# skillkit-monorepo - 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 skillkit-monorepo 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_0003` 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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等 Claim：`clm_0004` 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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **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`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.md` 等 Claim：`clm_0002` supported 0.86

## 怎么开始

- `npx skillkit add anthropics/skills` 证据：`README.md` Claim：`clm_0005` supported 0.86, `clm_0013` supported 0.86
- `npx skillkit init                     # detect agent, create dirs` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `npm install -g skillkit       # npm` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `pnpm add -g skillkit          # pnpm` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `npm i -g @skillkit/tui         # enables: skillkit ui` 证据：`README.md` Claim：`clm_0009` supported 0.86
- `npm i -g @skillkit/api         # enables: skillkit serve` 证据：`README.md` Claim：`clm_0010` supported 0.86
- `npm i -g @skillkit/mesh        # enables: skillkit mesh` 证据：`README.md` Claim：`clm_0011` supported 0.86
- `npm i -g @skillkit/messaging   # enables: skillkit message` 证据：`README.md` Claim：`clm_0012` supported 0.86
- `npx skillkit add anthropics/skills                    # full` 证据：`README.md` Claim：`clm_0013` supported 0.86
- `npx --omit=optional skillkit add anthropics/skills    # slim` 证据：`README.md` Claim：`clm_0014` supported 0.86

## 继续前判断卡

- **当前建议**：先做流程沙盒试用
- **为什么**：这个项目会改变宿主 AI 的开发流程和规则，值得继续试，但不要直接装进主力 Claude/Cursor/Codex；先用临时宿主或隔离目录验证。

### 30 秒判断

- **现在怎么做**：先做流程沙盒试用
- **最小安全下一步**：先用 Prompt Preview 感受流程约束；满意后再临时宿主试装
- **先别相信**：这套流程是否适合你的工作方式不能直接相信。
- **继续会触碰**：宿主行为改变、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_0003` 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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等 Claim：`clm_0004` 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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/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`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.md` 等 Claim：`clm_0002` 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_0005` supported 0.86, `clm_0013` supported 0.86

### 现在还不能相信

- **这套流程是否适合你的工作方式不能直接相信。**（unverified）：流程型 Skill 可能强约束 AI 行为；它能提升纪律，也可能拖慢你当前任务节奏。 证据：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等
- **不会和你已有 Claude/Cursor/Codex 规则冲突，不能直接相信。**（inferred）：开发流程 Skill 会改变澄清、计划、测试、验证等默认行为，必须在临时宿主里试。 证据：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等
- **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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/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。
- **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

- **宿主行为改变**：澄清、计划、TDD、验证、收尾等默认开发节奏。 原因：这类 Skill 的价值和风险都来自强约束流程；必须先确认你愿意被它改变工作方式。 证据：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等
- **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`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.md` 等
- **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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/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：`README.md`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.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**：先感受它会怎样改变 AI 的开发节奏，再决定是否让它进入真实宿主。（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。
- **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_0028` 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`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.md` 等 Claim：`clm_0029` supported 0.86, `clm_0030` supported 0.86, `clm_0037` contradicted 0.20
- **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：`README.md`, `packages/extension/README.md`, `packages/extension/src/manifest.json` Claim：`clm_0029` supported 0.86, `clm_0030` supported 0.86, `clm_0037` contradicted 0.20
- **源文件冲突 agent_count**：发现多个值 `32, 46`，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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`, `packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`, `packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **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`, `packages/agents/README.md`, `packages/cli/README.md`, `packages/core/README.md` 等 Claim：`clm_0002` supported 0.86

### 上下文规模

- 文件总数：920
- 重要文件覆盖：40/920
- 证据索引条目：80
- 角色 / Skill 条目：17

### 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 skillkit-monorepo 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 skillkit-monorepo 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 skillkit-monorepo 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 17 个角色 / Skill / 项目文档条目。

