[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AAS0B8EAPNJGC7ACEAC0B2":3,"skill-same:01M7AAS0B8EAPNJGC7ACEAC0B2":62},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M7AAS0B8EAPNJGC7ACEAC0B2","brain-taxonomist",null,"Filing gate for ALL brain writes. Consulted before creating any new\nbrain page to determine the correct path. Reads the ACTIVE schema pack\nvia `gbrain schema show --json` — no hardcoded directory table. Also\nruns periodic taxonomy drift detection via `gbrain schema review-orphans`.","azxav\u002F2brain-techawards","azxav","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179442426?v=4","01M7AAQ8FVXFBM43ZF24VGZNCE","Azizbek Xasanov","01M7AAQ8GXE9M074VFWBXAG49E",0,"MIT","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Fskills\u002Fbrain-taxonomist\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: brain-taxonomist\nversion: 1.0.0\nprompt_version: 1\ndescription: |\n  Filing gate for ALL brain writes. Consulted before creating any new\n  brain page to determine the correct path. Reads the ACTIVE schema pack\n  via `gbrain schema show --json` — no hardcoded directory table. Also\n  runs periodic taxonomy drift detection via `gbrain schema review-orphans`.\ntriggers:\n  - \"where does this brain page go\"\n  - \"file this in the brain\"\n  - \"brain taxonomist\"\n  - \"taxonomy check\"\n  - \"refile brain page\"\n  - \"create brain page\"\n  - \"which directory does this go\"\n  - \"which directory does this page go\"\nmutating: false\n---\n\n# brain-taxonomist\n\n## Purpose\n\n**Gate function:** Before creating ANY new brain page, consult this skill to determine the correct filing path. This prevents misfiling at write time rather than cleaning up drift after the fact.\n\n**Drift function:** Periodic scan for pages that have outgrown their current location.\n\n## Contract\n\nThis skill guarantees:\n- Every new page is filed at the path determined by the ACTIVE schema pack — never against a hardcoded directory table baked into this skill.\n- The decision is reproducible: invoking brain-taxonomist twice on the same content produces the same recommended path.\n- Ambiguous cases surface to the user via `skills\u002Fask-user\u002F` rather than silently picking a default.\n- Per-source overrides via `--source \u003Cid>` are honored — multi-brain users (Persona B) get a different recommendation per source if their packs diverge.\n- When no matching `page_types[]` entry exists in the active pack, the skill signals to EIIRP Phase 3 (SCHEMA CHECK) rather than picking the closest-fitting fallback.\n\n## Critical: this skill reads the ACTIVE schema pack as data\n\n`brain-taxonomist` has NO hardcoded directory table. Every decision is\ndriven by `gbrain schema show --json`. This means:\n- A user who runs `gbrain schema use gbrain-recommended` gets the full\n  recommended directory set (deal, meeting, concept, project, source,\n  daily, personal, civic, original, place, trip, conversation, writing,\n  plus all gbrain-base types).\n- A user who authored a custom pack via `gbrain schema init` + edit gets\n  filing recommendations based on THEIR taxonomy, not gbrain's defaults.\n- Per-source overrides (tier 3 in the 7-tier resolution chain) are honored\n  when `--source \u003Cid>` is passed to brain-taxonomist.\n\nThis is the single-source-of-truth principle (D9 from the v0.39 plan-eng-review).\n\n## When to Consult (MANDATORY)\n\nRun the taxonomist check before writing to the brain in these cases:\n\n1. **New brain page** — any `type` (person, company, concept, book, meeting, etc.)