[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R32RBQXAG40PM35VSA2Y8T":3,"skill-same:01M6R32RBQXAG40PM35VSA2Y8T":77},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":13,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6R32RBQXAG40PM35VSA2Y8T","skillify",null,"The meta skill. Turn any raw feature or script into a properly-skilled,\ntested, resolvable, evaled unit of agent-visible capability. Use when\nthe user says \"skillify this\", \"is this a skill?\", \"make this proper\",\nor after a new feature is built without the full skill infrastructure.\n\nPaired with `gbrain check-resolvable`, skillify gives a user-controllable\nequivalent of Hermes' auto-skill-creation: you build, skillify checks the\nchecklist, check-resolvable verifies nothing is orphaned. The human keeps\njudgment; the tooling keeps the checklist honest.","sixtycat2000-ctrl\u002Fgbrain-qmd","sixtycat2000-ctrl","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263121306?v=4","01M6R2SPVP79P6Y6CC3HW4Y6GD","01M6R2SQ2MJXN4VVXWT7NQW9DD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fskillify\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"when","infrastructure","capability","for","you","make","unit","add","false","feature","creation","full","judgment","human","evals","auto","list","Meta","search","2026-11-10 10:12:30",false,"---\nname: skillify\nversion: 1.0.0\ndescription: |\n  The meta skill. Turn any raw feature or script into a properly-skilled,\n  tested, resolvable, evaled unit of agent-visible capability. Use when\n  the user says \"skillify this\", \"is this a skill?\", \"make this proper\",\n  or after a new feature is built without the full skill infrastructure.\n\n  Paired with `gbrain check-resolvable`, skillify gives a user-controllable\n  equivalent of Hermes' auto-skill-creation: you build, skillify checks the\n  checklist, check-resolvable verifies nothing is orphaned. The human keeps\n  judgment; the tooling keeps the checklist honest.\ntriggers:\n  - \"skillify this\"\n  - \"skillify\"\n  - \"is this a skill?\"\n  - \"make this proper\"\n  - \"add tests and evals for this\"\n  - \"check skill completeness\"\ntools:\n  - search\n  - list_pages\nmutating: false\n---\n\n# Skillify — The Meta Skill\n\n## Contract\n\nA feature is \"properly skilled\" when all ten checklist items are present:\n\n1. `SKILL.md` — skill file with YAML frontmatter, triggers, contract, phases.\n2. Code — deterministic script if applicable.\n3. Unit tests — cover every branch of deterministic logic.\n4. Integration tests — exercise live endpoints, not just in-memory shape.\n5. LLM evals — quality\u002Fcorrectness cases if the feature includes any LLM call.\n6. Resolver trigger — `skills\u002FRESOLVER.md` entry with the trigger patterns\n   the user actually types.\n7. Resolver trigger eval — test that feeds trigger phrases to the resolver\n   and asserts they route to this skill, not the old pre-skillify path.\n8. Check-resolvable — `gbrain check-resolvable` passes (skill is reachable,\n   MECE against its siblings, no DRY violations).\n9. E2E test — exercises the full pipeline from user turn to side effect.\n10. Brain filing — if the feature writes brain pages, `brain\u002FRESOLVER.md`\n    has an entry for the directory so the pages aren't orphaned.\n\n## Trigger\n\n- \"skillify this\" \u002F \"skillify\" \u002F \"is this a skill?\" \u002F \"make this proper\"\n- \"add tests and evals for this\"\n- After building any new feature that touches user-facing behavior\n- When you grep the repo and notice a script with no SKILL.md next to it\n\n## Phases\n\n### Phase 1: Audit what exists\n\nFor the feature being skillified, answer:\n\n- **Feature name**: what does it do in one line?\n- **Code path**: where does the implementation live (file path)?\n- **Checklist status**: run `gbrain skillify check \u003Cpath>` (preferred)\n  or the legacy `scripts\u002Fskillify-check.ts \u003Cpath>` shim. Both produce\n  the same 10-item scorecard. Note which items are missing.\n\n### Phase 2: Create missing pieces in order\n\n**Fast path — brand-new skill:** run `gbrain skillify scaffold \u003Cname>\n--description \"...\" [--triggers \"p1,p2,p3\"] [--writes-pages --writes-to\n\"people\u002F,companies\u002F\"]`. This creates all 5 stub files atomically and\nappends an idempotent resolver row. Every scaffolded file carries the\n`SKILLIFY_STUB` sentinel; `gbrain check-resolvable --strict` will fail\nCI until you replace the stubs with real content.