必须比普通工具更保守。
- Evidence: packet_text.keyword_scan | https://github.com/silverstein/minutes | matched secret / private key / privacy / trading / finance keyword
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 5: 失败模式：installation: Recall chat panel text is not selectable or copyable (inherits body `user-select: none`)

- 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 | Recall chat panel text is not selectable or copyable (inherits body `user-select: none`)
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 6: 失败模式：installation: system_audio_record in Minutes 0.22.0 is built for macOS 26 and crashes on macOS 15

- 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 | system_audio_record in Minutes 0.22.0 is built for macOS 26 and crashes on macOS 15
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 7: 失败模式：installation: v0.18.13

- 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 | v0.18.13
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 8: 失败模式：installation: v0.18.14

- 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 | v0.18.14
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 9: 失败模式：installation: v0.19.0: Sherpa SOTA engine + sensitivity enforcement

- 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 | v0.19.0: Sherpa SOTA engine + sensitivity enforcement
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 10: 失败模式：installation: v0.20.0: Dictation at your cursor, in-app Documents, honest degradation

- 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 | v0.20.0: Dictation at your cursor, in-app Documents, honest degradation
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。