\n2. **Bulk import** — before committing a batch of new pages\n3. **Uncertain filing** — when the primary subject is ambiguous\n\nYou do NOT need to consult for:\n- Updating an existing page in place (same path)\n- Appending to a Timeline section\n- Meeting entity propagation to existing pages\n\n## Decision Protocol\n\n### Step 1: Identify primary subject type\n\nWalk these questions in order:\n1. Is the primary subject a NAMED PERSON? → person-typed directory\n2. Is the primary subject a NAMED ORGANIZATION? → company-typed directory\n3. Is it about a TIME-BOUNDED EVENT (meeting, deal, trip)? → temporal-typed directory\n4. Is it a REUSABLE MENTAL MODEL? → concept-typed directory\n5. Is it RAW MEDIA (article, video, book, PDF)? → media-typed directory\n6. Is it BULK SOURCE DATA? → source-typed directory\n7. None of the above → consult EIIRP Phase 3 for schema-pack candidate creation.\n\n### Step 2: Look up the directory for that type in the active pack\n\n```bash\ngbrain schema show --json | jq '.page_types[] | select(.primitive == \"entity\")'\n```\n\nEach `page_types[]` entry has a `path_prefixes:` array. The first prefix\nis the canonical path. If multiple types match (e.g. both `person` and\n`founder` exist in the pack with `expert_routing: true`), prefer the more\nspecific one (the one with the more specific path prefix).\n\n### Step 3: For books — determine sub-category\n\nThe `gbrain-recommended` pack treats books as `media\u002Fbooks\u002F\u003Ccategory>\u002F\u003Cslug>.md`\nwhere category is one of: psychology, philosophy, spirituality, business,\nmedia-and-society, family-and-divorce, heritage, science, fiction,\nbiography, arts-and-design. If your active pack has a different scheme,\nwalk it from `gbrain schema show --json` instead of hardcoding here.\n\n### Step 4: Construct the slug\n\n- kebab-case, descriptive\n- no author name unless disambiguation is needed\n- match the canonical path prefix exactly (no leading slash)\n\n### Step 5: Validate before writing\n\n- [ ] Path follows the active pack's `page_types[].path_prefixes`\n- [ ] Slug is kebab-case, descriptive\n- [ ] Frontmatter includes `type:` matching one of the pack's `page_types[].name`\n- [ ] Cross-links to related pages are included\n\nIf the active pack doesn't have a type for what you're trying to file,\nDON'T pick the closest-fitting one. Instead, signal to EIIRP that a new\ntype is needed and let the schema-pack cathedral handle the proposal flow.\n\n## Integration with Other Skills\n\n- `eiirp` — calls this skill as Phase 2 TAXONOMY for every output in its inventory.\n- `ingest` — article\u002Fmedia ingestion consults brain-taxonomist for filing.\n- `repo-architecture` — delegates the filing decision to this skill.\n- `book-mirror` — after generating a mirror, files it via brain-taxonomist.\n\n## Periodic Drift Detection\n\n```bash\n# What pages have no type matching the active pack?\ngbrain schema review-orphans --json\n\n# What's the overall health?\ngbrain doctor --json | jq '.checks[] | select(.name == \"schema_pack_consistency\")'\n```\n\nWhen `schema_pack_consistency` warns at >10% untyped, run the EIIRP\nPhase 3 SCHEMA CHECK flow to surface candidate types via `schema detect`.\n\n## Output Format\n\nAdvisory: a single recommendation block plus a one-line reasoning trail.\n\n```markdown\n**File at:** `\u003Cdirectory>\u002F\u003Cslug>.md`\n**Reasoning:**\n- Primary subject: \u003Cperson|company|concept|...>\n- Matched page_type: \u003Cname> (primitive: \u003Centity|temporal|concept|media|annotation>)\n- Active pack: \u003Cpack-name> v\u003Cversion>\n- Source: \u003Csource_id>\n```\n\nWhen ambiguous, surface 2 candidates via `skills\u002Fask-user\u002F` rather than\nsilently choosing.\n\nWhen the active pack has NO matching type, signal to EIIRP Phase 3\n(SCHEMA CHECK) and emit:\n\n```markdown\n**No match in active pack `\u003Cname>`.**\n**Suggested next step:** `gbrain schema detect --source \u003Csource_id>` then\n`gbrain schema review-candidates`.\n```\n\n## Anti-Patterns\n\n- **Hardcoded directory table in this skill.** Every decision goes through\n  `gbrain schema show --json`. v0.39+ broke the old hardcoded table on\n  purpose so users on `gbrain-recommended` or custom packs get the right\n  routing automatically.\n- **Picking the closest-fitting type when no type matches.