\n\n**Manual path — extending an existing skill:** work the list top-down.\nEach earlier item constrains what later items look like (the SKILL.md\ncontract determines what tests assert; tests determine what evals gate;\nthe resolver entry determines what trigger-eval checks).\n\n1. Write `SKILL.md` first. Frontmatter must include `name`, `version`,\n   `description`, `triggers[]`, `tools[]`, `mutating`. Body has at minimum\n   Contract, Phases, and Output Format sections.\n2. Extract deterministic code into a script if applicable (scripts\u002F*.ts\n   for gbrain; host projects may use .mjs \u002F .py \u002F whatever their runtime\n   uses).\n3. Write unit tests for every branch of the script. Mock external calls\n   (LLM, DB, network) so tests run fast and deterministic.\n4. Add integration tests that hit real endpoints. These catch bugs the\n   unit tests' mocks hide (see the `files-test-reimplements-production`\n   learning: reimplementation in tests lets production vulnerabilities\n   slip through).\n5. Add LLM evals if the feature includes any LLM call. Even a three-case\n   eval (happy \u002F edge \u002F adversarial) is cheap insurance against prompt\n   regressions.\n6. Add the resolver trigger to `skills\u002FRESOLVER.md`. Use the trigger\n   patterns the user ACTUALLY types, not what you think they should type.\n7. Add a resolver trigger eval that feeds those patterns in and asserts\n   they route to the new skill.\n8. Run `gbrain check-resolvable` (auto-detects skill trees) or\n   `gbrain check-resolvable --skills-dir \u003Cpath>` for custom locations.\n   OpenClaw workspaces are auto-detected from\n   `~\u002F.openclaw\u002Fworkspace\u002Fskills\u002F`. The check validates reachability (is\n   the skill mentioned from RESOLVER.md?), MECE overlap (does it duplicate\n   an existing skill's trigger?), gap detection (are there user intents\n   that fall through the resolver with no match?), and DRY. If it fails,\n   fix the skill (or extend an existing one instead of creating a\n   duplicate).\n9. Add an E2E smoke test. For gbrain: submit a Minion job or run a CLI\n   invocation end-to-end against a fixture brain; assert side effects.\n10. Update `brain\u002FRESOLVER.md` if the skill writes brain pages. Orphaned\n    brain pages are worse than no brain pages.\n\n### Phase 3: Verify\n\nRun each of these and confirm green:\n\n```bash\n# Unit tests\nbun test test\u002F\u003Cskill-name>.test.ts\n\n# Integration tests (when applicable)\nbun run test:e2e\n\n# Resolver reachability + MECE + DRY\ngbrain check-resolvable\n\n# Conformance tests (skill YAML + required sections)\nbun test test\u002Fskills-conformance.test.ts\n```\n\n## Quality gates\n\nA feature is NOT properly skilled until:\n\n- All tests pass (unit + integration + evals).\n- It appears in `skills\u002FRESOLVER.md` with accurate trigger patterns.\n- The resolver trigger eval confirms patterns route to the new skill.\n- `gbrain check-resolvable` shows no orphaned skills, no MECE overlaps,\n  no DRY violations.\n- If it writes brain pages, `brain\u002FRESOLVER.md` has the directory.\n\n## Anti-Patterns\n\n- ❌ Code with no SKILL.md — invisible to the resolver; the agent will\n  never run it.\n- ❌ SKILL.md with no tests — untested contract; one prompt change\n  regresses silently.\n- ❌ Tests that reimplement production code — the reimplementation's\n  bugs don't catch production's bugs (the `files-test-reimplements-\n  production` lesson).\n- ❌ Resolver entry that uses internal jargon the user never types —\n  trigger patterns must mirror real user language.\n- ❌ Feature that writes to brain without a `brain\u002FRESOLVER.md` entry —\n  orphaned pages the agent will never find.\n- ❌ Deterministic logic in LLM space — should be a script.\n- ❌ LLM judgment in deterministic space — should be an eval.\n\n## Why skillify + check-resolvable is the right pair\n\nHermes and similar agent frameworks auto-create skills as a background\nbehavior. That's fine until you don't know what the agent shipped —\nchecklists decay, tests drift, resolver entries get stale.\n\nGbrain ships the same capability as two user-controlled tools:\n\n- `\u002Fskillify` builds the checklist and helps you fill in the gaps.\n- `gbrain check-resolvable` validates the whole skill tree: reachability,\n  MECE, DRY, gap detection, orphaned skills.\n\nYou decide when and what. The human keeps judgment. The tooling keeps the\nchecklist honest. In practice this combo produces zero orphaned skills,\nevery feature with tests + evals + resolver triggers + evals of the\ntriggers.