[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WY9SJS1B5EC2Q8WGQJAZMZ":3,"skill-same:01M6WY9SJS1B5EC2Q8WGQJAZMZ":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":13,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M6WY9SJS1B5EC2Q8WGQJAZMZ","github-private-repo-file-audit",null,"Audit a specific filename or config doc across all private GitHub repositories for an authenticated account, using a reliable clone-first workflow when GitHub API tree\u002Fcode search is incomplete.","cryptopafi\u002Fnexusos-skills","cryptopafi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F177822724?v=4","01M6RBPGFV10VSR55V7A819TGZ","01M6RBPGKCQAZH5QFGX99QW128",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fgithub\u002Fgithub-private-repo-file-audit\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"github private repo file audit","repo","file","audit","github","doc","when","clone","for","tree","across","gh","api","search","git","code","repos","config","auth","workflow","2026-11-10 10:12:30",false,"---\nname: github-private-repo-file-audit\ndescription: Audit a specific filename or config doc across all private GitHub repositories for an authenticated account, using a reliable clone-first workflow when GitHub API tree\u002Fcode search is incomplete.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [GitHub, audit, private-repos, gh, git, USER.md]\n    related_skills: [github-auth, github-repo-management]\n---\n\n# GitHub Private Repo File Audit\n\nUse this when the user asks questions like:\n- \"Check `USER.md` in all my private repos\"\n- \"Find every `AGENTS.md`\u002F`SOUL.md`\u002F`README` variant across my repos\"\n- \"Show me which repos contain profile files and summarize differences\"\n\nThis skill is optimized for **private repos** and avoids false negatives from GitHub API\u002Fsearch limitations.\n\n## Why this workflow exists\n\nIn practice, these methods can fail or mislead when auditing many private repos:\n\n1. `gh api repos\u002FOWNER\u002FREPO\u002Fgit\u002Ftrees\u002FBRANCH?recursive=1`\n   - Large trees may return JSON that gets truncated or malformed in tool output.\n   - You may see parse errors like `Invalid control character at char 20000`.\n\n2. `gh api search\u002Fcode`\n   - Can miss results for private repos, case variants (`USER.md` vs `user.md`), or return inconsistent coverage.\n   - Do **not** trust code search alone for exhaustive audits.\n\nBecause of that, the **reliable method is clone-first, then local filesystem scan**.\n\n## Recommended workflow\n\n### 1. Confirm GitHub auth\n\nUse the `github-auth` skill if needed.\n\nQuick check:\n\n```bash\ngh auth status\ngit --version\n```\n\n### 2. List private repos\n\n```bash\ngh repo list \u003Cowner> --visibility private --limit 200 --json nameWithOwner\n```\n\nIf you need default branches too:\n\n```bash\ngh repo list \u003Cowner> --visibility private --limit 200 --json nameWithOwner,defaultBranchRef,isArchived\n```\n\n### 3. Clone each repo shallowly to a temp workspace\n\nPrefer SSH if `gh auth status` says git protocol is SSH.\n\n```bash\nBASE=~\u002Ftmp\u002Fgithub-private-scan\nmkdir -p \"$BASE\"\n\ngit clone --depth 1 git@github.com:OWNER\u002FREPO.git \"$BASE\u002FREPO\"\n```\n\nNotes:\n- Use `--depth 1` for speed.\n- Delete stale partial clones before retrying.\n- Skip `.git\u002F` during scanning.\n\n### 4. Scan locally for the filename, case-insensitive\n\nPython pattern:\n\n```python\nimport os\n\nfor root, dirs, files in os.walk(repo_dir):\n    dirs[:] = [d for d in dirs if d != '.git']\n    for f in files:\n        if f.lower() == 'user.md':\n            path = os.path.join(root, f)\n```\n\nThis catches:\n- `USER.md`\n- `user.md`\n- mixed-case variants\n\n### 5. Read previews and summarize\n\nFor each match, extract:\n- repo name\n- relative path\n- line count\n- first 20–25 lines preview\n- inferred profile type (owner profile \u002F agent persona \u002F template \u002F function-specific profile)\n\n### 6. Report at two levels\n\nAlways provide:\n1. **inventory** — which repos contain the file and where\n2. **meaning** — what those files represent conceptually\n\nGood summary buckets:\n- owner\u002Fuser profile\n- agent persona profile\n- role-specific profile\n- generic template\n- backup\u002Farchive duplicate\n\n## Suggested execution pattern with Hermes tools\n\nBest reliable stack:\n- `skill_view(github-auth)` if needed\n- `terminal()` or `execute_code()` to list repos and clone\n- `read_file()` for important matched files you want to quote accurately\n- `todo()` if the audit spans many repos\n\n## Heuristics for summarizing profile files\n\nWhen auditing files like `USER.md`, classify them by these questions:\n\n- Is this about the human owner, or about an agent persona?