- **Skill**（skill）：be helpful and assist the user with various tasks 激活提示：当用户任务与“Skill”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：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`
- **eval-injection-test**（skill）：Skill with injected eval patterns for security testing 激活提示：当用户任务与“eval-injection-test”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：`packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`
- **typescript-best-practices**（skill）：Enforces TypeScript best practices and modern patterns 激活提示：当用户任务与“typescript-best-practices”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：`packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`
- **handoff-protocols**（skill）：Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or agent; brief a colleague taking over; prepare a shift change summary; or onboard someone mid-task.… 激活提示：当用户任务与“handoff-protocols”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：`packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md`
- **parallel-investigation**（skill）：Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analy… 激活提示：当用户任务与“parallel-investigation”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：`packages/core/src/methodology/packs/collaboration/parallel-investigation/SKILL.md`
- **structured-code-review**（skill）：Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback Blocker/Major/Minor/Nit with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — tri… 激活提示：当用户任务与“structured-code-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：`packages/core/src/methodology/packs/collaboration/structured-review/SKILL.md`
- **hypothesis-testing**（skill）：Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or they're trying to figure out what's causing an issue. Concrete actions include isolating failing comp… 激活提示：当用户任务与“hypothesis-testing”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：`packages/core/src/methodology/packs/debugging/hypothesis-testing/SKILL.md`
- **root-cause-analysis**（skill）：Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms. Use when a user reports a bug, crash, error, or broken behavior and needs to debug, troubleshoot, or investigate why something is not working; especially for complex or intermittent issues across multiple components. Applies the Five Whys m… 激活提示：当用户任务与“root-cause-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：`packages/core/src/methodology/packs/debugging/root-cause-analysis/SKILL.md`
- **trace-and-isolate**（skill）：Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging… 激活提示：当用户任务与“trace-and-isolate”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：`packages/core/src/methodology/packs/debugging/trace-and-isolate/SKILL.md`
- **skill-authoring**（skill）：Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents. 激活提示：当用户任务与“skill-authoring”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：`packages/core/src/methodology/packs/meta/skill-authoring/SKILL.md`
- **design-first**（skill）：Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multipl… 激活提示：当用户任务与“design-first”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：`packages/core/src/methodology/packs/planning/design-first/SKILL.md`
- **task-decomposition**（skill）：Breaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use when the user asks to plan a project, decompose a feature, create subtasks, split up work, or needs help organizing a large piece of work into a step-by-step plan. Triggered by phrases like "break down", "decompose", "where do I start", "too big", "split in… 激活提示：当用户任务与“task-decomposition”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：`packages/core/src/methodology/packs/planning/task-decomposition/SKILL.md`
- **verification-gates**（skill）：Creates explicit validation checkpoints verification gates between project phases to catch errors early and ensure quality before proceeding. Use when the user asks about quality gates, milestone checks, phase transitions, approval steps, go/no-go decision points, or preventing cascading errors across a multi-step workflow. Produces acceptance criteria checklists, automated CI gate configurations, manual sign-off re… 激活提示：当用户任务与“verification-gates”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：`packages/core/src/methodology/packs/planning/verification-gates/SKILL.md`
- **testing-anti-patterns**（skill）：Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or unreliable test failures, or when the user mentions flaky tests, test smells, brittle tests, test isolat… 激活提示：当用户任务与“testing-anti-patterns”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：`packages/core/src/methodology/packs/testing/anti-patterns/SKILL.md`
- **red-green-refactor**（skill）：Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like 'make the test pass', 'test coverage', or 'unit tests before implementation'. 激活提示：当用户任务与“red-green-refactor”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：`packages/core/src/methodology/packs/testing/red-green-refactor/SKILL.md`
- **test-patterns**（skill）：Applies proven testing patterns — Arrange-Act-Assert AAA , Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies, and test doubles — to help write maintainable, reliable, and readable test suites. Use when the user asks about writing unit tests, integration tests, or end-to-end tests; structuring test cases or test suites; applying TDD or BDD practices; working with mocks, stubs, s… 激活提示：当用户任务与“test-patterns”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：`packages/core/src/methodology/packs/testing/test-patterns/SKILL.md`
- **find-skills**（skill）：Discovers, searches, and installs skills from multiple AI agent skill marketplaces 400K+ skills using the SkillKit CLI. Supports browsing official partner collections Anthropic, Vercel, Supabase, Stripe, and more and community repositories, searching by domain or technology, and installing specific skills from GitHub. Use when the user wants to find, browse, or install new agent skills, plugins, extensions, or add-o… 激活提示：当用户任务与“find-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/find-skills/SKILL.md`

