[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71K0K0M1THBJSK8W87D38XP":3,"skill-same:01M71K0K0M1THBJSK8W87D38XP":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},"01M71K0K0M1THBJSK8W87D38XP","brain:init",null,"Use when setting up project memory in a new folder or on the first brain:init in a project. Creates project_brain.db, registers the project, and bootstraps it from CLAUDE.local.md, memory files, docs, and emails; safe to re-run.","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-init\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,5,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"brain","init","emails","memory","setting","new","when","project memory","folder","re","db","safe","project","local","files","up","use","first","run","2026-11-10 10:12:30",false,"---\nname: brain:init\ndescription: \"Use when setting up project memory in a new folder or on the first brain:init in a project. Creates project_brain.db, registers the project, and bootstraps it from CLAUDE.local.md, memory files, docs, and emails; safe to re-run.\"\n---\n\n# \u002Fbrain:init --- Initialize Project Brain\n\nSets up a new `project_brain.db` in the current working directory and bootstraps it from existing project knowledge.\n\n## Procedure\n\n### Step 1: Check existing state\n\nRun:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py info\n```\n\n- If **no DB exists** → proceed to Step 2 (full init)\n- If **DB exists with project(s)** → skip to Step 3 (scan only). Tell user: \"Brain already initialized. Running scan for new\u002Fchanged files...\"\n\n### Step 2: Create the database and project record\n\nRun:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py init\n```\n\nAsk the user:\n- **Project name** (e.g., \"My Project A\", \"My Project B\")\n- **Slug** (short URL-safe identifier, e.g., \"my-project-a\", \"my-project-b\")\n- **Description** (one-liner)\n\nThen run:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py add-project \"{name}\" --slug {slug} --desc \"{description}\"\n```\n\nIf the project has sub-scopes (like ProjectA-Phase1 and ProjectA-Phase2 under one umbrella), ask if the user wants multiple project records.\n\n### Step 3: Scan the project folder\n\nRun the scanner to discover what's available:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py scan\n```\n\nThis returns a JSON report with:\n- **manifest_diff**: new\u002Fchanged\u002Funchanged file counts, whether this is the first scan\n- **files_to_process**: paths of new or changed files\n- **knowledge_sources**: which CLAUDE.local.md, memory files, docs, and emails were found\n\nShow the user a summary:\n```\nFOLDER SCAN\n===========\nFirst scan:     yes\u002Fno\nFiles found:    NN total (NN new, NN changed, NN unchanged)\n\nKnowledge sources detected:\n  CLAUDE.local.md:  found \u002F not found\n  CLAUDE.md:        found \u002F not found\n  Memory files:     N files (list names)\n  Documents:        N files in docs\u002F\n  Emails:           N files in emails\u002F\n  Reference docs:   N files\n```\n\nIf nothing to process (all unchanged): \"Everything up to date. No new knowledge to extract.\" → done.\n\n### Step 4: Extract knowledge from sources (Claude-driven)\n\nProcess sources in **priority order**. For each source, read the file, extract structured knowledge, and collect proposed writes. Do NOT write to the brain yet — collect everything first.\n\n#### Priority 1: CLAUDE.local.md\nIf found, read the full file. Extract:\n- **Sections like \"Key Decisions\"** → `decisions` (with date, decision text, decided_by if mentioned)\n- **People mentioned by name** → `person` entities (with metadata like role, email, team if mentioned)\n- **Systems\u002Ftools mentioned** → `system` entities (e.g., Snowflake, Postgres, Datadog)\n- **Teams mentioned** → `team` entities\n- **Folder structure sections** → `document` entities for key docs\n- **Recent Changes entries** → `events` (with date, type, title)\n\n#### Priority 2: Memory files (~\u002F.claude\u002Fprojects\u002F...