[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71K0GCF2WCRGE808DZJN18F":3,"skill-same:01M71K0GCF2WCRGE808DZJN18F":72},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M71K0GCF2WCRGE808DZJN18F","brain:export",null,"Use when the user asks to refresh CLAUDE.local.md, regenerate project context, or after a brain-update session flush. Rewrites only the sentinel-delimited auto-generated section from the brain DB, preserving manual behavior rules.","coco-research\u002Fcoco","coco-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F68911604?v=4","01M71JRE9C4NM4NSZM4JD0BJTB","Coco Research","01M71JREA0ZMR0PMH3CKA99SN1",631,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fbrain\u002Fskills\u002Fbrain-export\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"export","brain","brain db","when","section","manual","auto-generated","db","project","local","update","only","auto","use","session","generated","context","Rules","sentinel","2026-11-10 10:12:30",false,"---\nname: brain:export\ndescription: \"Use when the user asks to refresh CLAUDE.local.md, regenerate project context, or after a brain-update session flush. Rewrites only the sentinel-delimited auto-generated section from the brain DB, preserving manual behavior rules.\"\n---\n\n# \u002Fbrain-export — CLAUDE.local.md Auto-Generator\n\nGenerates or refreshes the `\u003C!-- AUTO-GENERATED: brain-export -->` section in the project's `CLAUDE.local.md` file from the brain SQLite DB. Protects all manually written content above and below the sentinels.\n\n## Quick Reference\n\n```bash\nBRAIN=\"python3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py\"\n\n# Basic export (writes CLAUDE.local.md next to project_brain.db)\n$BRAIN export \u003Cproject-slug>\n\n# Export with explicit output path\n$BRAIN export \u003Cproject-slug> --output \u002Fpath\u002Fto\u002FCLAUDE.local.md\n\n# Export with explicit DB path\n$BRAIN --db \u002Fpath\u002Fto\u002Fproject_brain.db export \u003Cproject-slug>\n```\n\n## Procedure\n\n### Step 1 — Verify brain DB exists\n\n```bash\nBRAIN=\"python3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py\"\n$BRAIN info\n```\n\nIf the DB is missing, tell the user to run `\u002Fbrain-init` first.\n\n### Step 2 — Run the export\n\n```bash\n$BRAIN export \u003Cproject-slug>\n```\n\nThe exporter will:\n1. Read any existing `CLAUDE.local.md` at the output path\n2. Preserve everything above `\u003C!-- AUTO-GENERATED: brain-export -->`\n3. Preserve everything below `\u003C!-- END AUTO-GENERATED -->`\n4. If no sentinels found, append the auto section at the bottom (safe first run)\n5. Regenerate the auto section from brain DB\n6. Write atomically (tmp file + rename)\n\n### Step 3 — Show the user what was generated\n\nParse the JSON output and display:\n\n```\nbrain:export complete\n─────────────────────────────────────────\nOutput:         \u002Fpath\u002Fto\u002FCLAUDE.local.md\nProject slug:   \u003Cslug>\nAuto section:   ~NNN tokens (within 1,200 token budget: YES\u002FNO)\nTotal file:     ~NNN tokens\n─────────────────────────────────────────\nSections generated:\n  - Project Identity  (if ~\u002F.mempalace\u002Fidentity.txt exists)\n  - Last Session      (most recent event + decision)\n  - Key People        (up to 8 person entities)\n  - Key Systems       (up to 8 system\u002Fmodule entities)\n  - Recent Decisions  (last 4 decisions)\n  - Project Status    (entity\u002Fdecision\u002Fevent counts + last sync date)\n```\n\n### Step 4 — First-run: offer to migrate feedback memories\n\nIf this is the first export AND the project memory directory contains files with `type: feedback` frontmatter, offer to migrate them into behavior rules:\n\n```\nFound N feedback memory files that could become behavior rules in CLAUDE.local.md:\n  - feedback_html_docs_with_tailwind.md → \"Documents as Tailwind HTML not Markdown\"\n\nAdd these as a ## Behavior Rules section below the auto-generated block? [y\u002FN]\n```\n\nTo migrate programmatically:\n\n```python\nfrom brain.exporter import migrate_feedback_memories\nfrom pathlib import Path\n\nmemory_dir = Path(\"~\u002F.claude\u002Fprojects\u002F\u003Cproject-slug-hash>\u002Fmemory\").expanduser()\nrules = migrate_feedback_memories(memory_dir)\nfor rule in rules:\n    print(rule)\n```\n\nThen append the rules as a `## Behavior Rules` section below `\u003C!