# pm-skills-docs - 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 pm-skills-docs 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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`, `docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`, `docs/templates/skill-template/SKILL.md`, `skills/define-hypothesis/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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`, `docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`, `docs/templates/skill-template/SKILL.md`, `skills/define-hypothesis/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-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/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：`README.md` Claim：`clm_0003` supported 0.86

## 怎么开始

- `/plugin marketplace add product-on-purpose/pm-skills` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `/plugin install pm-skills@pm-skills-marketplace` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `npx skills add product-on-purpose/pm-skills` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `git clone https://github.com/product-on-purpose/pm-skills.git` 证据：`README.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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`, `docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`, `docs/templates/skill-template/SKILL.md`, `skills/define-hypothesis/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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`, `docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`, `docs/templates/skill-template/SKILL.md`, `skills/define-hypothesis/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：`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：`.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `AGENTS.md`, `CLAUDE.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-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/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：`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：`.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `AGENTS.md`, `CLAUDE.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-plugin/plugin.json`, `README.md`, `docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/marketplace.json`
- **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-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/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：`README.md` Claim：`clm_0012` supported 0.86, `clm_0019` 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：`docs/internal/release-plans/v2.16.0/testing-summary_v2.16.0.md`, `CHANGELOG.md`, `docs/changelog.md`, `docs/internal/release-plans/v2.15.0/plan_v2.15.0.md` 等 Claim：`clm_0013` inferred 0.45
- **源文档冲突：agent_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：`docs/internal/release-plans/v2.15.0/design-sprint-integration-plan.md`, `docs/internal/efforts/M-13-convention-alignment.md`, `docs/internal/audit/2026-05-03_tooling-process.md` Claim：`clm_0014` inferred 0.45
- **源文件冲突 skill_count**：发现多个值 `10, 11, 15, 16, 17, 18, 19, 20, 24, 25, 26, 27, 28, 29, 30, 31, 32, 35, 38, 39, 40, 45, 55, 59, 60, 63`，应在真实使用前核实。
- **源文件冲突 agent_count**：发现多个值 `18, 115, 135`，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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`, `docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`, `docs/templates/skill-template/SKILL.md`, `skills/define-hypothesis/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-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/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：`README.md` Claim：`clm_0003` supported 0.86

### 上下文规模

- 文件总数：1113
- 重要文件覆盖：40/1113
- 证据索引条目：101
- 角色 / Skill 条目：62

### 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 pm-skills-docs 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 pm-skills-docs 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 pm-skills-docs 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 62 个角色 / Skill / 项目文档条目。