\n\n## Output Format\n\nA skillify run produces, in order:\n\n1. An audit printout listing which of the 10 items exist and which are\n   missing for the target feature.\n2. The files created to close each gap (SKILL.md, test files, resolver\n   entries).\n3. The final `gbrain check-resolvable` output confirming reachability.\n4. A one-line summary of the resulting skill completeness score (N\u002F10).\n","# Skillify — The Meta Skill\n\n## Contract\n\nA feature is \"properly skilled\" when all ten checklist items are present:\n\n1. `SKILL.md` — skill file with YAML frontmatter, triggers, contract, phases.\n2. Code — deterministic script if applicable.\n3. Unit tests — cover every branch of deterministic logic.\n4. Integration tests — exercise live endpoints, not just in-memory shape.\n5. LLM evals — quality\u002Fcorrectness cases if the feature includes any LLM call.\n6. Resolver trigger — `skills\u002FRESOLVER.md` entry with the trigger patterns\n   the user actually types.\n7. Resolver trigger eval — test that feeds trigger phrases to the resolver\n   and asserts they route to this skill, not the old pre-skillify path.\n8. Check-resolvable — `gbrain check-resolvable` passes (skill is reachable,\n   MECE against its siblings, no DRY violations).\n9. E2E test — exercises the full pipeline from user turn to side effect.\n10. Brain filing — if the feature writes brain pages, `brain\u002FRESOLVER.md`\n    has an entry for the directory so the pages aren't orphaned.\n\n## Trigger\n\n- \"skillify this\" \u002F \"skillify\" \u002F \"is this a skill?\" \u002F \"make this proper\"\n- \"add tests and evals for this\"\n- After building any new feature that touches user-facing behavior\n- When you grep the repo and notice a script with no SKILL.md next to it\n\n## Phases\n\n### Phase 1: Audit what exists\n\nFor the feature being skillified, answer:\n\n- **Feature name**: what does it do in one line?\n- **Code path**: where does the implementation live (file path)?\n- **Checklist status**: run `gbrain skillify check \u003Cpath>` (preferred)\n  or the legacy `scripts\u002Fskillify-check.ts \u003Cpath>` shim. Both produce\n  the same 10-item scorecard. Note which items are missing.\n\n### Phase 2: Create missing pieces in order\n\n**Fast path — brand-new skill:** run `gbrain skillify scaffold \u003Cname>\n--description \"...\" [--triggers \"p1,p2,p3\"] [--writes-pages --writes-to\n\"people\u002F,companies\u002F\"]`. This creates all 5 stub files atomically and\nappends an idempotent resolver row. Every scaffolded file carries the\n`SKILLIFY_STUB` sentinel; `gbrain check-resolvable --strict` will fail\nCI until you replace the stubs with real content.\n\n**Manual path — extending an existing skill:** work the list top-down.\nEach earlier item constrains what later items look like (the SKILL.md\ncontract determines what tests assert; tests determine what evals gate;\nthe resolver entry determines what trigger-eval checks).\n\n1. Write `SKILL.md` first. Frontmatter must include `name`, `version`,\n   `description`, `triggers[]`, `tools[]`, `mutating`. Body has at minimum\n   Contract, Phases, and Output Format sections.\n2. Extract deterministic code into a script if applicable (scripts\u002F*.ts\n   for gbrain; host projects may use .mjs \u002F .py \u002F whatever their runtime\n   uses).\n3. Write unit tests for every branch of the script. Mock external calls\n   (LLM, DB, network) so tests run fast and deterministic.\n4. Add integration tests that hit real endpoints. These catch bugs the\n   unit tests' mocks hide (see the `files-test-reimplements-production`\n   learning: reimplementation in tests lets production vulnerabilities\n   slip through).\n5. Add LLM evals if the feature includes any LLM call. Even a three-case\n   eval (happy \u002F edge \u002F adversarial) is cheap insurance against prompt\n   regressions.\n6. Add the resolver trigger to `skills\u002FRESOLVER.md`. Use the trigger\n   patterns the user ACTUALLY types, not what you think they should type.\n7. Add a resolver trigger eval that feeds those patterns in and asserts\n   they route to the new skill.\n8. Run `gbrain check-resolvable` (auto-detects skill trees) or\n   `gbrain check-resolvable --skills-dir \u003Cpath>` for custom locations.