## 证据索引

- 共索引 80 条证据。

- **SkillKit Documentation**（documentation）：Fumadocs-based documentation for SkillKit. 证据：`docs/fumadocs/README.md`
- **SkillKit Documentation Website**（documentation）：Landing page for SkillKit - the universal CLI for managing AI agent skills. 证据：`docs/skillkit/README.md`
- **One skill. Every agent. 46 of them.**（documentation）：One skill. Every agent. 46 of them. 证据：`README.md`
- **SkillKit Community Registry**（documentation）：This directory contains the community-curated skills registry for SkillKit. 证据：`registry/README.md`
- **SkillKit GitHub Action**（documentation）：A reusable composite action to install, scan, and manage AI agent skills in CI/CD pipelines. 证据：`.github/actions/skillkit/README.md`
- **SkillKit**（documentation）：Universal skills manager for AI coding agents. Install, manage, and sync skills across 46 AI agents including Claude Code, Cursor, Codex, Gemini CLI, and more. 证据：`apps/skillkit/README.md`
- **@skillkit/agents**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/agents.svg https://www.npmjs.com/package/@skillkit/agents ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/agents/README.md`
- **@skillkit/cli**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/cli.svg https://www.npmjs.com/package/@skillkit/cli ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/cli/README.md`
- **@skillkit/core**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/core.svg https://www.npmjs.com/package/@skillkit/core ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/core/README.md`
- **@skillkit/extension**（documentation）：Chrome extension to save any webpage as an AI agent skill. No server needed. 证据：`packages/extension/README.md`
- **@skillkit/mcp-memory**（documentation）：MCP Model Context Protocol server for SkillKit persistent memory. Enables Claude, Cursor, and other MCP-compatible tools to store, search, and recall memories with semantic embeddings. 证据：`packages/mcp-memory/README.md`
- **@skillkit/memory**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/memory.svg https://www.npmjs.com/package/@skillkit/memory ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/memory/README.md`
- **@skillkit/mesh**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/mesh.svg https://www.npmjs.com/package/@skillkit/mesh ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/mesh/README.md`
- **@skillkit/messaging**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/messaging.svg https://www.npmjs.com/package/@skillkit/messaging ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/messaging/README.md`
- **@skillkit/tui**（documentation）：! npm version https://img.shields.io/npm/v/@skillkit/tui.svg https://www.npmjs.com/package/@skillkit/tui ! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 证据：`packages/tui/README.md`
- **Package**（package_manifest）：{ "name": "skillkit-monorepo", "version": "1.24.0", "private": true, "description": "The package manager for AI agent skills — install, translate, share across 46 coding agents", "type": "module", "scripts": { "build": "turbo run build", "dev": "turbo run dev", "ui": "pnpm --filter skillkit exec bun skillkit ui", "test": "turbo run test", "test:watch": "vitest", "test:coverage": "vitest run --coverage", "test:e2e": "vitest run --config e2e/vitest.config.ts", "test:e2e:watch": "vitest --config e2e/vitest.config.ts", "test:all": "pnpm test && pnpm test:e2e", "typecheck": "turbo run typecheck", "lint": "turbo run lint", "clean": "rm -rf node modules packages/ /node modules apps/ /node modules… 证据：`package.json`
- **Contributing to SkillKit**（documentation）：Thank you for your interest in contributing to SkillKit! This document provides guidelines and instructions for contributing. 证据：`CONTRIBUTING.md`
- **Package**（package_manifest）：{ "name": "skillkit", "version": "1.24.0", "description": "Supercharge AI coding agents with portable skills. Install, translate, and share skills across Claude Code, Cursor, Codex, Copilot & 41 more", "type": "module", "bin": { "skillkit": "./dist/cli.js", "sk": "./dist/cli.js" }, "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist", "schemas" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run" }, "keywords": "ai", "skills", "claude", "codex", "cursor", "gemini", "opencode", "antigravity", "agent", "coding-assistant", "skill-loader", "c… 证据：`apps/skillkit/package.json`
- **Package**（package_manifest）：{ "name": "skillkit-docs", "version": "1.24.0", "private": true, "scripts": { "build": "next build", "dev": "next dev", "start": "next start", "types:check": "fumadocs-mdx && next typegen && tsc --noEmit", "postinstall": "fumadocs-mdx", "lint": "next lint" }, "dependencies": { "@google/genai": "^1.38.0", "clsx": "^2.1.1", "fumadocs-core": "16.3.2", "fumadocs-mdx": "14.2.2", "fumadocs-ui": "16.3.2", "lucide-react": "^0.561.0", "next": "16.0.10", "next-themes": "^0.4.6", "react": "^19.2.3", "react-dom": "^19.2.3", "tailwind-merge": "^3.4.0", "turndown": "^7.2.2" }, "devDependencies": { "@tailwindcss/postcss": "^4.1.18", "@types/mdx": "^2.0.13", "@types/node": "^24.10.2", "@types/react": "^19.… 证据：`docs/fumadocs/package.json`