- **utility-update-pm-skills**（skill）：Validates internet access, compares the locally installed pm-skills version against the latest public release, and updates local files with conflict-aware overwrite-or-skip options. Produces an update report listing changed files, skipped files, and new capabilities. Use when you want to bring a local pm-skills installation up to date. 激活提示：当用户任务与“utility-update-pm-skills”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：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`
- **utility-update-pm-skills**（skill）：- 激活提示：当用户任务与“utility-update-pm-skills”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：`docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`
- **<phase-or-classification-skill-name>**（skill）： 激活提示：当用户任务与“<phase-or-classification-skill-name>”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：`docs/templates/skill-template/SKILL.md`
- **define-hypothesis**（skill）：Defines a testable hypothesis with clear success metrics and validation approach. Use when forming assumptions to test, designing experiments, or aligning team on what success looks like. 激活提示：当用户任务与“define-hypothesis”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：`skills/define-hypothesis/SKILL.md`
- **define-jtbd-canvas**（skill）：Creates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job. Use when deeply understanding customer motivations, designing for jobs, or reframing product positioning. 激活提示：当用户任务与“define-jtbd-canvas”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：`skills/define-jtbd-canvas/SKILL.md`
- **define-opportunity-tree**（skill）：Creates an opportunity solution tree mapping desired outcomes to opportunities and potential solutions. Use for outcome-driven product discovery, prioritization, or communicating product strategy. 激活提示：当用户任务与“define-opportunity-tree”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：`skills/define-opportunity-tree/SKILL.md`
- **define-problem-statement**（skill）：Creates a clear problem framing document with user impact, business context, and success criteria. Use when starting a new initiative, realigning a drifted project, or communicating up to leadership. 激活提示：当用户任务与“define-problem-statement”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：`skills/define-problem-statement/SKILL.md`
- **deliver-acceptance-criteria**（skill）：Generates structured Given/When/Then acceptance criteria for a user story or feature slice. Use when translating product requirements into testable scenarios that cover the happy path, edge cases, error states, and non-functional expectations for engineering handoff and QA. 激活提示：当用户任务与“deliver-acceptance-criteria”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：`skills/deliver-acceptance-criteria/SKILL.md`
- **deliver-edge-cases**（skill）：Documents edge cases, error states, boundary conditions, and recovery paths for a feature. Use during specification to ensure comprehensive coverage, or during QA planning to identify test scenarios. 激活提示：当用户任务与“deliver-edge-cases”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：`skills/deliver-edge-cases/SKILL.md`
- **deliver-launch-checklist**（skill）：Creates a comprehensive pre-launch checklist covering engineering, design, marketing, support, legal, and operations readiness. Use before releasing features, products, or major updates to ensure nothing is missed. 激活提示：当用户任务与“deliver-launch-checklist”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：`skills/deliver-launch-checklist/SKILL.md`
- **deliver-prd**（skill）：Creates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be measured. Use when specifying features, epics, or product initiatives for engineering handoff. 激活提示：当用户任务与“deliver-prd”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：`skills/deliver-prd/SKILL.md`
- **deliver-release-notes**（skill）：Creates user-facing release notes that communicate new features, improvements, and fixes in clear, benefit-focused language. Use when shipping updates to communicate changes to users, customers, or stakeholders. 激活提示：当用户任务与“deliver-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：`skills/deliver-release-notes/SKILL.md`
- **deliver-user-stories**（skill）：Generates user stories with clear acceptance criteria from product requirements or feature descriptions. Use when breaking down features for sprint planning, writing tickets, or communicating requirements to engineering. 激活提示：当用户任务与“deliver-user-stories”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：`skills/deliver-user-stories/SKILL.md`
- **develop-adr**（skill）：Creates an Architecture Decision Record following the Nygard format to document significant technical decisions, their context, and consequences. Use when making technical choices that affect system architecture, technology selection, or development patterns. 激活提示：当用户任务与“develop-adr”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：`skills/develop-adr/SKILL.md`
- **develop-design-rationale**（skill）：Documents the reasoning behind design decisions including alternatives considered, trade-offs evaluated, and principles applied. Use when making significant UX decisions, aligning with stakeholders on design direction, or preserving design context for future reference. 激活提示：当用户任务与“develop-design-rationale”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：`skills/develop-design-rationale/SKILL.md`
- **develop-solution-brief**（skill）：Creates a concise one-page solution overview that communicates the proposed approach, key decisions, and trade-offs. Use when pitching solutions to stakeholders, aligning teams on approach, or documenting solution intent before detailed specification. 激活提示：当用户任务与“develop-solution-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：`skills/develop-solution-brief/SKILL.md`
- **develop-spike-summary**（skill）：Documents the results of a time-boxed technical or design exploration spike . Use after completing a spike to capture learnings, findings, and recommendations for the team. 激活提示：当用户任务与“develop-spike-summary”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：`skills/develop-spike-summary/SKILL.md`
- **discover-competitive-analysis**（skill）：Creates a structured competitive analysis comparing features, positioning, and strategy across competitors. Use when entering a market, planning differentiation, or understanding the competitive landscape. 激活提示：当用户任务与“discover-competitive-analysis”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：`skills/discover-competitive-analysis/SKILL.md`
- **discover-interview-synthesis**（skill）：Synthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user interviews, customer calls, or usability sessions to extract and communicate findings. 激活提示：当用户任务与“discover-interview-synthesis”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：`skills/discover-interview-synthesis/SKILL.md`
- **discover-stakeholder-summary**（skill）：Documents stakeholder needs, concerns, and influence for a project or initiative. Use when starting projects, managing complex stakeholder relationships, or ensuring alignment across organizational boundaries. 激活提示：当用户任务与“discover-stakeholder-summary”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：`skills/discover-stakeholder-summary/SKILL.md`
- **foundation-lean-canvas**（skill）：Produces a one-page lean canvas across nine interlocking blocks problem, customer, UVP, solution, channels, revenue, cost, metrics, unfair advantage with optional inline HTML and SVG visual rendering. Use when framing a new product thesis, stress-testing an existing strategy, comparing strategic options side-by-side, or aligning a team on business-model assumptions. Works as a strategic hub that cross-links to deepe… 激活提示：当用户任务与“foundation-lean-canvas”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：`skills/foundation-lean-canvas/SKILL.md`
- **foundation-meeting-agenda**（skill）：Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing . Emits a shareable summary suitable for Slack or email plus a full agenda with time-boxed topics, type tags, owners, attendee prep, a… 激活提示：当用户任务与“foundation-meeting-agenda”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：`skills/foundation-meeting-agenda/SKILL.md`
- **foundation-meeting-brief**（skill）：Produces a private strategic preparation document for the user before a meeting that matters. Captures stakes, stakeholder positions and reads, ranked desired outcomes, key messages, anticipated questions with prepared responses, risks and tensions, specific asks, and success signals. Distinct from meeting-agenda because this artifact is not shared with attendees; it is the user's personal tactical prep for meetings… 激活提示：当用户任务与“foundation-meeting-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：`skills/foundation-meeting-brief/SKILL.md`
- **foundation-meeting-recap**（skill）：Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic plus a consolidated action view at the end . Auto-populates topic skeleton from a sibling meeting-agenda when available and reconciles planned vs. actual topics. Accepts transcripts from Zoom, Meet, Otter, Fireflies, Krisp MCP, or manual notes; runs on variable-quality input without blocking. 激活提示：当用户任务与“foundation-meeting-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：`skills/foundation-meeting-recap/SKILL.md`