-- END AUTO-GENERATED -->` in `CLAUDE.local.md`.\n\n## Auto-Section Format\n\n```markdown\n\u003C!-- AUTO-GENERATED: brain-export -->\n\u003C!-- Generated: 2026-04-09T12:00:00Z | Brain DB: 42 entities | MemPalace: 7 drawers -->\n\n## Project Identity\n\u003Ccontents of ~\u002F.mempalace\u002Fidentity.txt if it exists>\n\n## Last Session\n- Most recent event title (YYYY-MM-DD)\n- Most recent decision text (YYYY-MM-DD)\n\n## Key People\n| Name | Role | Email |\n|------|------|-------|\n| Alice Smith | Product Manager | alice@example.com |\n\n## Key Systems\n- **SystemA** — Description from metadata\n- **ModuleB**\n\n## Recent Decisions\n- [2026-04-08] Decision text (truncated to 120 chars)\n\n## Project Status\n- Entities: 42 | Decisions: 12 | Events: 8\n- Last brain sync: 2026-04-09\n- Query: `\u002Fcoco brain` or `\u002Fbrain context {slug}` for full context\n\n\u003C!-- END AUTO-GENERATED -->\n```\n\n## Sentinel Contract\n\n| Sentinel | Position | Meaning |\n|----------|----------|---------|\n| `\u003C!-- AUTO-GENERATED: brain-export -->` | Start of auto block | Everything below is managed by exporter |\n| `\u003C!-- END AUTO-GENERATED -->` | End of auto block | Everything below is protected manual content |\n\n**Never manually edit between the sentinels** — changes will be overwritten on next export.\n**Safe to edit** anything above START or below END at any time.\n\n## Token Budget\n\nThe auto section is capped at **1,200 tokens (~4,800 characters)**. If the generated content exceeds this, the body is truncated. The header comment and sentinels are always preserved intact.\n\n## When to Run\n\n- After every `\u002Fbrain-update` session flush (brain DB has new data)\n- After `\u002Fbrain-init` (first time setup)\n- After `\u002Fbrain-rescan` (bulk entity import)\n- When starting work on a project for the first time in a new session (ensure context is fresh)\n\n## Trigger Phrases\n\n- \"export brain to CLAUDE.local.md\"\n- \"refresh project context file\"\n- \"generate CLAUDE.local\"\n- \"update auto-generated section\"\n- \"brain export \u003Cslug>\"\n","# \u002Fbrain-export — CLAUDE.local.md Auto-Generator\n\nGenerates or refreshes the `\u003C!-- AUTO-GENERATED: brain-export -->` section in the project's `CLAUDE.local.md` file from the brain SQLite DB. Protects all manually written content above and below the sentinels.\n\n## Quick Reference\n\n```bash\nBRAIN=\"python3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py\"\n\n# Basic export (writes CLAUDE.local.md next to project_brain.db)\n$BRAIN export \u003Cproject-slug>\n\n# Export with explicit output path\n$BRAIN export \u003Cproject-slug> --output \u002Fpath\u002Fto\u002FCLAUDE.local.md\n\n# Export with explicit DB path\n$BRAIN --db \u002Fpath\u002Fto\u002Fproject_brain.db export \u003Cproject-slug>\n```\n\n## Procedure\n\n### Step 1 — Verify brain DB exists\n\n```bash\nBRAIN=\"python3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py\"\n$BRAIN info\n```\n\nIf the DB is missing, tell the user to run `\u002Fbrain-init` first.\n\n### Step 2 — Run the export\n\n```bash\n$BRAIN export \u003Cproject-slug>\n```\n\nThe exporter will:\n1. Read any existing `CLAUDE.local.md` at the output path\n2. Preserve everything above `\u003C!-- AUTO-GENERATED: brain-export -->`\n3. Preserve everything below `\u003C!