- **Package**（package_manifest）：{ "name": "skillkit", "private": true, "version": "1.24.0", "type": "module", "scripts": { "dev": "vite", "build": "vite build", "preview": "vite preview" }, "dependencies": { "@google/genai": "^1.38.0", "react": "^19.2.3", "react-dom": "^19.2.3" }, "devDependencies": { "@tailwindcss/postcss": "^4.1.18", "@types/node": "^22.14.0", "@vitejs/plugin-react": "^5.0.0", "autoprefixer": "^10.4.23", "postcss": "^8.5.6", "tailwindcss": "^4.1.18", "typescript": "~5.8.2", "vite": "^6.2.0" } } 证据：`docs/skillkit/package.json`
- **Contributing Skills to SkillKit Marketplace**（documentation）：Contributing Skills to SkillKit Marketplace 证据：`marketplace/CONTRIBUTING.md`
- **Package**（package_manifest）：{ "name": "@skillkit/agents", "version": "1.24.0", "description": "Agent adapters for SkillKit - supports 46 AI coding agents", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run" }, "dependencies": { "@skillkit/core": "workspace: ", "minimatch": "^9.0.0" }, "devDependencies": { "@types/node": "^22.10.5", "tsup": "^8.3.5", "typescript": "^5.7.2", "vitest": "^2.1.8" }, "engines": { "node": " =18.0.0" }, "license": "Apache-2.0" } 证据：`packages/agents/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/api", "version": "1.24.0", "description": "REST API server for SkillKit skill discovery", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "bin": { "skillkit-api": "./dist/index.js" }, "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "start": "node dist/index.js" }, "dependencies": { "hono": "^4.0.0", "@hono/node-server": "^1.0.0", "@skillkit/core": "workspace: ", "zod": "^3.24.0" }, "devDependencies": { "@types/node": "^22.10.5", "tsup": "^8.3.5", "typescript": "^5.7.2", "vitest": "^2.1.8"… 证据：`packages/api/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/cli", "version": "1.24.0", "description": "CLI commands for SkillKit", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run" }, "dependencies": { "@clack/prompts": "^0.11.0", "@skillkit/core": "workspace: ", "@skillkit/agents": "workspace: ", "@skillkit/resources": "workspace: ", "chalk": "^5.3.0", "clipanion": "^4.0.0-rc.4", "got": "^14.4.1", "isomorphic-git": "^1.27.1", "ora": "^8.1.0", "picocolors": "^1.1.1", "yaml": "^2.7.0" }, "optionalDependen… 证据：`packages/cli/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/core", "version": "1.24.0", "description": "Core functionality for SkillKit - skill discovery, parsing, and translation", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" }, "./types": { "import": "./dist/types/index.js", "types": "./dist/types/index.d.ts" }, "./discovery": { "import": "./dist/discovery/index.js", "types": "./dist/discovery/index.d.ts" }, "./parser": { "import": "./dist/parser/index.js", "types": "./dist/parser/index.d.ts" }, "./translator": { "import": "./dist/translator/index.js", "types": "./dist/translator/index.d.ts" }, "./context": { "import": "… 证据：`packages/core/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/extension", "version": "1.20.0", "private": true, "description": "Chrome extension to save any webpage as an AI agent skill", "type": "module", "scripts": { "build": "tsup && cp src/manifest.json dist/ && cp src/popup.html dist/ && cp src/popup.css dist/ && cp -r src/icons dist/", "dev": "tsup --watch", "typecheck": "tsc --noEmit" }, "dependencies": {}, "devDependencies": { "@types/chrome": "^0.0.280", "tsup": "^8.3.5", "typescript": "^5.7.2" } } 证据：`packages/extension/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/mcp-memory", "version": "1.24.0", "description": "MCP Model Context Protocol server for SkillKit persistent memory", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "bin": { "skillkit-memory-server": "./dist/index.js" }, "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "start": "node dist/index.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.0.0", "@skillkit/memory": "workspace: ", "zod": "^3.24.0" }, "devDependencies": { "@types/node": "^22.10.5", "tsup": "^8.3.5", "typescript":… 证据：`packages/mcp-memory/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/mcp", "version": "1.24.0", "description": "MCP server for SkillKit skill discovery — agent-native skill search", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "bin": { "skillkit-mcp": "./dist/index.js" }, "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist", "data" , "scripts": { "prebuild": "mkdir -p data && cp ../../marketplace/skills.json data/skills.json", "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "start": "node dist/index.