- **foundation-meeting-synthesize**（skill）：Cross-meeting archaeology skill. Consumes multiple meeting recaps or raw notes over a period and surfaces patterns invisible in any single meeting. Shows how decisions evolved, who has been saying what, where threads are stalling, and where contradictions have emerged. Produces a plain-text timeline, themes with confidence markers, stakeholder position tracking, consolidated decision list, contradiction flags, open… 激活提示：当用户任务与“foundation-meeting-synthesize”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：`skills/foundation-meeting-synthesize/SKILL.md`
- **foundation-okr-writer**（skill）：Drafts, reviews, rewrites, and coaches outcome-based OKR sets across team, department, product, or company scopes. Supports five entry modes Guided default, One-Shot via --oneshot, Sustained Coach, Audit Only, Rewrite . Diagnoses empowered-team context and adjusts framing; refuses to fabricate baselines or targets; refuses to use OKR scores for compensation; reframes feature-delivery KRs into outcome KRs. Use when p… 激活提示：当用户任务与“foundation-okr-writer”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：`skills/foundation-okr-writer/SKILL.md`
- **foundation-persona**（skill）：Generates an evidence-calibrated product or marketing persona using the canonical v2.5 output contract. Use when shaping artifact perspective, stress-testing decisions, or framing product and GTM strategy. 激活提示：当用户任务与“foundation-persona”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：`skills/foundation-persona/SKILL.md`
- **foundation-stakeholder-update**（skill）：Produces async communication to stakeholders, primarily non-attendees and secondarily some attendees who want a reference. Translates meeting outcomes into what-it-means language for readers, with channel variants slack, teams, email, notion, exec-memo and audience variants engineering, design, leadership, customer-facing, mixed . Surfaces a primary CTA up front, flags technical-to-business translations for user ver… 激活提示：当用户任务与“foundation-stakeholder-update”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：`skills/foundation-stakeholder-update/SKILL.md`
- **iterate-lessons-log**（skill）：Creates a structured lessons learned entry for organizational memory. Use after projects, incidents, or significant learnings to capture knowledge for future teams and initiatives. 激活提示：当用户任务与“iterate-lessons-log”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：`skills/iterate-lessons-log/SKILL.md`
- **iterate-pivot-decision**（skill）：Documents a strategic pivot or persevere decision with the evidence, analysis, and rationale. Use when evaluating whether to change direction on a product, feature, or strategy based on market feedback. 激活提示：当用户任务与“iterate-pivot-decision”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：`skills/iterate-pivot-decision/SKILL.md`
- **iterate-refinement-notes**（skill）：Documents backlog refinement session outcomes including stories refined, estimates, questions raised, and decisions made. Use during or after refinement to capture the results and share with absent team members. 激活提示：当用户任务与“iterate-refinement-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：`skills/iterate-refinement-notes/SKILL.md`
- **iterate-retrospective**（skill）：Facilitates and documents a team retrospective capturing what went well, what to improve, and action items. Use at the end of sprints, projects, or milestones to reflect and improve team practices. 激活提示：当用户任务与“iterate-retrospective”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：`skills/iterate-retrospective/SKILL.md`
- **measure-dashboard-requirements**（skill）：Specifies requirements for an analytics dashboard including metrics, visualizations, filters, and data sources. Use when requesting dashboards from data teams, defining KPI tracking, or documenting reporting needs. 激活提示：当用户任务与“measure-dashboard-requirements”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：`skills/measure-dashboard-requirements/SKILL.md`
- **measure-experiment-design**（skill）：Designs an A/B test or experiment with clear hypothesis, variants, success metrics, sample size, and duration. Use when planning experiments to validate product changes or test hypotheses. 激活提示：当用户任务与“measure-experiment-design”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：`skills/measure-experiment-design/SKILL.md`
- **measure-experiment-results**（skill）：Documents the results of a completed experiment or A/B test with statistical analysis, learnings, and recommendations. Use after experiments conclude to communicate findings, inform decisions, and build organizational knowledge. 激活提示：当用户任务与“measure-experiment-results”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：`skills/measure-experiment-results/SKILL.md`
- **measure-instrumentation-spec**（skill）：Specifies event tracking and analytics instrumentation requirements for a feature. Use when defining what data to collect, ensuring consistent tracking implementation, or documenting analytics requirements for engineering. 激活提示：当用户任务与“measure-instrumentation-spec”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：`skills/measure-instrumentation-spec/SKILL.md`
- **measure-okr-grader**（skill）：Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum committed aspirational learning operational health compliance or safety , committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committ… 激活提示：当用户任务与“measure-okr-grader”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：`skills/measure-okr-grader/SKILL.md`
- **tool-design-sprint-brief**（skill）：Pre-sprint brief that locks challenge, sprint questions, team and role assignments, customer recruiting plan, prototype medium, interview format, logistics, and success criteria before Monday of a Design Sprint. Use after the readiness verdict is Go and before Monday begins. Produces a two-page artifact the team and Decider sign off on as the contract for the next five days. 激活提示：当用户任务与“tool-design-sprint-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：`skills/tool-design-sprint-brief/SKILL.md`
- **tool-design-sprint-decide-and-storyboard**（skill）：Day 3 Wednesday move of a Design Sprint that runs the art museum layout, heat map, speed critique, straw poll, Decider supervote, rumble-vs-all-in-one decision, and the storyboard that drives Thursday's prototype build. The most decision-heavy day of the sprint. Use Wednesday morning and afternoon after Tuesday's sketches are collected and attribution-stripped. Produces the canonical 5-15 step storyboard that become… 激活提示：当用户任务与“tool-design-sprint-decide-and-storyboard”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：`skills/tool-design-sprint-decide-and-storyboard/SKILL.md`
- **tool-design-sprint-map-and-target**（skill）：Day 1 Monday move of a Design Sprint that produces the bundled Monday artifact containing long-term goal, sprint questions 3-7 testable risks , customer or system map 5-15 step flow , expert interview notes, HMW How Might We cluster board, and the Decider's chosen target moment. Use Day 1 morning and afternoon after the sprint brief is locked. Sets the design target for Tuesday's sketches and Wednesday's storyboard. 激活提示：当用户任务与“tool-design-sprint-map-and-target”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：`skills/tool-design-sprint-map-and-target/SKILL.md`
- **tool-design-sprint-prototype-plan**（skill）：Day 4 Thursday move of a Design Sprint that produces the planning artifact for the day. Output covers the prototype role plan Maker, Stitcher, Writer, Asset Collector, Interviewer , prototype brief what to build, fidelity bar, time allocation per role , canonical Five-Act Interview script Welcome, Context, Intro, Tasks, Debrief , trial-run checklist, and Friday participant confirmation tracker. The actual prototype… 激活提示：当用户任务与“tool-design-sprint-prototype-plan”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：`skills/tool-design-sprint-prototype-plan/SKILL.md`
- **tool-design-sprint-readiness**（skill）：Pre-sprint diagnostic that determines whether a team should run a Design Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, customer recruiting plan, and pre-sprint activities. Use when a team is considering starting a Design Sprint and wants a fast yes/no diagnosis before committing five days of team time an… 激活提示：当用户任务与“tool-design-sprint-readiness”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：`skills/tool-design-sprint-readiness/SKILL.md`
- **tool-design-sprint-sketch**（skill）：Day 2 Tuesday move of a Design Sprint that structures lightning demos and the four-step independent solution sketch protocol Notes, Ideas, Crazy 8s, Solution Sketch . Each team member produces one solution sketch individually; the skill orchestrates the day but does not author the sketches themselves. Use Tuesday morning after Monday's target moment is locked. Output is the lightning demo board, sketch assignments,… 激活提示：当用户任务与“tool-design-sprint-sketch”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：`skills/tool-design-sprint-sketch/SKILL.md`
