[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APPR0QHWFCCYZ0N725EAA4":3,"skill-same:01M7APPR0QHWFCCYZ0N725EAA4":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7APPR0QHWFCCYZ0N725EAA4","writing-plans",null,"将 spec\u002F需求拆分为可执行的分步实施计划。 Use when: 有 spec 或需求，准备动手前需要拆分步骤。 Not for: trivial 改动（≤5 行）、已有详细计划。 Output: 分步实施计划（含 TDD 步骤和检查点）。","peps1666\u002FBuildCrew-AI","peps1666","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128503359?v=4","01M7APD9BQ6NTJ79J9FTB6YZGT","junhao zhou","01M7APD9CD06Q6CCJ22FYVG2AK",0,"MIT","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: writing-plans\ntips_exempt: internal plan-authoring command-provenance guard; no new end-user capability or discovery surface\ndescription: >\n  将 spec\u002F需求拆分为可执行的分步实施计划。\n  Use when: 有 spec 或需求，准备动手前需要拆分步骤。\n  Not for: trivial 改动（≤5 行）、已有详细计划。\n  Output: 分步实施计划（含 TDD 步骤和检查点）。\ntriggers:\n  - \"写计划\"\n  - \"implementation plan\"\n  - \"拆分步骤\"\n---\n\n# Writing Plans\n\n## Overview\n\n将 spec\u002F需求拆分为分步实施计划。写清楚每步改哪些文件、代码、测试、怎么验证。DRY. YAGNI. TDD. Frequent commits.\n\n**Announce at start:** \"I'm using the writing-plans skill to create the implementation plan.\"\n\n**Context:** Write the plan on main before opening a feature worktree. After the plan is committed, continue to `worktree` and then `tdd`.\n\n**开工前 Recall（F102 记忆系统）🔴**：写计划前先搜相关历史——`search_evidence(\"{feature}\")` 找相关 spec\u002FADR\u002F讨论，避免重复造轮子。\n\n**Save plans to:** `feature-specs\u002FYYYY-MM-DD-\u003Cfeature-name>.md`\n\n## Straight-Line Check (A→B, No Detour)\n\n**Before splitting steps, do this first:**\n\n1. **Pin the finish line**: one-sentence B definition + acceptance criteria + \"what we're NOT building\"\n2. **Define terminal schema**: interfaces \u002F types \u002F data structures of the final form — steps are built around this, not throwaway scaffolding\n3. **Every step passes three questions:**\n   - Will this step's output stay in the final system as-is (extend only, no rewrite)? → Yes = on the line; No = detour\n   - What can we demo\u002Ftest after this step? (no verifiable evidence = detour)\n   - If we remove this step, what specific cost does it add to reaching B? (can't articulate = detour)\n4. **Pure exploration = explicit Spike** (time-boxed + output is a decision\u002Fconclusion, not a deliverable)\n\n**Steps are internal implementation rhythm, NOT delivery batches.** The deliverable to the user is a complete feat matching the full spec — not a step's output. Do not expose intermediate steps as \"验收点\" to the user.\n\n## Stateful Object Gate（F229 PR-A1 20 轮教训）🔴\n\nPlan 涉及**有生命周期的状态对象**（thread 标记 \u002F carrier \u002F session \u002F 持久 config \u002F cache \u002F 索引 \u002F 注册表）时，「功能描述 + 幂等测试点」**不够**——那是把状态机的边留给 reviewer 逐轮补（PR #2202 实测：4 P1 + 16 P2 全是同一对象的状态转移边——crash window \u002F restore 复活 \u002F deleted-list 漏过滤 \u002F 并发 race \u002F self-heal，打了 20 轮才合入）。\n\n**Census 先行（F229 A3a 二次教训 2026-06-11）**：gate 第一步是**普查**——列出 plan 涉及的全部有生命周期对象再逐个三件套。