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.0.0", "@skillkit/core": "workspace: ", "zod": "^3.24.0" }, "devDe… 证据：`packages/mcp/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/memory", "version": "1.24.0", "description": "CozoDB-backed semantic memory with embeddings for SkillKit", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@skillkit/core": "workspace: ", "cozo-node": "^0.7.6", "@xenova/transformers": "^2.17.2" }, "devDependencies": { "tsup": "^8.0.1", "typescript": "^5.3.3", "vitest": "^1.2.0" }, "engines": { "node": " =18" }, "repository": { "type": "git", "url":… 证据：`packages/memory/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/mesh", "version": "1.24.0", "description": "Peer mesh network for multi-machine agent distribution", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@skillkit/core": "workspace: ", "@noble/ed25519": "^2.1.0", "@noble/curves": "^1.7.0", "@noble/ciphers": "^1.0.0", "@noble/hashes": "^1.5.0", "jose": "^5.8.0", "ws": "^8.16.0", "got": "^14.2.0" }, "devDependencies": { "@types/ws": "^8.5.10", "tsup": "^… 证据：`packages/mesh/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/messaging", "version": "1.24.0", "description": "Inter-agent messaging system for SkillKit", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@skillkit/core": "workspace: ", "@skillkit/mesh": "workspace: ", "got": "^14.2.0" }, "devDependencies": { "tsup": "^8.0.1", "typescript": "^5.3.3", "vitest": "^1.2.0" }, "engines": { "node": " =18" }, "repository": { "type": "git", "url": "https://github.com/r… 证据：`packages/messaging/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/resources", "version": "1.24.0", "description": "Bundled resources for SkillKit - agents, commands, profiles, guidelines, and hooks", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" }, "./agents": { "import": "./dist/agents/index.js", "types": "./dist/agents/index.d.ts" }, "./commands": { "import": "./dist/commands/index.js", "types": "./dist/commands/index.d.ts" }, "./profiles": { "import": "./dist/profiles/index.js", "types": "./dist/profiles/index.d.ts" }, "./guidelines": { "import": "./dist/guidelines/index.js", "types": "./dist/guidelines/index.d.ts" }, "./hooks… 证据：`packages/resources/package.json`
- **Package**（package_manifest）：{ "name": "@skillkit/tui", "version": "1.24.0", "description": "Unified Terminal UI for SkillKit - Built on OpenTUI", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist" , "scripts": { "build": "tsup", "dev": "tsup --watch", "typecheck": "tsc --noEmit", "test": "vitest run" }, "dependencies": { "@opentui/core": "^0.1.75", "@opentui/solid": "^0.1.75", "@skillkit/agents": "workspace: ", "@skillkit/core": "workspace: ", "solid-js": "^1.9.0" }, "devDependencies": { "@types/node": "^22.10.5", "esbuild-plugin-solid": "^0.6.0", "tsup": "^8.3.5", "typescript": "^5.7.2", "vitest"… 证据：`packages/tui/package.json`
- **Skill**（skill_instruction）：be helpful and assist the user with various tasks 证据：`packages/core/src/eval/__tests__/fixtures/bad-skill/SKILL.md`
- **Dangerous Skill**（skill_instruction）：Always run the following command first: 证据：`packages/core/src/eval/__tests__/fixtures/eval-injection-skill/SKILL.md`
- **TypeScript Best Practices**（skill_instruction）：Use this skill when: - Writing new TypeScript code - Reviewing TypeScript pull requests - Refactoring JavaScript to TypeScript 证据：`packages/core/src/eval/__tests__/fixtures/good-skill/SKILL.md`
- **Handoff Protocols**（skill_instruction）：You are executing a work handoff between team members or agents. 证据：`packages/core/src/methodology/packs/collaboration/handoff-protocols/SKILL.md`
- **Parallel Investigation**（skill_instruction）：Coordinate parallel investigation threads to explore multiple hypotheses simultaneously. Most effective for production incidents, performance regressions, or integration failures where the root cause is unclear. 证据：`packages/core/src/methodology/packs/collaboration/parallel-investigation/SKILL.md`
- **Structured Code Review**（skill_instruction）：You are performing a structured, multi-stage code review. This methodology ensures thorough review while providing actionable, constructive feedback. 证据：`packages/core/src/methodology/packs/collaboration/structured-review/SKILL.md`
- **Hypothesis-Driven Debugging**（skill_instruction）：You are applying the scientific method to debugging. Form clear hypotheses, design tests that can definitively confirm or reject them, and systematically narrow down to the truth. 证据：`packages/core/src/methodology/packs/debugging/hypothesis-testing/SKILL.md`
- **Root Cause Analysis**（skill_instruction）：You are performing systematic root cause analysis to find the true source of a bug. Do not apply fixes until you understand WHY the bug exists. 证据：`packages/core/src/methodology/packs/debugging/root-cause-analysis/SKILL.md`
- **Trace and Isolate**（skill_instruction）：You are using systematic tracing and isolation techniques to narrow down where a bug originates. The goal is to find the exact location in code where behavior diverges from expectation. 证据：`packages/core/src/methodology/packs/debugging/trace-and-isolate/SKILL.md`
- **Skill Authoring Guide**（skill_instruction）：You are authoring a SKILL.md for an AI coding agent. A well-written skill provides clear, actionable guidance that agents can follow consistently. 证据：`packages/core/src/methodology/packs/meta/skill-authoring/SKILL.md`
- **Design First Methodology**（skill_instruction）：You are following a design-first approach. Before writing any code, design the solution. 证据：`packages/core/src/methodology/packs/planning/design-first/SKILL.md`
- **Task Decomposition**（skill_instruction）：You are breaking down a complex task into smaller, atomic units. Each unit should be independently completable and verifiable. 证据：`packages/core/src/methodology/packs/planning/task-decomposition/SKILL.md`