- **tool-design-sprint-test-and-score**（skill）：Day 5 Friday sprint-closing move of a Design Sprint that produces the bundled Friday artifact covering per-customer interview observations, best quotes, scorecard grid sprint questions by customers , observed patterns, hot takes from each team member, and the Decider summary build, iterate, pivot, or stop, plus highest-confidence learning, most important revision, and next artifact . Use Friday after Thursday's prot… 激活提示：当用户任务与“tool-design-sprint-test-and-score”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：`skills/tool-design-sprint-test-and-score/SKILL.md`
- **tool-foundation-sprint-approach-options**（skill）：Day 2 morning move of a Foundation Sprint. Forces generation of 3 to 7 candidate approaches as one-page summaries before the team converges on a top bet. Use after Day 1 is signed and before Magic Lenses on Day 2 afternoon. Enforces a minimum of 3 approaches to prevent first-idea anchoring. Each approach summary names what it is, why it serves the differentiators, and includes a simple visual. 激活提示：当用户任务与“tool-foundation-sprint-approach-options”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：`skills/tool-foundation-sprint-approach-options/SKILL.md`
- **tool-foundation-sprint-basics**（skill）：Day 1 morning move of a Foundation Sprint. Forces explicit team choices on target customer, important problem, team advantage, and competitors and alternatives. Produces a single coherent strategic frame that becomes the input to Day 1 afternoon Differentiation. Use after the sprint brief is signed and Day 1 morning is scheduled. Bundled artifact, not four separate decisions. 激活提示：当用户任务与“tool-foundation-sprint-basics”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：`skills/tool-foundation-sprint-basics/SKILL.md`
- **tool-foundation-sprint-brief**（skill）：Pre-sprint brief that locks scope, the decision the sprint must unlock, team and role assignments, logistics, inputs to bring, and success criteria before Day 1 of a Foundation Sprint. Use after the readiness verdict is Go and before the sprint begins. Produces a one-page artifact the team and Decider sign off on as the contract for the next two days. 激活提示：当用户任务与“tool-foundation-sprint-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：`skills/tool-foundation-sprint-brief/SKILL.md`
- **tool-foundation-sprint-differentiation**（skill）：Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed differentiators, plotting alternatives on a 2x2 chart, writing decision principles, and producing a one-page Mini Manifesto. Use after Basics is signed; before Approach Options the next morning. 激活提示：当用户任务与“tool-foundation-sprint-differentiation”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：`skills/tool-foundation-sprint-differentiation/SKILL.md`
- **tool-foundation-sprint-founding-hypothesis**（skill）：Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence the Founding Hypothesis plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic Lenses is signed. Strict canonical template; paraphrase is not accepted in v0.1.0. The Founding Hypothesis is the spine artifact the sprint ex… 激活提示：当用户任务与“tool-foundation-sprint-founding-hypothesis”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：`skills/tool-foundation-sprint-founding-hypothesis/SKILL.md`
- **tool-foundation-sprint-magic-lenses**（skill）：Day 2 afternoon move of a Foundation Sprint. Evaluates the candidate approach set through multiple lenses 4 classic plus at least 1 custom to surface trade-offs, identify consistent winners and contradictions, and produce a top bet plus a backup plan. Use after Approach Options is signed. Lens scoring is a sense-making tool, not mathematical truth; arbitrary precision is a smell. 激活提示：当用户任务与“tool-foundation-sprint-magic-lenses”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：`skills/tool-foundation-sprint-magic-lenses/SKILL.md`
- **tool-foundation-sprint-readiness**（skill）：Pre-sprint diagnostic that determines whether a team should run a Foundation Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, and pre-sprint activities. Use when a team is considering starting a Foundation Sprint and wants a fast yes/no diagnosis before committing two days of facilitated work. 激活提示：当用户任务与“tool-foundation-sprint-readiness”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：`skills/tool-foundation-sprint-readiness/SKILL.md`
- **tool-note-and-vote**（skill）：Structured group-decision mechanic that captures silent ideation, voting summaries, and Decider sign-off in a single bundled artifact. Use when a small team needs to make a fast decision with diverse input, when groupthink is a risk, or when a workshop moment demands silent contribution before discussion. Applicable to Foundation Sprint, Design Sprint, and any participatory decision context. 激活提示：当用户任务与“tool-note-and-vote”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：`skills/tool-note-and-vote/SKILL.md`
- **utility-mermaid-diagrams**（skill）：Teaches PMs to create syntactically valid mermaid diagrams by selecting the right diagram type for their communication need, following syntax validity rules, and validating before shipping. Covers all 15 mermaid diagram types with PM-relevant examples and a dual-lens navigation system. 激活提示：当用户任务与“utility-mermaid-diagrams”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：`skills/utility-mermaid-diagrams/SKILL.md`
- **utility-pm-changelog-curator**（skill）：Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent. Dispatches natively on Claude Code with the pm-skills plugin invokes @agent-pm-changelog-curator ; on non-Claude clients Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI reads agents/pm-changelog-curator.md and executes the system prompt inline. Applies CLAUDE.md hygiene rules no internal-notes references, no em-dashes, no Claude attributio… 激活提示：当用户任务与“utility-pm-changelog-curator”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：`skills/utility-pm-changelog-curator/SKILL.md`
- **utility-pm-critic**（skill）：Run adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin invokes @agent-pm-critic ; on non-Claude clients Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI reads agents/pm-critic.md and executes the system prompt inline. Returns findings graded P0/P1/P2/P3 with concrete fix suggestions per finding, plus a layered Status Summary section and machi… 激活提示：当用户任务与“utility-pm-critic”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：`skills/utility-pm-critic/SKILL.md`
- **utility-pm-release-conductor**（skill）：Walk the guided release runbook 6 gates G0/G1/G2/G2.5/G3/G4 via the pm-release-conductor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin invokes @agent-pm-release-conductor with native chain composition to pm-skill-auditor at G0 and pm-changelog-curator at G2 ; on non-Claude clients Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI reads agents/pm-release-conductor.md and inlines auditor + cur… 激活提示：当用户任务与“utility-pm-release-conductor”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：`skills/utility-pm-release-conductor/SKILL.md`
- **utility-pm-skill-auditor**（skill）：Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin invokes @agent-pm-skill-auditor ; on non-Claude clients Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI reads agents/pm-skill-auditor.md and executes the system prompt inline. Returns a layered audit report full findings + Status Summary prose + Status YAML envelope per mas… 激活提示：当用户任务与“utility-pm-skill-auditor”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：`skills/utility-pm-skill-auditor/SKILL.md`
- **utility-pm-skill-builder**（skill）：Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies by type and phase, generates draft files, and writes to a staging area for review before promotion. 激活提示：当用户任务与“utility-pm-skill-builder”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：`skills/utility-pm-skill-builder/SKILL.md`
- **utility-pm-skill-iterate**（skill）：Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback. 激活提示：当用户任务与“utility-pm-skill-iterate”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：`skills/utility-pm-skill-iterate/SKILL.md`
- **utility-pm-skill-validate**（skill）：Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass/fail checks, severity-graded findings, and actionable recommendations. Use when checking whether a skill meets repo standards before shipping or after making changes. 激活提示：当用户任务与“utility-pm-skill-validate”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：`skills/utility-pm-skill-validate/SKILL.md`
- **utility-slideshow-creator**（skill）：Generates professional presentations from a JSON deck specification using 18 slide types with dark/light variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme and supports custom themes via utility-slideshow-themer. 激活提示：当用户任务与“utility-slideshow-creator”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：`skills/utility-slideshow-creator/SKILL.md`
- **utility-update-pm-skills**（skill）：Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date. 激活提示：当用户任务与“utility-update-pm-skills”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：`skills/utility-update-pm-skills/SKILL.md`