特别注意\"复用现有 API\"场景下的**新消费侧状态**（轮询循环、发送闸门、到达判定器都是状态机）。漏报对象 = gate 形同虚设：F229 A3b 三对象三件套齐全，A3a 的 ConversationSendCycle 漏普查 → 云端同型 5 轮逐边补课。\n\n**三件套，缺一 = plan 不完整，不准发给实现猫：**\n\n1. **状态×事件转移表** — 含「唯一 lifecycle owner 是谁」+「旁路 API（generic restore \u002F delete \u002F list）禁止哪些操作」\n2. **不变量清单** — INV-N 编号，每条标注可测方式，test matrix 逐条对应\n3. **对抗场景** — crash window \u002F 并发双写 \u002F 恢复路径 \u002F 旁路 API 误用，每个场景一条测试\n\n**派生值规则**：能用纯投影（pure selector，零存储）表达的状态，禁止落独立存储——无同步即无失同步。\n\n- 范例：*(internal reference removed)*（球态纯投影 + INV-1~9 + test matrix 即写码顺序）\n- 反例：同 feature PR-A1 plan 段（一行\"幂等懒创建\"→ remote review 20 轮逐边补课）\n\n## Bite-Sized Task Granularity\n\n**Each step is one action (2-5 minutes):**\n- \"Write the failing test\" - step\n- \"Run it to make sure it fails\" - step\n- \"Implement the minimal code to make the test pass\" - step\n- \"Run the tests and make sure they pass\" - step\n- \"Commit\" - step\n\n## Plan Document Header\n\n**Every plan MUST start with this header:**\n\n```markdown\n# [Feature Name] Implementation Plan\n\n**Feature:** F0xx — `docs\u002Ffeatures\u002FF0xx-xxx.md`\n**Goal:** [One sentence — must match feat doc 的 goal]\n**Acceptance Criteria:** [从 feat doc 逐条抄过来，plan 必须覆盖全部 AC]\n**Architecture cell:** [ownership cell id from docs\u002Farchitecture\u002Fownership\u002FREADME.md]\n**Map delta:** none | update required | new cell required\n**Map delta why:** [一句话说明为什么不改 map \u002F 改哪个 cell \u002F 为什么需要新 cell]\n**Architecture:** [2-3 sentences about approach]\n**Tech Stack:** [Key technologies\u002Flibraries]\n**前端验证:** [涉及前端？标注 Yes — reviewer 必须用 Playwright\u002FChrome 实测]\n\n---\n```\n\n**F191 约束**：普通增量写 `Map delta: none`，不得重新画架构图。`update required` 或 `new cell required` 代表 Phase 0 还包含 ownership map 更新，必须在 implementation steps 里列出来。\n\n## Task Structure\n\n```markdown\n### Task N: [Component Name]\n\n**Files:**\n- Create: `exact\u002Fpath\u002Fto\u002Ffile.py`\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:123-145`\n- Test: `tests\u002Fexact\u002Fpath\u002Fto\u002Ftest.py`\n\n**Step 1: Write the failing test**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n**Step 2: Run test to verify it fails**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: FAIL with \"function not defined\"\n\n**Step 3: Write minimal implementation**\n\n```python\ndef function(input):\n    return expected\n```\n\n**Step 4: Run test to verify it passes**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: PASS\n\n**Step 5: Commit**\n\n```bash\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\ngit commit -m \"feat: add specific feature\"\n```\n```\n\n## Open Questions in Plans\n\n计划中的 Open Question 必须分类：\n- **技术 OQ**：实现过程中自行解决\n- **价值 OQ**：需要 operator 判断 → 附 Decision Packet（格式见 `refs\u002Fdecision-matrix.md`），包含 TL;DR + 回滚成本 + 真正需要判断的价值问题\n\n先判断可逆性：回滚成本低的不升级 operator，猫猫自决。\n\n## Formatting Command Contract\n\n计划写到格式化步骤时，先从当前仓库的 `package.json`、CI 或现有脚本确认可执行命令及适用范围；不要凭跨仓库习惯猜 formatter。计划中必须写出已确认的完整命令和预期结果，禁止只写“run formatting”或“格式化”。