\n   OpenClaw workspaces are auto-detected from\n   `~\u002F.openclaw\u002Fworkspace\u002Fskills\u002F`. The check validates reachability (is\n   the skill mentioned from RESOLVER.md?), MECE overlap (does it duplicate\n   an existing skill's trigger?), gap detection (are there user intents\n   that fall through the resolver with no match?), and DRY. If it fails,\n   fix the skill (or extend an existing one instead of creating a\n   duplicate).\n9. Add an E2E smoke test. For gbrain: submit a Minion job or run a CLI\n   invocation end-to-end against a fixture brain; assert side effects.\n10. Update `brain\u002FRESOLVER.md` if the skill writes brain pages. Orphaned\n    brain pages are worse than no brain pages.\n\n### Phase 3: Verify\n\nRun each of these and confirm green:\n\n```bash\n# Unit tests\nbun test test\u002F\u003Cskill-name>.test.ts\n\n# Integration tests (when applicable)\nbun run test:e2e\n\n# Resolver reachability + MECE + DRY\ngbrain check-resolvable\n\n# Conformance tests (skill YAML + required sections)\nbun test test\u002Fskills-conformance.test.ts\n```\n\n## Quality gates\n\nA feature is NOT properly skilled until:\n\n- All tests pass (unit + integration + evals).\n- It appears in `skills\u002FRESOLVER.md` with accurate trigger patterns.\n- The resolver trigger eval confirms patterns route to the new skill.\n- `gbrain check-resolvable` shows no orphaned skills, no MECE overlaps,\n  no DRY violations.\n- If it writes brain pages, `brain\u002FRESOLVER.md` has the directory.\n\n## Anti-Patterns\n\n- ❌ Code with no SKILL.md — invisible to the resolver; the agent will\n  never run it.\n- ❌ SKILL.md with no tests — untested contract; one prompt change\n  regresses silently.\n- ❌ Tests that reimplement production code — the reimplementation's\n  bugs don't catch production's bugs (the `files-test-reimplements-\n  production` lesson).\n- ❌ Resolver entry that uses internal jargon the user never types —\n  trigger patterns must mirror real user language.\n- ❌ Feature that writes to brain without a `brain\u002FRESOLVER.md` entry —\n  orphaned pages the agent will never find.\n- ❌ Deterministic logic in LLM space — should be a script.\n- ❌ LLM judgment in deterministic space — should be an eval.\n\n## Why skillify + check-resolvable is the right pair\n\nHermes and similar agent frameworks auto-create skills as a background\nbehavior. That's fine until you don't know what the agent shipped —\nchecklists decay, tests drift, resolver entries get stale.\n\nGbrain ships the same capability as two user-controlled tools:\n\n- `\u002Fskillify` builds the checklist and helps you fill in the gaps.\n- `gbrain check-resolvable` validates the whole skill tree: reachability,\n  MECE, DRY, gap detection, orphaned skills.\n\nYou decide when and what. The human keeps judgment. The tooling keeps the\nchecklist honest. In practice this combo produces zero orphaned skills,\nevery feature with tests + evals + resolver triggers + evals of the\ntriggers.\n\n## Output Format\n\nA skillify run produces, in order:\n\n1. An audit printout listing which of the 10 items exist and which are\n   missing for the target feature.\n2. The files created to close each gap (SKILL.md, test files, resolver\n   entries).\n3. The final `gbrain check-resolvable` output confirming reachability.\n4. A one-line summary of the resulting skill completeness score (N\u002F10).\n",{"name":5,"tools":47,"version":49,"mutating":43,"triggers":50,"description":56},[41,48],"list_pages","1.0.0",[51,5,52,53,54,55],"skillify this","is this a skill?","make this proper","add tests and evals for this","check skill completeness","The meta skill. Turn any raw feature or script into a properly-skilled,\ntested, resolvable, evaled unit of agent-visible capability. Use when\nthe user says \"skillify this\", \"is this a skill?\", \"make this proper\",\nor after a new feature is built without the full skill infrastructure.\n\nPaired with `gbrain check-resolvable`, skillify gives a user-controllable\nequivalent of Hermes' auto-skill-creation: you build, skillify checks the\nchecklist, check-resolvable verifies nothing is orphaned. The human keeps\njudgment; the tooling keeps the checklist honest.