## 证据索引

- 共索引 101 条证据。

- **Concepts source folder**（documentation）：The Concepts section renders at https://product-on-purpose.github.io/pm-skills/concepts/. 证据：`docs/concepts/README.md`
- **Contributing source folder**（documentation）：The Contributing section renders at https://product-on-purpose.github.io/pm-skills/contributing/. 证据：`docs/contributing/README.md`
- **Getting Started source folder**（documentation）：The Getting Started section renders at https://product-on-purpose.github.io/pm-skills/getting-started/. 证据：`docs/getting-started/README.md`
- **Guides source folder**（documentation）：The Guides section renders at https://product-on-purpose.github.io/pm-skills/guides/. 证据：`docs/guides/README.md`
- **Internal Audits**（documentation）：This folder holds analytical audits of the pm-skills repository. Each audit is a static review producing findings, recommendations, and where applicable implementation specifications. Audits are durable knowledge artifacts; they outlive the cycles that consume them. 证据：`docs/internal/audit/README.md`
- **F-38 Release Skill Working Folder**（documentation）：This folder holds in-progress specs, plans, and working notes for the /pm-release utility skill. 证据：`docs/internal/efforts/F-38-release-skill/README.md`
- **F-39 find-skills Empirical Test Working Folder**（documentation）：F-39 find-skills Empirical Test Working Folder 证据：`docs/internal/efforts/F-39-find-skills-empirical-test/README.md`
- **F-40 Skill Description Discoverability Audit Working Folder**（documentation）：F-40 Skill Description Discoverability Audit Working Folder 证据：`docs/internal/efforts/F-40-skill-description-discoverability-audit/README.md`
- **F-41 Design Sprint Skills Working Folder**（documentation）：F-41 Design Sprint Skills Working Folder 证据：`docs/internal/efforts/F-41-design-sprint-skills/README.md`
- **F-42 Foundation Sprint Skills Working Folder**（documentation）：F-42 Foundation Sprint Skills Working Folder 证据：`docs/internal/efforts/F-42-foundation-sprint-skills/README.md`
- **Effort Briefs**（documentation）：Status: Active Owner: Maintainers Last updated: 2026-03-17 证据：`docs/internal/efforts/README.md`
- **Design Sprint Skill: Sample Output Artifacts**（documentation）：Design Sprint Skill: Sample Output Artifacts 证据：`docs/internal/efforts/design-sprint-skills/samples/README.md`
- **Sprint Skills Design Working Folder**（documentation）：Sprint Skills Design Working Folder 证据：`docs/internal/efforts/foundation-sprint-skills/README.md`
- **Foundation Sprint Skill: Sample Output Artifacts**（documentation）：Foundation Sprint Skill: Sample Output Artifacts 证据：`docs/internal/efforts/foundation-sprint-skills/samples/README.md`
- **2026-03 Baseline Cleanup**（documentation）：Status: Complete Scope: March 2026 baseline cleanup for repo continuity, governance, contributor docs, and release-supporting standards 证据：`docs/internal/milestones/2026-03-baseline-cleanup/README.md`
- **Internal Release Governance**（documentation）：Status: Active Owner: Maintainers Last updated: 2026-05-05 证据：`docs/internal/release-plans/README.md`
- **v2.2.0 Internal Release Governance**（documentation）：Status: Shipped Owner: Maintainers Last updated: 2026-03-22 证据：`docs/internal/release-plans/v2.2.0/README.md`
- **v2.3.0 Internal Release Governance**（documentation）：Status: Shipped Owner: Maintainers Last updated: 2026-03-22 证据：`docs/internal/release-plans/v2.3.0/README.md`
- **v2.4.0 Internal Release Record**（documentation）：Status: Historical record Release: v2.4.0 Last updated: 2026-03-16 证据：`docs/internal/release-plans/v2.4.0/README.md`
- **v2.5.0 Internal Release Record**（documentation）：Status: Released Release: v2.5.0 Last updated: 2026-03-16 证据：`docs/internal/release-plans/v2.5.0/README.md`
- **v2.6.1 Internal Release Governance**（documentation）：Status: Shipped Owner: Maintainers Last updated: 2026-03-19 证据：`docs/internal/release-plans/v2.6.1/README.md`
- **v2.7.0 Internal Release Governance**（documentation）：Status: Ready for tag . all gating criteria met Owner: Maintainers Last updated: 2026-03-22 证据：`docs/internal/release-plans/v2.7.0/README.md`
- **Product on Purpose**（documentation）：DRAFT skeleton. This is the proposed content for a future product-on-purpose/plugins repo, staged here inside pm-skills planning for review. When the real repo is created, this file becomes its root README.md and this banner is removed. 证据：`docs/internal/release-plans/v3.0.0/marketplace-repo-skeleton/README.md`
- **Reference source folder**（documentation）：The reference docs render at https://product-on-purpose.github.io/pm-skills/reference/. 证据：`docs/reference/README.md`
- **Releases source folder**（documentation）：The Releases section renders at https://product-on-purpose.github.io/pm-skills/releases/. 证据：`docs/releases/README.md`
- **Showcase source folder**（documentation）：The Showcase section renders at https://product-on-purpose.github.io/pm-skills/showcase/. 证据：`docs/showcase/README.md`
- **Skills source folder**（documentation）：The Skills section renders at https://product-on-purpose.github.io/pm-skills/skills/. 证据：`docs/skills/README.md`
- **Workflows Generated**（documentation）：Do not edit directly. Source of truth is workflows/ . 证据：`docs/workflows/README.md`
- **PM Skills Updater**（skill_instruction）：This skill updates a local pm-skills installation to the latest public release. It validates connectivity, compares versions, detects local modifications, gives the user control over conflict resolution, and produces a structured update report documenting every change. 证据：`docs/internal/efforts/F-24-update-pm-skills/_discovery/2026-04-09_claude-web-session/skills/utility-update-pm-skills/SKILL.md`
- **PM Skills Updater**（skill_instruction）：This skill updates a local pm-skills installation to the latest public release. It validates connectivity, compares versions, previews changes, and produces a structured report documenting what was updated and what new capabilities are available. 证据：`docs/internal/efforts/F-24-update-pm-skills/drafts/skills/utility-update-pm-skills/SKILL.md`
- **classification: For non-domain skills, use classification and omit phase**（skill_instruction）：When asked to , follow these steps: 证据：`docs/templates/skill-template/SKILL.md`
- **PM-Skills**（documentation）：Open source Product Management skills for AI agents 证据：`AGENTS.md`
- **Claude Code Instructions**（documentation）：NEVER use em-dash characters — , U+2014 in any output. This is a hard rule across all generated content: prose, code comments, file names, commit messages, plan docs, internal notes, memory files, or anything authored by Claude in this repo. 证据：`CLAUDE.md`
- **Quick Start**（documentation）：A curated library of 59 best-practice, plug-and-play product management skills covering the complete product lifecycle - plus templates, workflows, and 95+ real-world sample outputs that set the quality bar. 证据：`README.md`
- **Workflows**（documentation）：Source of truth for workflow definitions. 证据：`_workflows/README.md`
- **Awesome Lists Submission Issues**（documentation）：This directory contains draft issue content for submitting pm-skills to various awesome lists and curated repositories. 证据：`.github/issues-drafts/README.md`
- **GitHub Actions Scripts**（documentation）：This directory contains scripts used by GitHub Actions workflows. 证据：`.github/scripts/README.md`
- **Codex Workspace Policy**（documentation）：This folder is the Codex working area for pm-skills . 证据：`_agent-context/codex/README.md`
- **Sub-Agent Library Samples**（documentation）：Real example outputs from each pm-skills sub-agent demonstrating the canonical patterns each sub-agent produces. Three samples per sub-agent across the three narrative threads Brainshelf, Storevine, Workbench . 证据：`library/sub-agent-samples/README.md`
- **Package**（package_manifest）：{ "name": "pm-skills-docs", "version": "0.1.0", "private": true, "type": "module", "description": "Astro Starlight documentation site for pm-skills", "engines": { "node": " =22.12.0" }, "scripts": { "dev": "astro dev", "start": "astro dev", "build": "astro build && node scripts/post-build-strip-md-links.mjs", "preview": "astro preview", "astro": "astro" }, "dependencies": { "@astrojs/starlight": "~0.39.0", "astro": "^6.3.0", "astro-mermaid": "~2.0.1", "sharp": "^0.34.5" }, "overrides": { "mermaid": "^11.15.0", "devalue": "^5.8.1" } } 证据：`package.json`