** Closest-fit\n  silently degrades user filing. Surface to EIIRP Phase 3 instead.\n- **Ignoring `--source \u003Cid>` on multi-brain setups.** Per-source overrides\n  are tier-3 in the 7-tier resolution chain; missing the flag silently\n  uses the brain-wide active pack.\n- **Auto-applying a `gbrain schema review-candidates --apply` decision.**\n  Even high-confidence suggestions need user approval — this skill is a\n  GATE, not an automator.\n\n## Hard Rules\n\n- **Never hardcode a directory table in this skill.** Every decision goes\n  through `gbrain schema show --json`. The active pack is canonical.\n- **Per-source flag is first-class.** Pass `--source \u003Cid>` to every CLI\n  call when working with a non-default source.\n- **Confidence-floor honor.** EIIRP's Phase 3 produces suggestions with\n  confidence \u003C 0.6 that brain-taxonomist must surface to the user rather\n  than auto-apply. Don't silently promote a low-confidence schema delta.\n\n## Changelog\n\n### v1.0.0 — gbrain v0.39.0.0\n- Initial port from upstream OpenClaw. Genericized — no references to\n  private fork names per CLAUDE.md privacy rules.\n- Hardcoded directory table REMOVED. Every decision now reads the active\n  schema pack via `gbrain schema show --json`. Single source of truth.\n- Book taxonomy moved from skill-text to the `gbrain-recommended` pack's\n  media\u002Fbooks\u002F branch (see `src\u002Fcore\u002Fschema-pack\u002Fbase\u002Fgbrain-recommended.yaml`).\n- `--source \u003Cid>` propagation documented for multi-brain users (Persona B).\n","# brain-taxonomist\n\n## Purpose\n\n**Gate function:** Before creating ANY new brain page, consult this skill to determine the correct filing path. This prevents misfiling at write time rather than cleaning up drift after the fact.\n\n**Drift function:** Periodic scan for pages that have outgrown their current location.\n\n## Contract\n\nThis skill guarantees:\n- Every new page is filed at the path determined by the ACTIVE schema pack — never against a hardcoded directory table baked into this skill.\n- The decision is reproducible: invoking brain-taxonomist twice on the same content produces the same recommended path.\n- Ambiguous cases surface to the user via `skills\u002Fask-user\u002F` rather than silently picking a default.\n- Per-source overrides via `--source \u003Cid>` are honored — multi-brain users (Persona B) get a different recommendation per source if their packs diverge.\n- When no matching `page_types[]` entry exists in the active pack, the skill signals to EIIRP Phase 3 (SCHEMA CHECK) rather than picking the closest-fitting fallback.\n\n## Critical: this skill reads the ACTIVE schema pack as data\n\n`brain-taxonomist` has NO hardcoded directory table. Every decision is\ndriven by `gbrain schema show --json`. This means:\n- A user who runs `gbrain schema use gbrain-recommended` gets the full\n  recommended directory set (deal, meeting, concept, project, source,\n  daily, personal, civic, original, place, trip, conversation, writing,\n  plus all gbrain-base types).\n- A user who authored a custom pack via `gbrain schema init` + edit gets\n  filing recommendations based on THEIR taxonomy, not gbrain's defaults.\n- Per-source overrides (tier 3 in the 7-tier resolution chain) are honored\n  when `--source \u003Cid>` is passed to brain-taxonomist.\n\nThis is the single-source-of-truth principle (D9 from the v0.39 plan-eng-review).\n\n## When to Consult (MANDATORY)\n\nRun the taxonomist check before writing to the brain in these cases:\n\n1. **New brain page** — any `type` (person, company, concept, book, meeting, etc.)