\n- Is it generic, or scoped to a function (ops\u002Fmarketing\u002Flegal\u002Ffinance\u002Fetc.)?\n- Does it define communication style?\n- Does it define approval boundaries?\n- Does it define projects\u002Fbusiness priorities?\n- Does it define environment\u002Finfrastructure constraints?\n- Is it canonical, or obviously backup\u002Farchive\u002Fhistory?\n\n## Common pitfalls\n\n- Do not trust GitHub tree API alone for large repos.\n- Do not trust GitHub code search alone for exhaustive private-repo audits.\n- Do not forget case-insensitive filename matching.\n- Do not treat backup\u002Farchive copies as separate living profiles unless the user asks for historical comparison.\n- Do not stop at file inventory; the user usually wants a synthesis of identity\u002Fprofile differences.\n\n## Minimal reusable Python outline\n\n```python\nfrom hermes_tools import terminal\nimport json, os\n\nrepos = json.loads(terminal(\n    \"gh repo list OWNER --visibility private --limit 200 --json nameWithOwner\",\n    timeout=120,\n)[\"output\"])\n\nbase = os.path.expanduser('~\u002Ftmp\u002Fgithub-private-scan')\nos.makedirs(base, exist_ok=True)\nresults = []\n\nfor repo in repos:\n    full = repo['nameWithOwner']\n    name = full.split('\u002F')[-1]\n    target = os.path.join(base, name)\n    terminal(f\"rm -rf {target}\", timeout=120)\n    clone = terminal(f\"git clone --depth 1 git@github.com:{full}.git {target}\", timeout=300)\n    if clone['exit_code'] != 0:\n        results.append({'repo': full, 'error': clone['output'][:500]})\n        continue\n\n    matches = []\n    for root, dirs, files in os.walk(target):\n        dirs[:] = [d for d in dirs if d != '.git']\n        for f in files:\n            if f.lower() == 'user.md':\n                path = os.path.join(root, f)\n                rel = os.path.relpath(path, target)\n                with open(path, 'r', encoding='utf-8', errors='replace') as fh:\n                    lines = fh.read().splitlines()\n                matches.append({\n                    'path': rel,\n                    'line_count': len(lines),\n                    'preview': '\\n'.join(lines[:25]),\n                })\n\n    results.append({'repo': full, 'matches': matches})\n```\n\n## Output format recommendation\n\nUse this structure in the final answer:\n\n- total repos scanned\n- repos with matches\n- repos without matches\n- detailed list of matching repos + paths\n- conceptual synthesis\n- duplicates\u002Fbackups note\n- strongest conclusion \u002F recommended next step\n\n## Best-practice conclusion\n\nFor exhaustive audits of a file across private repos:\n- use `gh repo list` to enumerate,\n- shallow clone each repo,\n- scan locally,\n- then use file reads for the key matches.\n\nThis is more reliable than GitHub tree API or code search when completeness matters.\n","# GitHub Private Repo File Audit\n\nUse this when the user asks questions like:\n- \"Check `USER.md` in all my private repos\"\n- \"Find every `AGENTS.md`\u002F`SOUL.md`\u002F`README` variant across my repos\"\n- \"Show me which repos contain profile files and summarize differences\"\n\nThis skill is optimized for **private repos** and avoids false negatives from GitHub API\u002Fsearch limitations.\n\n## Why this workflow exists\n\nIn practice, these methods can fail or mislead when auditing many private repos:\n\n1. `gh api repos\u002FOWNER\u002FREPO\u002Fgit\u002Ftrees\u002FBRANCH?recursive=1`\n   - Large trees may return JSON that gets truncated or malformed in tool output.\n   - You may see parse errors like `Invalid control character at char 20000`.\n\n2. `gh api search\u002Fcode`\n   - Can miss results for private repos, case variants (`USER.md` vs `user.md`), or return inconsistent coverage.\n   - Do **not** trust code search alone for exhaustive audits.\n\nBecause of that, the **reliable method is clone-first, then local filesystem scan**.\n\n## Recommended workflow\n\n### 1. Confirm GitHub auth\n\nUse the `github-auth` skill if needed.\n\nQuick check:\n\n```bash\ngh auth status\ngit --version\n```\n\n### 2. List private repos\n\n```bash\ngh repo list \u003Cowner> --visibility private --limit 200 --json nameWithOwner\n```\n\nIf you need default branches too:\n\n```bash\ngh repo list \u003Cowner> --visibility private --limit 200 --json nameWithOwner,defaultBranchRef,isArchived\n```\n\n### 3. Clone each repo shallowly to a temp workspace\n\nPrefer SSH if `gh auth status` says git protocol is SSH.