- **Package**（package_manifest）：{ "name": "issue-creation-scripts", "version": "1.0.0", "description": "Scripts for automated issue creation from markdown drafts", "type": "module", "scripts": { "create-issues": "node create-issues.js" }, "dependencies": { "@octokit/rest": "^22.0.0", "gray-matter": "^4.0.3" } } 证据：`.github/scripts/package.json`
- **Contributing to PM-Skills**（documentation）：Thank you for your interest in contributing to PM-Skills! This document provides guidelines for contributing skills and other improvements. 证据：`CONTRIBUTING.md`
- **Hypothesis**（skill_instruction）：A hypothesis is a testable prediction about how a change will affect user behavior or business outcomes. It transforms assumptions into explicit statements that can be validated or invalidated through experimentation. Well-formed hypotheses prevent teams from building features based on untested beliefs and create shared understanding of what success looks like. 证据：`skills/define-hypothesis/SKILL.md`
- **Jobs to be Done Canvas**（skill_instruction）：A Jobs to be Done JTBD canvas captures the complete picture of why customers "hire" products to make progress in their lives. Based on Clayton Christensen's framework, JTBD goes beyond features and demographics to understand the underlying motivations.functional, emotional, and social.that drive customer behavior. 证据：`skills/define-jtbd-canvas/SKILL.md`
- **Opportunity Solution Tree**（skill_instruction）：An Opportunity Solution Tree OST is a visual framework for product discovery that connects business outcomes to customer opportunities and potential solutions. Developed by Teresa Torres, it prevents the common trap of jumping straight to solutions by ensuring every feature idea traces back to a customer need and measurable outcome. 证据：`skills/define-opportunity-tree/SKILL.md`
- **Problem Statement**（skill_instruction）：A problem statement is a concise document that frames the problem you're solving, articulates the impact on users and the business, and defines clear success criteria. It serves as the foundation for all subsequent product work by ensuring alignment on what problem to solve before jumping to how to solve it. 证据：`skills/define-problem-statement/SKILL.md`
- **Acceptance Criteria**（skill_instruction）：Acceptance criteria define the observable behavior that must be true for a story or feature to be considered done. This skill turns feature context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent. 证据：`skills/deliver-acceptance-criteria/SKILL.md`
- **Edge Cases**（skill_instruction）：An edge cases document systematically catalogs the unusual, boundary, and error scenarios for a feature. While happy-path flows are typically well-specified, edge cases often get discovered in production . causing bugs, poor user experience, and support burden. Documenting edge cases upfront ensures engineering handles them intentionally and QA knows what to test. 证据：`skills/deliver-edge-cases/SKILL.md`
- **Launch Checklist**（skill_instruction）：A launch checklist is a comprehensive verification document that ensures all functions are ready before releasing a feature or product. It coordinates across engineering, QA, design, marketing, support, legal, and operations to prevent launch-day surprises. Good launch checklists surface blockers early and create shared accountability for launch readiness. 证据：`skills/deliver-launch-checklist/SKILL.md`
- **Product Requirements Document PRD**（skill_instruction）：A Product Requirements Document is the primary specification artifact that communicates what to build and why. It bridges the gap between problem understanding and engineering implementation by providing clear requirements, success criteria, and scope boundaries. A good PRD enables engineering to build the right thing while maintaining flexibility on implementation details. 证据：`skills/deliver-prd/SKILL.md`
- **Release Notes**（skill_instruction）：Release notes communicate product changes to users in a way that highlights value and builds excitement. Unlike changelogs which document what changed technically , release notes translate changes into user benefits. Good release notes help users discover new capabilities, understand improvements, and trust that issues are being addressed. 证据：`skills/deliver-release-notes/SKILL.md`
- **User Stories**（skill_instruction）：User stories are concise descriptions of functionality from the user's perspective. They capture who needs something, what they need, and why . without prescribing how to build it. Good user stories enable teams to break large features into estimable, deliverable increments while maintaining focus on user value. 证据：`skills/deliver-user-stories/SKILL.md`
- **Architecture Decision Record ADR**（skill_instruction）：An Architecture Decision Record documents a significant technical decision along with its context and consequences. ADRs capture the "why" behind architectural choices so future team members understand the reasoning . especially important when they question why something was done a particular way. This skill follows Michael Nygard's lightweight ADR format. 证据：`skills/develop-adr/SKILL.md`
- **Design Rationale**（skill_instruction）：A design rationale document captures the "why" behind design decisions.the context, constraints, alternatives considered, and reasoning that led to a particular solution. While designs themselves show what was built, rationale documents preserve institutional knowledge about why it was built that way. 证据：`skills/develop-design-rationale/SKILL.md`
- **Solution Brief**（skill_instruction）：A solution brief is a concise, one-page document that communicates the proposed solution to a problem. It serves as the bridge between problem understanding and detailed specification, providing enough context for stakeholders to align on the approach without getting lost in implementation details. The one-page constraint forces clarity and prioritization. 证据：`skills/develop-solution-brief/SKILL.md`
- **Spike Summary**（skill_instruction）：A spike summary documents the results of a time-boxed exploration . a focused investigation to reduce uncertainty before committing to implementation. Spikes answer specific questions like "Can we integrate with this API?" or "Is this technology viable for our use case?" The summary captures findings so the team can make informed decisions without the spike participants needing to repeat explanations. 证据：`skills/develop-spike-summary/SKILL.md`
- **Competitive Analysis**（skill_instruction）：A competitive analysis provides structured insight into the competitive landscape, helping product teams understand where they stand relative to alternatives and identify opportunities for differentiation. Rather than exhaustively cataloging every competitor, an effective analysis focuses on actionable insights that inform product strategy. 证据：`skills/discover-competitive-analysis/SKILL.md`
- **Interview Synthesis**（skill_instruction）：An interview synthesis transforms raw user research data into structured insights that drive product decisions. Rather than simply listing what participants said, a good synthesis identifies patterns across conversations, connects observations to underlying user needs, and translates findings into actionable recommendations. 证据：`skills/discover-interview-synthesis/SKILL.md`
- **Stakeholder Summary**（skill_instruction）：A stakeholder summary documents the people and groups who have interest in or influence over a project, capturing their needs, concerns, and relationships. Effective stakeholder management often determines project success more than technical execution, making this document essential for navigating organizational complexity. 证据：`skills/discover-stakeholder-summary/SKILL.md`
- **Lean Canvas**（skill_instruction）：A lean canvas is a one-page business thesis that makes your assumptions about problem, customer, solution, and viability explicit and testable. Developed by Ash Maurya from Alex Osterwalder's Business Model Canvas, it is specifically adapted for startups and product teams operating under uncertainty. Nine interlocking blocks force you to articulate the whole picture at once so that changing one block's assumptions surfaces the ripple effect on the others. 证据：`skills/foundation-lean-canvas/SKILL.md`
- 其余 41 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/concepts/README.md`, `docs/contributing/README.md`, `docs/getting-started/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/concepts/README.md`, `docs/contributing/README.md`, `docs/getting-started/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。