\n\n- 全仓自动修复：`pnpm check:fix`\n- 仅格式化本次文件：`pnpm biome format --write \u003Cfiles>`\n- 终态验证：`pnpm check`\n\n若仓库真相源提供不同命令，以真相源为准，并在计划中标明来源。\n\n## Remember\n- Exact file paths always\n- Complete code in plan (not \"add validation\")\n- Exact commands with expected output\n- DRY, YAGNI, TDD, frequent commits\n\n## 下一步\n\n计划写完并提交 → `worktree`（隔离开发环境）→ `tdd`（实现）。\n","# Writing Plans\n\n## Overview\n\n将 spec\u002F需求拆分为分步实施计划。写清楚每步改哪些文件、代码、测试、怎么验证。DRY. YAGNI. TDD. Frequent commits.\n\n**Announce at start:** \"I'm using the writing-plans skill to create the implementation plan.\"\n\n**Context:** Write the plan on main before opening a feature worktree. After the plan is committed, continue to `worktree` and then `tdd`.\n\n**开工前 Recall（F102 记忆系统）🔴**：写计划前先搜相关历史——`search_evidence(\"{feature}\")` 找相关 spec\u002FADR\u002F讨论，避免重复造轮子。\n\n**Save plans to:** `feature-specs\u002FYYYY-MM-DD-\u003Cfeature-name>.md`\n\n## Straight-Line Check (A→B, No Detour)\n\n**Before splitting steps, do this first:**\n\n1. **Pin the finish line**: one-sentence B definition + acceptance criteria + \"what we're NOT building\"\n2. **Define terminal schema**: interfaces \u002F types \u002F data structures of the final form — steps are built around this, not throwaway scaffolding\n3. **Every step passes three questions:**\n   - Will this step's output stay in the final system as-is (extend only, no rewrite)? → Yes = on the line; No = detour\n   - What can we demo\u002Ftest after this step? (no verifiable evidence = detour)\n   - If we remove this step, what specific cost does it add to reaching B? (can't articulate = detour)\n4. **Pure exploration = explicit Spike** (time-boxed + output is a decision\u002Fconclusion, not a deliverable)\n\n**Steps are internal implementation rhythm, NOT delivery batches.** The deliverable to the user is a complete feat matching the full spec — not a step's output. Do not expose intermediate steps as \"验收点\" to the user.\n\n## Stateful Object Gate（F229 PR-A1 20 轮教训）🔴\n\nPlan 涉及**有生命周期的状态对象**（thread 标记 \u002F carrier \u002F session \u002F 持久 config \u002F cache \u002F 索引 \u002F 注册表）时，「功能描述 + 幂等测试点」**不够**——那是把状态机的边留给 reviewer 逐轮补（PR #2202 实测：4 P1 + 16 P2 全是同一对象的状态转移边——crash window \u002F restore 复活 \u002F deleted-list 漏过滤 \u002F 并发 race \u002F self-heal，打了 20 轮才合入）。\n\n**Census 先行（F229 A3a 二次教训 2026-06-11）**：gate 第一步是**普查**——列出 plan 涉及的全部有生命周期对象再逐个三件套。特别注意\"复用现有 API\"场景下的**新消费侧状态**（轮询循环、发送闸门、到达判定器都是状态机）。漏报对象 = gate 形同虚设：F229 A3b 三对象三件套齐全，A3a 的 ConversationSendCycle 漏普查 → 云端同型 5 轮逐边补课。\n\n**三件套，缺一 = plan 不完整，不准发给实现猫：**\n\n1. **状态×事件转移表** — 含「唯一 lifecycle owner 是谁」+「旁路 API（generic restore \u002F delete \u002F list）禁止哪些操作」\n2. **不变量清单** — INV-N 编号，每条标注可测方式，test matrix 逐条对应\n3. **对抗场景** — crash window \u002F 并发双写 \u002F 恢复路径 \u002F 旁路 API 误用，每个场景一条测试\n\n**派生值规则**：能用纯投影（pure selector，零存储）表达的状态，禁止落独立存储——无同步即无失同步。