-- END AUTO-GENERATED -->`\n4. If no sentinels found, append the auto section at the bottom (safe first run)\n5. Regenerate the auto section from brain DB\n6. Write atomically (tmp file + rename)\n\n### Step 3 — Show the user what was generated\n\nParse the JSON output and display:\n\n```\nbrain:export complete\n─────────────────────────────────────────\nOutput:         \u002Fpath\u002Fto\u002FCLAUDE.local.md\nProject slug:   \u003Cslug>\nAuto section:   ~NNN tokens (within 1,200 token budget: YES\u002FNO)\nTotal file:     ~NNN tokens\n─────────────────────────────────────────\nSections generated:\n  - Project Identity  (if ~\u002F.mempalace\u002Fidentity.txt exists)\n  - Last Session      (most recent event + decision)\n  - Key People        (up to 8 person entities)\n  - Key Systems       (up to 8 system\u002Fmodule entities)\n  - Recent Decisions  (last 4 decisions)\n  - Project Status    (entity\u002Fdecision\u002Fevent counts + last sync date)\n```\n\n### Step 4 — First-run: offer to migrate feedback memories\n\nIf this is the first export AND the project memory directory contains files with `type: feedback` frontmatter, offer to migrate them into behavior rules:\n\n```\nFound N feedback memory files that could become behavior rules in CLAUDE.local.md:\n  - feedback_html_docs_with_tailwind.md → \"Documents as Tailwind HTML not Markdown\"\n\nAdd these as a ## Behavior Rules section below the auto-generated block? [y\u002FN]\n```\n\nTo migrate programmatically:\n\n```python\nfrom brain.exporter import migrate_feedback_memories\nfrom pathlib import Path\n\nmemory_dir = Path(\"~\u002F.claude\u002Fprojects\u002F\u003Cproject-slug-hash>\u002Fmemory\").expanduser()\nrules = migrate_feedback_memories(memory_dir)\nfor rule in rules:\n    print(rule)\n```\n\nThen append the rules as a `## Behavior Rules` section below `\u003C!-- END AUTO-GENERATED -->` in `CLAUDE.local.md`.\n\n## Auto-Section Format\n\n```markdown\n\u003C!-- AUTO-GENERATED: brain-export -->\n\u003C!-- Generated: 2026-04-09T12:00:00Z | Brain DB: 42 entities | MemPalace: 7 drawers -->\n\n## Project Identity\n\u003Ccontents of ~\u002F.mempalace\u002Fidentity.txt if it exists>\n\n## Last Session\n- Most recent event title (YYYY-MM-DD)\n- Most recent decision text (YYYY-MM-DD)\n\n## Key People\n| Name | Role | Email |\n|------|------|-------|\n| Alice Smith | Product Manager | alice@example.com |\n\n## Key Systems\n- **SystemA** — Description from metadata\n- **ModuleB**\n\n## Recent Decisions\n- [2026-04-08] Decision text (truncated to 120 chars)\n\n## Project Status\n- Entities: 42 | Decisions: 12 | Events: 8\n- Last brain sync: 2026-04-09\n- Query: `\u002Fcoco brain` or `\u002Fbrain context {slug}` for full context\n\n\u003C!-- END AUTO-GENERATED -->\n```\n\n## Sentinel Contract\n\n| Sentinel | Position | Meaning |\n|----------|----------|---------|\n| `\u003C!-- AUTO-GENERATED: brain-export -->` | Start of auto block | Everything below is managed by exporter |\n| `\u003C!-- END AUTO-GENERATED -->` | End of auto block | Everything below is protected manual content |\n\n**Never manually edit between the sentinels** — changes will be overwritten on next export.\n**Safe to edit** anything above START or below END at any time.\n\n## Token Budget\n\nThe auto section is capped at **1,200 tokens (~4,800 characters)**. If the generated content exceeds this, the body is truncated. The header comment and sentinels are always preserved intact.\n\n## When to Run\n\n- After every `\u002Fbrain-update` session flush (brain DB has new data)\n- After `\u002Fbrain-init` (first time setup)\n- After `\u002Fbrain-rescan` (bulk entity import)\n- When starting work on a project for the first time in a new session (ensure context is fresh)\n\n## Trigger Phrases\n\n- \"export brain to CLAUDE.local.md\"\n- \"refresh project context file\"\n- \"generate CLAUDE.local\"\n- \"update auto-generated section\"\n- \"brain export \u003Cslug>\"\n",{"name":5,"description":7},"main","cd89f013b617f7eea982a9bbc60e992974fda2aa","systems\u002Fbrain\u002Fskills\u002Fbrain-export",15,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco","https:\u002F\u002Fcocoresearch.org\u002Fcoco\u002F","https:\u002F\u002Fgithub.com\u002Fcoco-research","https:\u002F\u002Fcocoresearch.org","Local-first, open-source