\u002Fmemory\u002F*.md)\nEach memory file has frontmatter (name, description, type) and content. Read each file:\n- **project type memories** → `decisions` or context to enrich existing entities\n- **feedback type memories** → skip (these are Claude behavior guidance, not project knowledge)\n- **reference type memories** → `system` or `document` entities with metadata\n\n#### Priority 3: Document inventory\nFor each file in docs\u002F, emails\u002F, and Reference Doc\u002F:\n- Create a `document` entity with metadata: `{\"path\": \"relative\u002Fpath\", \"type\": \"doc|email|reference\", \"size\": N}`\n- Use the filename (cleaned) as the entity name\n- Do NOT read the full content of every file — just register them in the inventory\n\n#### Priority 4: CLAUDE.md (project-level, if exists)\nSame extraction as CLAUDE.local.md but lower priority (may overlap).\n\n### Step 5: Present extraction summary\n\nShow proposed writes:\n```\nBRAIN BOOTSTRAP SUMMARY\n========================\nProject: {name} ({slug})\n\nFrom CLAUDE.local.md:\n  Entities:    N (list: name [type])\n  Decisions:   N (list: short text)\n  Events:      N (list: title)\n\nFrom memory files:\n  Decisions:   N (list: short text)\n  Entities:    N (list: name [type])\n\nDocument inventory:\n  Documents:   N (list: filename [doc|email|reference])\n\nTotal proposed writes: NN\n```\n\nAsk: **\"Write all to brain? [Y\u002Fn\u002Fadjust]\"**\n\n### Step 6: Execute writes\n\nOn confirmation, write in this order using Python:\n```python\nimport sys\nsys.path.insert(0, '$HOME\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts')\nfrom brain.schema import get_db\nfrom brain.operations import *\n```\n\n1. **Entities** — use `upsert_entity` (idempotent, safe to re-run)\n2. **Relationships** — use `create_relationship` (also idempotent)\n3. **Decisions** — use `create_decision` (check for duplicates by matching decision text before inserting)\n4. **Events** — use `create_event` (check for duplicates by matching title + date)\n5. **Document entities** — use `upsert_entity` with type=\"document\"\n\nAfter all writes, sync to MemPalace and brain.json:\n```python\nfrom brain.memory_bridge import full_sync\nfull_sync(\"project_brain.db\", project_slug)\n```\n\nAfter writes complete, update the manifest:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py scan-update\n```\n\n### Step 7: Report\n\n```\nBRAIN INITIALIZED\n=================\nDB:            {path}\u002Fproject_brain.db\nProject:       {name} ({slug})\nSchema:        v1 (11 tables)\n\nBootstrapped from existing knowledge:\n  Entities:      +N (total: N)\n  Decisions:     +N (total: N)\n  Events:        +N (total: N)\n  Documents:     +N (total: N)\n  Relationships: +N (total: N)\n\nManifest updated: N files tracked\n\nNext: Run \u002Fbrain-update at end of session, or \u002Fbrain-rescan when files change.\n```\n\n### Step 8: Generate knowledge articles\n\nAfter completing brain writes (Step 6) and confirming the manifest is updated (Step 6\nscan-update), initialize the knowledge engine for this project.\n\n**First, register the project with the knowledge engine:**\n\n```python\nimport sys, os\nsys.path.insert(0, os.path.expanduser(\"~\u002F.coco\u002Fknowledge\"))\nfrom engine import KnowledgeEngine\n\nengine = KnowledgeEngine()\nengine.register_project(\"{slug}\", os.path.abspath(\"project_brain.db\"))\n```\n\nThis is required before the cron can harvest the project. (FIX M1: register_project\nmust be called before running any cron phases.)\n\n**Then, bootstrap article generation:**\n\n```python\nengine.full_refresh(\"{slug}\")\n```\n\nOr equivalently via CLI:\n\n```bash\npython3 ~\u002F.coco\u002Fknowledge\u002Fcron.py --run --project {slug} --phases 2,3,5\n```\n\nThis runs:\n- Phase 2 (harvest evidence from the brain DB you just populated + infer relationships)\n- Phase 3 (generate articles for all entities — first run will generate all)\n- Phase 5 (FTS5 index the new articles)\n\nShow the user:\n```\nKNOWLEDGE ENGINE\n================\nArticles generated:  N\nFTS5 indexed:        N\nEstimated cost:      $0.XXX\n\nArticles written to: ~\u002F.coco\u002Fknowledge\u002Farticles\u002F\nSearch with: \u002Fbrain-wiki search \"{project_name}\"\n```\n\n**Skip this step silently if:**\n- `~\u002F.coco\u002Fknowledge\u002F` does not exist (knowledge engine not installed)\n- The `cron.py` call fails for any reason (non-blocking — brain init still succeeds)\n\n---\n\n## Important Rules\n\n- **Dedup before writing.** Always check what exists in the DB before proposing new writes. Use `upsert_entity` which handles this automatically for entities.\n- **Don't read every file.** For doc inventory, just register the file — don't parse 130KB HTML files to extract content. That's what `\u002Fbrain-update` is for (conversation-driven).