\n\n- 范例：*(internal reference removed)*（球态纯投影 + INV-1~9 + test matrix 即写码顺序）\n- 反例：同 feature PR-A1 plan 段（一行\"幂等懒创建\"→ remote review 20 轮逐边补课）\n\n## Bite-Sized Task Granularity\n\n**Each step is one action (2-5 minutes):**\n- \"Write the failing test\" - step\n- \"Run it to make sure it fails\" - step\n- \"Implement the minimal code to make the test pass\" - step\n- \"Run the tests and make sure they pass\" - step\n- \"Commit\" - step\n\n## Plan Document Header\n\n**Every plan MUST start with this header:**\n\n```markdown\n# [Feature Name] Implementation Plan\n\n**Feature:** F0xx — `docs\u002Ffeatures\u002FF0xx-xxx.md`\n**Goal:** [One sentence — must match feat doc 的 goal]\n**Acceptance Criteria:** [从 feat doc 逐条抄过来，plan 必须覆盖全部 AC]\n**Architecture cell:** [ownership cell id from docs\u002Farchitecture\u002Fownership\u002FREADME.md]\n**Map delta:** none | update required | new cell required\n**Map delta why:** [一句话说明为什么不改 map \u002F 改哪个 cell \u002F 为什么需要新 cell]\n**Architecture:** [2-3 sentences about approach]\n**Tech Stack:** [Key technologies\u002Flibraries]\n**前端验证:** [涉及前端？标注 Yes — reviewer 必须用 Playwright\u002FChrome 实测]\n\n---\n```\n\n**F191 约束**：普通增量写 `Map delta: none`，不得重新画架构图。`update required` 或 `new cell required` 代表 Phase 0 还包含 ownership map 更新，必须在 implementation steps 里列出来。\n\n## Task Structure\n\n```markdown\n### Task N: [Component Name]\n\n**Files:**\n- Create: `exact\u002Fpath\u002Fto\u002Ffile.py`\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:123-145`\n- Test: `tests\u002Fexact\u002Fpath\u002Fto\u002Ftest.py`\n\n**Step 1: Write the failing test**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n**Step 2: Run test to verify it fails**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: FAIL with \"function not defined\"\n\n**Step 3: Write minimal implementation**\n\n```python\ndef function(input):\n    return expected\n```\n\n**Step 4: Run test to verify it passes**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: PASS\n\n**Step 5: Commit**\n\n```bash\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\ngit commit -m \"feat: add specific feature\"\n```\n```\n\n## Open Questions in Plans\n\n计划中的 Open Question 必须分类：\n- **技术 OQ**：实现过程中自行解决\n- **价值 OQ**：需要 operator 判断 → 附 Decision Packet（格式见 `refs\u002Fdecision-matrix.md`），包含 TL;DR + 回滚成本 + 真正需要判断的价值问题\n\n先判断可逆性：回滚成本低的不升级 operator，猫猫自决。\n\n## Formatting Command Contract\n\n计划写到格式化步骤时，先从当前仓库的 `package.json`、CI 或现有脚本确认可执行命令及适用范围；不要凭跨仓库习惯猜 formatter。计划中必须写出已确认的完整命令和预期结果，禁止只写“run formatting”或“格式化”。\n\n- 全仓自动修复：`pnpm check:fix`\n- 仅格式化本次文件：`pnpm biome format --write \u003Cfiles>`\n- 终态验证：`pnpm check`\n\n若仓库真相源提供不同命令，以真相源为准，并在计划中标明来源。\n\n## Remember\n- Exact file paths always\n- Complete code in plan (not \"add validation\")\n- Exact commands with expected output\n- DRY, YAGNI, TDD, frequent commits\n\n## 下一步\n\n计划写完并提交 → `worktree`（隔离开发环境）→ `tdd`（实现）。\n",{"name":5,"triggers":24,"description":28,"tips_exempt":29},[25,26,27],"写计划","implementation plan","拆分步骤","将 spec\u002F需求拆分为可执行的分步实施计划。 Use when: 有 spec 或需求，准备动手前需要拆分步骤。 Not for: trivial 改动（≤5 行）、已有详细计划。 