- **项目介绍**：importance `high`
  - source_paths: README.md, LICENSE, docs/index.mdx
- **技能库概览**：importance `high`
  - source_paths: docs/skills/index.md, docs/skills/discover/index.md, docs/skills/define/index.md, docs/skills/develop/index.md, docs/skills/deliver/index.md
- **技能结构解析**：importance `high`
  - source_paths: docs/reference/pm-skill-anatomy.md, docs/reference/frontmatter-schema.yaml, docs/templates/skill-template/SKILL.md, docs/templates/skill-template/references/TEMPLATE.md, docs/templates/skill-template/references/EXAMPLE.md
- **技能分类体系**：importance `medium`
  - source_paths: docs/reference/categories.md, docs/reference/skill-families/index.md, docs/reference/skill-families/design-sprint-skills-contract.md, docs/reference/skill-families/foundation-sprint-skills-contract.md, docs/reference/skill-families/meeting-skills-contract.md
- **技能生命周期管理**：importance `high`
  - source_paths: docs/guides/pm-skill-lifecycle.md, docs/guides/creating-pm-skills.md, skills/utility-pm-skill-builder/SKILL.md, skills/utility-pm-skill-validate/SKILL.md, skills/utility-pm-skill-iterate/SKILL.md
- **子代理系统**：importance `high`
  - source_paths: docs/concepts/sub-agents.md, docs/reference/runtime-components.md, agents/pm-critic.md, agents/pm-skill-auditor.md, agents/pm-changelog-curator.md
- **工作流系统**：importance `high`
  - source_paths: docs/workflows/index.md, docs/guides/using-workflows.md, _workflows/feature-kickoff.md, _workflows/sprint-planning.md, _workflows/product-strategy.md
- **工具家族**：importance `medium`
  - source_paths: docs/concepts/foundation-sprint.md, docs/concepts/design-sprint.md, docs/guides/using-foundation-sprint.md, docs/guides/using-design-sprint.md, docs/reference/workshop-method-comparison.md