tools for people who work with AI agents: governed memory, agents that check their own work, and data that stays on your machine.","2026-11-11 12:18:13",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add coco-research\u002Fcoco --skill \"brain:export\"",{"tool":64,"command":65},"bunx","bunx skills add coco-research\u002Fcoco --skill \"brain:export\"",{"tool":67,"command":68},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill \"brain:export\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fbrain\u002Fskills\u002Fbrain-export\u002FSKILL.md",true,[],[73,97,107,125,159,178],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":43},"01M71KEJXF9KMT0BWCMRSRFA4M","trading-super-intelligence","Trading Super Intelligence Team. Named real-world personas across 8 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Ftrading\u002FSKILL.md",[79],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[81,82,83,84,85,86,33,87,88,89,90,91,92,93,94,95,96],"super","trading super intelligence","intelligence","trading","validator","personas","composites","studio","team","across","world","first","gated","2026","lm studio","local-first",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":43},"01M71KEFWS3CMAP7DF1P0FWTDE","strategy-super-intelligence","Strategy Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fstrategy\u002FSKILL.md",[103],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[105,81,106,83,85,86,33,87,88,89,90,91,92,93,94,95,96],"strategy","strategy super intelligence",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":119,"publishedAt":43},"01M71KED56ZEPK2QE84QSQPMT0","risk-compliance-super-intelligence","Risk & Compliance (GRC) Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Frisk-compliance\u002FSKILL.md",[113,114],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[120,81,121,122,123,83,85,86,33,87,124,88,89,90,91,92,93,94,95,96],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":144,"publishedAt":43},"01M71KE9A2FWSC74VA96W1EZSN","product-design-super-intelligence","Your product + design brain trust and decision partner. Named personas across 8 cells spanning product strategy, discovery\u002Fresearch, growth\u002Fmetrics, design foundations\u002Fusability, design leadership\u002Fcraft, UX\u002Fcontent, design systems, and a…","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fproduct-design\u002FSKILL.md",[131,134,137,138,141],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":139,"categoryName":140,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":142,"categoryName":143,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000032","设计师",[145,146,83,147,81,148,149,150,151,152,153,89,90,154,155,94,25,156,157,158],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","craft","metrics","trust",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":167,"publishedAt":43},"01M71KE6H9FPSD9TECYFBPXZ8Y","legal-ip-super-intelligence","Your legal, IP, and regulatory brain trust. 31 named personas across 7 cells covering patent strategy, tech licensing, regulatory litigation, AI governance, open-source compliance, privacy law, and antitrust.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Flegal-ip\u002FSKILL.md",[165,166],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[168,81,169,83,170,171,158,172,86,173,174,175,105,89,90,176,122,177,94,25],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":43},"01M71KE36QRY610V6YVB9JWRND","healthcare-life-sciences-super-intelligence","Your healthcare and life sciences brain trust. 25 named personas across 7 cells covering drug discovery, medtech, biotech strategy, health policy, genomics, clinical trials, and healthcare economics.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fhealthcare-life-sciences\u002FSKILL.md",[184],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[186,81,187,188,83,171,158,189,190,86,191,192,105,89,90,193,194,195,196,94],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]