\n2. **Bulk import** — before committing a batch of new pages\n3. **Uncertain filing** — when the primary subject is ambiguous\n\nYou do NOT need to consult for:\n- Updating an existing page in place (same path)\n- Appending to a Timeline section\n- Meeting entity propagation to existing pages\n\n## Decision Protocol\n\n### Step 1: Identify primary subject type\n\nWalk these questions in order:\n1. Is the primary subject a NAMED PERSON? → person-typed directory\n2. Is the primary subject a NAMED ORGANIZATION? → company-typed directory\n3. Is it about a TIME-BOUNDED EVENT (meeting, deal, trip)? → temporal-typed directory\n4. Is it a REUSABLE MENTAL MODEL? → concept-typed directory\n5. Is it RAW MEDIA (article, video, book, PDF)? → media-typed directory\n6. Is it BULK SOURCE DATA? → source-typed directory\n7. None of the above → consult EIIRP Phase 3 for schema-pack candidate creation.\n\n### Step 2: Look up the directory for that type in the active pack\n\n```bash\ngbrain schema show --json | jq '.page_types[] | select(.primitive == \"entity\")'\n```\n\nEach `page_types[]` entry has a `path_prefixes:` array. The first prefix\nis the canonical path. If multiple types match (e.g. both `person` and\n`founder` exist in the pack with `expert_routing: true`), prefer the more\nspecific one (the one with the more specific path prefix).\n\n### Step 3: For books — determine sub-category\n\nThe `gbrain-recommended` pack treats books as `media\u002Fbooks\u002F\u003Ccategory>\u002F\u003Cslug>.md`\nwhere category is one of: psychology, philosophy, spirituality, business,\nmedia-and-society, family-and-divorce, heritage, science, fiction,\nbiography, arts-and-design. If your active pack has a different scheme,\nwalk it from `gbrain schema show --json` instead of hardcoding here.\n\n### Step 4: Construct the slug\n\n- kebab-case, descriptive\n- no author name unless disambiguation is needed\n- match the canonical path prefix exactly (no leading slash)\n\n### Step 5: Validate before writing\n\n- [ ] Path follows the active pack's `page_types[].path_prefixes`\n- [ ] Slug is kebab-case, descriptive\n- [ ] Frontmatter includes `type:` matching one of the pack's `page_types[].name`\n- [ ] Cross-links to related pages are included\n\nIf the active pack doesn't have a type for what you're trying to file,\nDON'T pick the closest-fitting one. Instead, signal to EIIRP that a new\ntype is needed and let the schema-pack cathedral handle the proposal flow.\n\n## Integration with Other Skills\n\n- `eiirp` — calls this skill as Phase 2 TAXONOMY for every output in its inventory.\n- `ingest` — article\u002Fmedia ingestion consults brain-taxonomist for filing.\n- `repo-architecture` — delegates the filing decision to this skill.\n- `book-mirror` — after generating a mirror, files it via brain-taxonomist.\n\n## Periodic Drift Detection\n\n```bash\n# What pages have no type matching the active pack?\ngbrain schema review-orphans --json\n\n# What's the overall health?\ngbrain doctor --json | jq '.checks[] | select(.name == \"schema_pack_consistency\")'\n```\n\nWhen `schema_pack_consistency` warns at >10% untyped, run the EIIRP\nPhase 3 SCHEMA CHECK flow to surface candidate types via `schema detect`.\n\n## Output Format\n\nAdvisory: a single recommendation block plus a one-line reasoning trail.\n\n```markdown\n**File at:** `\u003Cdirectory>\u002F\u003Cslug>.md`\n**Reasoning:**\n- Primary subject: \u003Cperson|company|concept|...>\n- Matched page_type: \u003Cname> (primitive: \u003Centity|temporal|concept|media|annotation>)\n- Active pack: \u003Cpack-name> v\u003Cversion>\n- Source: \u003Csource_id>\n```\n\nWhen ambiguous, surface 2 candidates via `skills\u002Fask-user\u002F` rather than\nsilently choosing.\n\nWhen the active pack has NO matching type, signal to EIIRP Phase 3\n(SCHEMA CHECK) and emit:\n\n```markdown\n**No match in active pack `\u003Cname>`.**\n**Suggested next step:** `gbrain schema detect --source \u003Csource_id>` then\n`gbrain schema review-candidates`.\n```\n\n## Anti-Patterns\n\n- **Hardcoded directory table in this skill.** Every decision goes through\n  `gbrain schema show --json`. v0.39+ broke the old hardcoded table on\n  purpose so users on `gbrain-recommended` or custom packs get the right\n  routing automatically.