Output: 分步实施计划（含 TDD 步骤和检查点）。\n","internal plan-authoring command-provenance guard; no new end-user capability or discovery surface","main","e43f83d5ceb309323cae7e0f31e5e48fd816a57d",".claude\u002Fskills\u002Fwriting-plans","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI","https:\u002F\u002Fgithub.com\u002Fpeps1666","https:\u002F\u002Fwww.cug.edu.cn\u002F","My name is Zhou Junhao, and I am from China University of Geosciences (Wuhan). My major is Resources and Environment, and my research direction is Remote Sensin","2026-08-16 00:25:38",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add peps1666\u002FBuildCrew-AI --skill writing-plans",{"tool":44,"command":45},"bunx","bunx skills add peps1666\u002FBuildCrew-AI --skill writing-plans",{"tool":47,"command":48},"pnpm","pnpm dlx skills add peps1666\u002FBuildCrew-AI --skill writing-plans","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-plans\u002FSKILL.md",true,[],[53,59,66,73,78,85],{"skillNo":54,"name":55,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7APYYSHV2SSSRV5Q15JWWPF","plugin-reconcile-skill","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fplugins\u002Ftest-reconcile-plugin-regr\u002Fskills\u002Fplugin-reconcile-skill\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7APYWAJ119TPF079F2AXWAS","weixin-mp","通过 Limb 体系操作微信公众号：发布文章、上传图片、管理草稿。 Use when: 需要发布内容到微信公众号、查看草稿、检查公众号连接状态。 Not for: 其他平台的发布、纯文本聊天、非公众号相关操作。 Output: 微信公众号操作结果（发布ID、草稿列表、图片URL等）。","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fpackages\u002Fapi\u002Fsrc\u002Fplugins\u002Fweixin-mp\u002Fskills\u002Fweixin-mp\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7APYNNEMBP2T62WT0JT7GNE","writing-skills","创建或修改 Clowder AI skill \u002F MCP tool description 的元技能（含质量标准、范本、发布）。 Use when: 写新 skill、修改现有 skill、写\u002F改 MCP tool description、验证 skill 质量； 或者功能实现中产出了 SKILL.md \u002F cat-cafe-skills\u002F 新目录 \u002F manifest.yaml skill 条目。 Not for: 使用 skill（直接触发对应 skill）。 Output: 新\u002F更新的 SKILL.md + manifest 条目 + symlinks。 GOTCHA: 软硬同重——skill\u002FMCP 质量 = 代码质量；不要写模型已知的通用教程，先过价值门禁。","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fcat-cafe-skills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":74,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7APYHJDXRH9EDP5D3JZHSVN","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fcat-cafe-skills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7APYD2SSZ6Y6CF5SD3YZ5C0","worktree","为代码、脚本、API 与第一方执行面创建隔离 Git worktree，并配置 Redis 6398；classifier 放行的 co-creation docs direct push 不进入本流程。","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fcat-cafe-skills\u002Fworktree\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7APY8R4E7RR2WZVPH9V8WWP","workspace-navigator","猫猫把“打开文档、代码或日志”等模糊意图解析成本地绝对路径或 worktree 相对路径，并返回 applied、queued、blocked 或 unconfirmed 的真实 Workspace 投递状态。","https:\u002F\u002Fgithub.com\u002Fpeps1666\u002FBuildCrew-AI\u002Fblob\u002Fmain\u002Fcat-cafe-skills\u002Fworkspace-navigator\u002FSKILL.md",[],[]]