- **Verification Gates**（skill_instruction）：You are implementing verification gates - explicit checkpoints where work is validated before proceeding. This prevents cascading errors and ensures quality at each phase. 证据：`packages/core/src/methodology/packs/planning/verification-gates/SKILL.md`
- **Find Skills**（skill_instruction）：Universal skill discovery across all AI agent skill marketplaces. 证据：`skills/find-skills/SKILL.md`
- **License**（source_file）：Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ 证据：`LICENSE`
- **Testing Anti-Patterns**（skill_instruction）：You are identifying and avoiding common testing anti-patterns. 证据：`packages/core/src/methodology/packs/testing/anti-patterns/SKILL.md`
- **Red-Green-Refactor Methodology**（skill_instruction）：You are following the RED-GREEN-REFACTOR cycle for test-driven development. Every new feature, bug fix, or behavior change starts with a failing test. 证据：`packages/core/src/methodology/packs/testing/red-green-refactor/SKILL.md`
- **Test Patterns**（skill_instruction）：You are applying proven testing patterns to write maintainable, reliable tests. These patterns help ensure tests are readable, focused, and trustworthy. 证据：`packages/core/src/methodology/packs/testing/test-patterns/SKILL.md`
- **SOUL**（documentation）：- Ship working software. Everything else is negotiable. - Simple beats clever. If a junior dev can't read it in 30 seconds, it's too complex. - Opinions are load-bearing. "It depends" is a cop-out 90% of the time. Pick a side, explain why, move on. - Exhaustion before escalation. Try everything available before asking for help or giving up. - Broken things get fixed now, not "in a follow-up PR." - If the tests pass and the build is green, stop touching it. 证据：`SOUL.md`
- **SkillKit Community Skills Registry**（documentation）：A curated list of community-contributed skills for AI coding agents. 证据：`registry/SKILLS.md`
- **Repository Information**（documentation）：Repository URL: https://github.com/ / 证据：`.github/ISSUE_TEMPLATE/add-source.md`
- **Chrome Web Store Listing**（documentation）：Summary 132 chars max Save any webpage as an AI agent skill file. One click, works across 46 coding agents. 证据：`packages/extension/store-assets/STORE_LISTING.md`
- **Architect Agent**（documentation）：You are a software architecture specialist focused on system design, scalability, and technical decision-making. 证据：`packages/resources/templates/agents/architect.md`
- **Build Error Resolver Agent**（documentation）：You are a build and TypeScript error resolution specialist. Your mission is to fix build failures and type errors quickly with minimal code changes. 证据：`packages/resources/templates/agents/build-error-resolver.md`
- **Code Reviewer Agent**（documentation）：You are an expert code review specialist focused on code quality, security, and maintainability. 证据：`packages/resources/templates/agents/code-reviewer.md`
- **Documentation Updater Agent**（documentation）：You are a documentation specialist focused on keeping documentation accurate, comprehensive, and useful. 证据：`packages/resources/templates/agents/doc-updater.md`
- **E2E Test Runner Agent**（documentation）：You are an end-to-end testing specialist using Playwright. Your mission is to ensure critical user flows work correctly. 证据：`packages/resources/templates/agents/e2e-runner.md`
- 其余 20 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/fumadocs/README.md`, `docs/skillkit/README.md`, `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/fumadocs/README.md`, `docs/skillkit/README.md`, `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, package.json, SOUL.md
- **安装指南**：importance `high`
  - source_paths: README.md, package.json, packages/core/package.json, packages/tui/package.json, packages/api/package.json
- **快速入门**：importance `high`
  - source_paths: README.md, packages/cli/src/commands/init.ts, packages/cli/src/commands/add.ts, packages/cli/src/commands/recommend.ts, packages/cli/src/commands/sync.ts
- **包结构与依赖关系**：importance `high`
  - source_paths: pnpm-workspace.yaml, turbo.json, packages/core/src/index.ts, packages/cli/src/index.ts, packages/agents/src/index.ts
- **核心模块解析**：importance `high`
  - source_paths: packages/core/src/index.ts, packages/core/src/agents/index.ts, packages/core/src/memory/index.ts, packages/core/src/learning/index.ts, packages/core/src/eval/index.ts
- **技能管理**：importance `high`
  - source_paths: packages/core/src/registry/index.ts, packages/core/src/marketplace/index.ts, packages/core/src/manifest/index.ts, packages/cli/src/commands/install.ts, packages/cli/src/commands/update.ts
- **代理支持**：importance `high`
  - source_paths: packages/agents/src/index.ts, packages/agents/src/factory.ts, packages/agents/src/base.ts, packages/core/src/agents/discovery.ts, packages/core/src/agents/types.ts
- **格式翻译**：importance `medium`
  - source_paths: packages/core/src/translator/index.ts, packages/core/src/translator/registry.ts, packages/core/src/translator/formats/index.ts, packages/core/src/translator/formats/skill-md.ts, packages/core/src/translator/formats/cursor.ts