\n\n```bash\nBASE=~\u002Ftmp\u002Fgithub-private-scan\nmkdir -p \"$BASE\"\n\ngit clone --depth 1 git@github.com:OWNER\u002FREPO.git \"$BASE\u002FREPO\"\n```\n\nNotes:\n- Use `--depth 1` for speed.\n- Delete stale partial clones before retrying.\n- Skip `.git\u002F` during scanning.\n\n### 4. Scan locally for the filename, case-insensitive\n\nPython pattern:\n\n```python\nimport os\n\nfor root, dirs, files in os.walk(repo_dir):\n    dirs[:] = [d for d in dirs if d != '.git']\n    for f in files:\n        if f.lower() == 'user.md':\n            path = os.path.join(root, f)\n```\n\nThis catches:\n- `USER.md`\n- `user.md`\n- mixed-case variants\n\n### 5. Read previews and summarize\n\nFor each match, extract:\n- repo name\n- relative path\n- line count\n- first 20–25 lines preview\n- inferred profile type (owner profile \u002F agent persona \u002F template \u002F function-specific profile)\n\n### 6. Report at two levels\n\nAlways provide:\n1. **inventory** — which repos contain the file and where\n2. **meaning** — what those files represent conceptually\n\nGood summary buckets:\n- owner\u002Fuser profile\n- agent persona profile\n- role-specific profile\n- generic template\n- backup\u002Farchive duplicate\n\n## Suggested execution pattern with Hermes tools\n\nBest reliable stack:\n- `skill_view(github-auth)` if needed\n- `terminal()` or `execute_code()` to list repos and clone\n- `read_file()` for important matched files you want to quote accurately\n- `todo()` if the audit spans many repos\n\n## Heuristics for summarizing profile files\n\nWhen auditing files like `USER.md`, classify them by these questions:\n\n- Is this about the human owner, or about an agent persona?\n- Is it generic, or scoped to a function (ops\u002Fmarketing\u002Flegal\u002Ffinance\u002Fetc.)?\n- Does it define communication style?\n- Does it define approval boundaries?\n- Does it define projects\u002Fbusiness priorities?\n- Does it define environment\u002Finfrastructure constraints?\n- Is it canonical, or obviously backup\u002Farchive\u002Fhistory?\n\n## Common pitfalls\n\n- Do not trust GitHub tree API alone for large repos.\n- Do not trust GitHub code search alone for exhaustive private-repo audits.\n- Do not forget case-insensitive filename matching.\n- Do not treat backup\u002Farchive copies as separate living profiles unless the user asks for historical comparison.\n- Do not stop at file inventory; the user usually wants a synthesis of identity\u002Fprofile differences.\n\n## Minimal reusable Python outline\n\n```python\nfrom hermes_tools import terminal\nimport json, os\n\nrepos = json.loads(terminal(\n    \"gh repo list OWNER --visibility private --limit 200 --json nameWithOwner\",\n    timeout=120,\n)[\"output\"])\n\nbase = os.path.expanduser('~\u002Ftmp\u002Fgithub-private-scan')\nos.makedirs(base, exist_ok=True)\nresults = []\n\nfor repo in repos:\n    full = repo['nameWithOwner']\n    name = full.split('\u002F')[-1]\n    target = os.path.join(base, name)\n    terminal(f\"rm -rf {target}\", timeout=120)\n    clone = terminal(f\"git clone --depth 1 git@github.com:{full}.git {target}\", timeout=300)\n    if clone['exit_code'] != 0:\n        results.append({'repo': full, 'error': clone['output'][:500]})\n        continue\n\n    matches = []\n    for root, dirs, files in os.walk(target):\n        dirs[:] = [d for d in dirs if d != '.git']\n        for f in files:\n            if f.lower() == 'user.md':\n                path = os.path.join(root, f)\n                rel = os.path.relpath(path, target)\n                with open(path, 'r', encoding='utf-8', errors='replace') as fh:\n                    lines = fh.read().splitlines()\n                matches.append({\n                    'path': rel,\n                    'line_count': len(lines),\n                    'preview': '\\n'.join(lines[:25]),\n                })\n\n    results.append({'repo': full, 'matches': matches})\n```\n\n## Output format recommendation\n\nUse this structure in the final answer:\n\n- total repos scanned\n- repos with matches\n- repos without matches\n- detailed list of matching repos + paths\n- conceptual synthesis\n- duplicates\u002Fbackups note\n- strongest conclusion \u002F recommended next step\n\n## Best-practice conclusion\n\nFor exhaustive audits of a file across private repos:\n- use `gh repo list` to enumerate,\n- shallow clone each repo,\n- scan locally,\n- then use file reads for the key matches.\n\nThis is more reliable than GitHub tree API or code search when completeness matters.