\n","master","48f3da67113808a35b3721091cc58290a8c49ab4","skills\u002Fskillify","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl","2026-04-26 19:27:01",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add sixtycat2000-ctrl\u002Fgbrain-qmd --skill skillify",{"tool":69,"command":70},"bunx","bunx skills add sixtycat2000-ctrl\u002Fgbrain-qmd --skill skillify",{"tool":72,"command":73},"pnpm","pnpm dlx skills add sixtycat2000-ctrl\u002Fgbrain-qmd --skill skillify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fskillify\u002FSKILL.md",true,[],[78,103,135,159,181,203],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":42},"01M6R33ZFP10GVGJ7FX4GQWVK1","webhook-transforms","Generic framework for converting external events (SMS, meetings, social mentions)\ninto brain-ingestible signals. Define a transform function, register a webhook URL,\nand incoming events get processed through the brain pipeline.","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fwebhook-transforms\u002FSKILL.md",[],[85,86,87,41,88,89,90,91,92,93,94,95,96,97,98,99,100,101,26,102],"webhook","transforms","webhook transforms","pipeline","SET","page","meetings","up","social","signals","get","define","register","sms","event","URL","true","generic",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":118,"publishedAt":42},"01M6R33SCJAHZHG7HRN0JF29AB","testing","Skill validation framework. Validates every skill has SKILL.md with frontmatter,\nevery reference exists, every env var is declared. The testing contract for the\nskill system itself.","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Ftesting\u002FSKILL.md",[109,112,113],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[105,119,120,121,41,122,123,124,125,126,127,128,129,130,131,132,31,133,134,26],"test","run","validation","health","system","check","health check","skill validation","validate skills","contract","tests","skill health","pages","env","test skills","with",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":42},"01M6R33DCE6RSA4YRCJ5H787E3","soul-audit","6-phase interactive interview that generates the agent's identity (SOUL.md),\nuser profile (USER.md), access control (ACCESS_POLICY.md), and operational\ncadence (HEARTBEAT.md). Re-runnable anytime to update any section.","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fsoul-audit\u002FSKILL.md",[141],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[143,144,145,146,147,89,148,90,149,150,92,151,152,153,154,155,156,101,157,158],"audit","soul","soul audit","policy","customize","access","interactive","interview","personality","Access Control","cadence","SOUL.md","re","my agent","section","phase",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":42},"01M6R338GVZ1B8RCTWCEBG3SFS","smoke-test","Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments.\nTests critical services, auto-fixes known issues, extensible via user-defined\ntest scripts in ~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh.","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fsmoke-test\u002FSKILL.md",[165],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},[119,167,168,169,170,120,171,172,173,38,174,129,175,176,177,101,26,178,179,180],"smoke","smoke test","openclaw","run smoke tests","issues","read","fix","restart","critical","scripts","environments","fixes","break","auto-fix",{"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":187,"publishedAt":42},"01M6R32XF94PR8S1G75S1FRZ94","skillpack-check","Run `gbrain skillpack-check` to produce an agent-readable JSON health report\nfor the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations\n--list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron)\ncan see at a glance whether the skillpack needs attention.\n\nUse when the user asks \"is gbrain healthy?\", when a cron fires a morning\ncheck, or proactively when something seems off (jobs not running, brain\nnot updating, autopilot silent).","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fskillpack-check\u002FSKILL.md",[],[124,188,189,190,122,191,192,193,194,31,195,196,197,198,199,26,200,201,23,202],"skillpack check","doctor","produce","use","migrations","glance","attention","gbrain","host","healthy","briefing","can","apply","morning check","running",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":211,"publishedAt":42},"01M6R32H0AWRMVGZ5EPSVJCBWH","skill-creator","Create new skills following the GBrain conformance standard. Generates SKILL.md\nwith frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks\nMECE against existing skills. Updates manifest and resolver.","https:\u002F\u002Fgithub.com\u002Fsixtycat2000-ctrl\u002Fgbrain-qmd\u002Fblob\u002Fmaster\u002Fskills\u002Fskill-creator\u002FSKILL.md",[209,210],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},[212,213,214,41,215,216,217,218,219,128,131,195,220,134,101,221,222,223,224,225],"skill creator","creator","create","manifest","improve","format","anti-patterns","mece","output","resolver","updates","conformance","Existing","standard"]