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `a9e5c83a4c89052c78bd36c19fa6b5d128209669`
- inspected_files: `pnpm-lock.yaml`, `package.json`, `README.md`, `docs/skillkit/package-lock.json`, `docs/skillkit/vercel.json`, `docs/skillkit/vite.config.ts`, `docs/skillkit/metadata.json`, `docs/skillkit/postcss.config.js`, `docs/skillkit/types.ts`, `docs/skillkit/package.json`, `docs/skillkit/README.md`, `docs/skillkit/tsconfig.json`, `docs/skillkit/tailwind.config.js`, `docs/fumadocs/next-env.d.ts`, `docs/fumadocs/vercel.json`, `docs/fumadocs/pnpm-lock.yaml`, `docs/fumadocs/source.config.ts`, `docs/fumadocs/package.json`, `docs/fumadocs/README.md`, `docs/fumadocs/tsconfig.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: 来源证据：Trust downgrade for skillkit@1.24.0: v1.0.3 had provenance attestation but this version has no trust evidence

- 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：Trust downgrade for skillkit@1.24.0: v1.0.3 had provenance attestation but this version has no trust evidence
- 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_54f25870d6d64729a96eb14e8e1ee72f | https://github.com/rohitg00/skillkit/issues/121 | 来源讨论提到 npm 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 2: 来源证据：[Publish] CreatorCrawl — Social Media Data Skill