\n",{"name":5,"author":48,"license":14,"version":49,"metadata":50,"description":7},"Hermes Agent","1.0.0",{"hermes":51},{"tags":52,"related_skills":56},[53,26,54,34,37,55],"GitHub","private-repos","USER.md",[57,58],"github-auth","github-repo-management","main","5c34213899a7e6ba7597a65f60c542d4b7cb9521","github\u002Fgithub-private-repo-file-audit","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills","https:\u002F\u002Fgithub.com\u002Fcryptopafi","2026-08-24 14:21:06",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add cryptopafi\u002Fnexusos-skills --skill github-private-repo-file-audit",{"tool":71,"command":72},"bunx","bunx skills add cryptopafi\u002Fnexusos-skills --skill github-private-repo-file-audit",{"tool":74,"command":75},"pnpm","pnpm dlx skills add cryptopafi\u002Fnexusos-skills --skill github-private-repo-file-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fgithub\u002Fgithub-private-repo-file-audit\u002FSKILL.md",true,[],[80,117,145,161,181,202],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":100,"publishedAt":43},"01M6WYTX72QQN7J0ZKSES38NEN","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[86,89,92,97],{"categoryNo":87,"categoryName":88,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":90,"categoryName":91,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":98,"categoryName":99,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000036","内容创作者",[101,102,103,104,105,42,106,107,108,38,109,110,111,112,113,114,115,31,116,29],"writing","writing plans","plans","design","review","documentation","tasks","development","planning","code-review","subagent","superpowers","paths","test-driven-development","you","test-driven",{"skillNo":118,"name":114,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":130,"publishedAt":43},"01M6WYTN5C9XC8EYWGPXPWKGGX","Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[122,125,128,129],{"categoryNo":123,"categoryName":124,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":126,"categoryName":127,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":90,"categoryName":91,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":98,"categoryName":99,"taxonomyType":95,"taxonomyTypeDesc":96},[131,132,108,133,134,101,135,38,136,111,112,137,138,139,140,141,142,143,144,29],"test","test driven development","driven","testing","debugging","refactor","red-green-refactor","cycle","green","systematic","bugfix","implementing","systematic-debugging","test-first",{"skillNo":146,"name":143,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":43},"01M6WYTDP76WP7Y5QVSWT2303F","Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[150],{"categoryNo":126,"categoryName":127,"taxonomyType":20,"taxonomyTypeDesc":21},[152,135,140,101,131,108,111,153,112,154,155,156,103,157,114,158,116,159,160,29],"systematic debugging","use","bug","root-cause","problem-solving","problem","fixes","phase","root cause",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":174,"publishedAt":43},"01M6WYT5P36B4M01BASQB9F0AY","subagent-driven-development","Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[167,168,169,170,171],{"categoryNo":90,"categoryName":91,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},{"categoryNo":98,"categoryName":99,"taxonomyType":95,"taxonomyTypeDesc":96},{"categoryNo":172,"categoryName":173,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000037","律师与法务",[108,175,111,133,101,105,42,176,107,38,177,110,178,179,112,103,180,114,116,29],"subagent driven development","code quality","delegation","parallel","delegate","fresh",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":189,"publishedAt":43},"01M6WYSXD1J366HVZRMRE7ENDA","requesting-code-review","Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[187,188],{"categoryNo":123,"categoryName":124,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},[190,105,38,191,101,192,110,193,194,195,196,111,197,198,199,112,114,200,201,116],"code review","requesting code review","commit","verification","security scan","pipeline","loop","reviewer","fix","auto","static","auto-fix",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":43},"01M6WYSNEBG74A5FCMCDGQ7QP4","plan","Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes\u002Fplans\u002F` directory, and do not execute the work.","https:\u002F\u002Fgithub.com\u002Fcryptopafi\u002Fnexusos-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[204,101,209,42,108,109,210,111,211,212,213,214,215,216,103,217,218,219,31,220],"directory","markdown","workspace","work","write","implementation","do","active","plan mode","inspect","mode","plan-mode"]