\n- **Picking the closest-fitting type when no type matches.** Closest-fit\n  silently degrades user filing. Surface to EIIRP Phase 3 instead.\n- **Ignoring `--source \u003Cid>` on multi-brain setups.** Per-source overrides\n  are tier-3 in the 7-tier resolution chain; missing the flag silently\n  uses the brain-wide active pack.\n- **Auto-applying a `gbrain schema review-candidates --apply` decision.**\n  Even high-confidence suggestions need user approval — this skill is a\n  GATE, not an automator.\n\n## Hard Rules\n\n- **Never hardcode a directory table in this skill.** Every decision goes\n  through `gbrain schema show --json`. The active pack is canonical.\n- **Per-source flag is first-class.** Pass `--source \u003Cid>` to every CLI\n  call when working with a non-default source.\n- **Confidence-floor honor.** EIIRP's Phase 3 produces suggestions with\n  confidence \u003C 0.6 that brain-taxonomist must surface to the user rather\n  than auto-apply. Don't silently promote a low-confidence schema delta.\n\n## Changelog\n\n### v1.0.0 — gbrain v0.39.0.0\n- Initial port from upstream OpenClaw. Genericized — no references to\n  private fork names per CLAUDE.md privacy rules.\n- Hardcoded directory table REMOVED. Every decision now reads the active\n  schema pack via `gbrain schema show --json`. Single source of truth.\n- Book taxonomy moved from skill-text to the `gbrain-recommended` pack's\n  media\u002Fbooks\u002F branch (see `src\u002Fcore\u002Fschema-pack\u002Fbase\u002Fgbrain-recommended.yaml`).\n- `--source \u003Cid>` propagation documented for multi-brain users (Persona B).\n",{"name":5,"version":24,"mutating":20,"triggers":25,"description":34,"prompt_version":35},"1.0.0",[26,27,28,29,30,31,32,33],"where does this brain page go","file this in the brain","brain taxonomist","taxonomy check","refile brain page","create brain page","which directory does this go","which directory does this page go","Filing gate for ALL brain writes. Consulted before creating any new\nbrain page to determine the correct path. Reads the ACTIVE schema pack\nvia `gbrain schema show --json` — no hardcoded directory table. Also\nruns periodic taxonomy drift detection via `gbrain schema review-orphans`.\n",1,"main","837bd04f933ca05cfef2ba496e5df0f5f92681da","skills\u002Fbrain-taxonomist","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards","https:\u002F\u002Fgithub.com\u002Fazxav","2026-10-05 01:03:28",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add azxav\u002F2brain-techawards --skill brain-taxonomist",{"tool":48,"command":49},"bunx","bunx skills add azxav\u002F2brain-techawards --skill brain-taxonomist",{"tool":51,"command":52},"pnpm","pnpm dlx skills add azxav\u002F2brain-techawards --skill brain-taxonomist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Fskills\u002Fbrain-taxonomist\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"routing-eval.jsonl","OTHER","其他",632,"https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Fskills\u002Fbrain-taxonomist\u002Frouting-eval.jsonl",[63,69,75,82,89,96],{"skillNo":64,"name":65,"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":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AB1Q20A3N1F3B7V7ABYR00","query-helper","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"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":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AB1M3ASM6Q4W5YCRS8TD4J","broken","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AB1HW3SCP26YJN6A03EV4A","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AB1G2F1SB33PW9GSMG9148","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7AB1E9DYEXR3AN2DSKFTFT3","query","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7AB1CD0BAW318SKC8DBBFYX","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fazxav\u002F2brain-techawards\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[]]