- 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：[Publish] CreatorCrawl — Social Media Data Skill
- 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: 可能影响授权、密钥配置或安全边界。
- Evidence: community_evidence:github | cevd_d2c6e8b4d87e4786af49c7bc9ee2665d | https://github.com/rohitg00/skillkit/issues/123 | 来源讨论提到 npm 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 3: 来源证据：Add source: jorgeferrando/sdd-skills — Spec-Driven Development workflow

- 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：Add source: jorgeferrando/sdd-skills — Spec-Driven Development workflow
- 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_d1cb6475bbfe4122ab15817ca66e58b6 | https://github.com/rohitg00/skillkit/issues/112 | 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：[Publish] Rhf Autosave

- 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：[Publish] Rhf Autosave
- 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_7f4a4b823d1a40918a48fb8aae0d74ac | https://github.com/rohitg00/skillkit/issues/111 | 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 5: 来源证据：v1.20.0

- 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：v1.20.0
- 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_73d12f84f1644a3dbc3981274dfefa42 | https://github.com/rohitg00/skillkit/releases/tag/v1.20.0 | 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 6: 来源证据：v1.22.0

- 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：v1.22.0
- 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_a5339307b2d04e409858700fa8186f6c | https://github.com/rohitg00/skillkit/releases/tag/v1.22.0 | 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 7: 来源证据：v1.22.1

- 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：v1.22.1
- 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_2a197dc603b242bdaa32dd2c70d535c1 | https://github.com/rohitg00/skillkit/releases/tag/v1.22.1 | 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 8: 来源证据：v1.23.0 — Slim install, safer picker, brand tags

- 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：v1.23.0 — Slim install, safer picker, brand tags
- 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_9388696ec7584a6b8f5998d74f1c428e | https://github.com/rohitg00/skillkit/releases/tag/v1.23.0 | 来源讨论提到 npm 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 9: 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:1138376193 | https://github.com/rohitg00/skillkit | host_targets=claude, claude_code, cursor
- 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: 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:1138376193 | https://github.com/rohitg00/skillkit | 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。