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `ae771c7aafef58d2a1197453c9d153ce88498822`
- inspected_files: `package.json`, `README.md`, `docs/changelog.md`, `docs/index.mdx`, `docs/tags.md`, `docs/skills/index.md`, `docs/skills/README.md`, `docs/reference/frontmatter-schema.yaml`, `docs/reference/mermaid-style-guide.md`, `docs/reference/index.md`, `docs/reference/runtime-components.md`, `docs/reference/project-structure.md`, `docs/reference/commands.md`, `docs/reference/sub-agent-compatibility.md`, `docs/reference/categories.md`, `docs/reference/README.md`, `docs/reference/pm-skill-anatomy.md`, `docs/reference/sprint-methodology-glossary.md`, `docs/reference/workshop-method-comparison.md`, `docs/reference/ecosystem.md`

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: 仓库名和安装名不一致

- Trigger: 仓库名 `pm-skills` 与安装入口 `skills` 不完全一致。
- Host AI rule: 在 npm/PyPI/GitHub 上确认包名映射和官方 README 说明。
- Why it matters: 用户照着仓库名搜索包或照着包名找仓库时容易走错入口。
- Evidence: identity.distribution | github_repo:1130952330 | https://github.com/product-on-purpose/pm-skills | repo=pm-skills; install=skills
- 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: 来源证据：[F-14] Workflow Builder (/workflow-builder)

- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[F-14] Workflow Builder (/workflow-builder)
- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | cevd_fd2240d9f58c49edbcc147428ff9b561 | https://github.com/product-on-purpose/pm-skills/issues/133 | 来源类型 github_issue 暴露的待验证使用条件。
- 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：[F-15] Ad-Hoc Skill Chaining (/chain)

- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[F-15] Ad-Hoc Skill Chaining (/chain)
- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | cevd_151a0a8448c84b81b626bf03b88d2714 | https://github.com/product-on-purpose/pm-skills/issues/134 | 来源类型 github_issue 暴露的待验证使用条件。
- 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: 来源证据：v2.11.1 - skills.sh CLI Compatibility Patch

- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：v2.11.1 - skills.sh CLI Compatibility Patch
- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。
- Why it matters: 可能影响升级、迁移或版本选择。
- Evidence: community_evidence:github | cevd_55aa5dc614634b48a39a0310a9b5fd45 | https://github.com/product-on-purpose/pm-skills/releases/tag/v2.11.1 | 来源类型 github_release 暴露的待验证使用条件。
- 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: 可能修改宿主 AI 配置

- Trigger: 项目面向 Claude/Cursor/Codex/Gemini/OpenCode 等宿主，或安装命令涉及用户配置目录。
- Host AI rule: 列出会写入的配置文件、目录和卸载/回滚步骤。
- Why it matters: 安装可能改变本机 AI 工具行为，用户需要知道写入位置和回滚方法。
- Evidence: capability.host_targets | github_repo:1130952330 | https://github.com/product-on-purpose/pm-skills | host_targets=claude, claude_code
- 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: 能力判断依赖假设

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: 将假设转成下游验证清单。
- Why it matters: 假设不成立时，用户拿不到承诺的能力。
- Evidence: capability.assumptions | github_repo:1130952330 | https://github.com/product-on-purpose/pm-skills | README/documentation is current enough for a first validation pass.
- 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: 来源证据：[M-21] Explore release-please Integration

- Trigger: GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[M-21] Explore release-please Integration
- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | cevd_acdd9d4cd91c449f964bf1924ec0b6e1 | https://github.com/product-on-purpose/pm-skills/issues/136 | 来源类型 github_issue 暴露的待验证使用条件。
- 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: 来源证据：v2.12.0 OKR Skills Launch

- Trigger: GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：v2.12.0 OKR Skills Launch
- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | cevd_f2a160e56ca04946816b63eab92a85cd | https://github.com/product-on-purpose/pm-skills/releases/tag/v2.12.0 | 来源类型 github_release 暴露的待验证使用条件。
- 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: 维护活跃度未知

- Trigger: 未记录 last_activity_observed。
- Host AI rule: 补 GitHub 最近 commit、release、issue/PR 响应信号。
- Why it matters: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
- Evidence: evidence.maintainer_signals | github_repo:1130952330 | https://github.com/product-on-purpose/pm-skills | last_activity_observed missing
- 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: 下游验证发现风险项

- Trigger: no_demo
- Host AI rule: 进入安全/权限治理复核队列。
- Why it matters: 下游已经要求复核，不能在页面中弱化。
- Evidence: downstream_validation.risk_items | github_repo:1130952330 | https://github.com/product-on-purpose/pm-skills | no_demo; severity=medium
- 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。