\n- **Date everything.** Decisions and events need dates. Parse from the source if available, fall back to file modification date, then today.\n- **Memory files are structured.** They have frontmatter — use the `type` field to decide what to extract.\n- **Manifest tracks scan state.** Always run `scan-update` after writes so the next scan is incremental.\n","# \u002Fbrain:init --- Initialize Project Brain\n\nSets up a new `project_brain.db` in the current working directory and bootstraps it from existing project knowledge.\n\n## Procedure\n\n### Step 1: Check existing state\n\nRun:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py info\n```\n\n- If **no DB exists** → proceed to Step 2 (full init)\n- If **DB exists with project(s)** → skip to Step 3 (scan only). Tell user: \"Brain already initialized. Running scan for new\u002Fchanged files...\"\n\n### Step 2: Create the database and project record\n\nRun:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py init\n```\n\nAsk the user:\n- **Project name** (e.g., \"My Project A\", \"My Project B\")\n- **Slug** (short URL-safe identifier, e.g., \"my-project-a\", \"my-project-b\")\n- **Description** (one-liner)\n\nThen run:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py add-project \"{name}\" --slug {slug} --desc \"{description}\"\n```\n\nIf the project has sub-scopes (like ProjectA-Phase1 and ProjectA-Phase2 under one umbrella), ask if the user wants multiple project records.\n\n### Step 3: Scan the project folder\n\nRun the scanner to discover what's available:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py scan\n```\n\nThis returns a JSON report with:\n- **manifest_diff**: new\u002Fchanged\u002Funchanged file counts, whether this is the first scan\n- **files_to_process**: paths of new or changed files\n- **knowledge_sources**: which CLAUDE.local.md, memory files, docs, and emails were found\n\nShow the user a summary:\n```\nFOLDER SCAN\n===========\nFirst scan:     yes\u002Fno\nFiles found:    NN total (NN new, NN changed, NN unchanged)\n\nKnowledge sources detected:\n  CLAUDE.local.md:  found \u002F not found\n  CLAUDE.md:        found \u002F not found\n  Memory files:     N files (list names)\n  Documents:        N files in docs\u002F\n  Emails:           N files in emails\u002F\n  Reference docs:   N files\n```\n\nIf nothing to process (all unchanged): \"Everything up to date. No new knowledge to extract.\" → done.\n\n### Step 4: Extract knowledge from sources (Claude-driven)\n\nProcess sources in **priority order**. For each source, read the file, extract structured knowledge, and collect proposed writes. Do NOT write to the brain yet — collect everything first.\n\n#### Priority 1: CLAUDE.local.md\nIf found, read the full file. Extract:\n- **Sections like \"Key Decisions\"** → `decisions` (with date, decision text, decided_by if mentioned)\n- **People mentioned by name** → `person` entities (with metadata like role, email, team if mentioned)\n- **Systems\u002Ftools mentioned** → `system` entities (e.g., Snowflake, Postgres, Datadog)\n- **Teams mentioned** → `team` entities\n- **Folder structure sections** → `document` entities for key docs\n- **Recent Changes entries** → `events` (with date, type, title)\n\n#### Priority 2: Memory files (~\u002F.claude\u002Fprojects\u002F...\u002Fmemory\u002F*.md)\nEach memory file has frontmatter (name, description, type) and content. Read each file:\n- **project type memories** → `decisions` or context to enrich existing entities\n- **feedback type memories** → skip (these are Claude behavior guidance, not project knowledge)\n- **reference type memories** → `system` or `document` entities with metadata\n\n#### Priority 3: Document inventory\nFor each file in docs\u002F, emails\u002F, and Reference Doc\u002F:\n- Create a `document` entity with metadata: `{\"path\": \"relative\u002Fpath\", \"type\": \"doc|email|reference\", \"size\": N}`\n- Use the filename (cleaned) as the entity name\n- Do NOT read the full content of every file — just register them in the inventory\n\n#### Priority 4: CLAUDE.md (project-level, if exists)\nSame extraction as CLAUDE.local.md but lower priority (may overlap).\n\n### Step 5: Present extraction summary\n\nShow proposed writes:\n```\nBRAIN BOOTSTRAP SUMMARY\n========================\nProject: {name} ({slug})\n\nFrom CLAUDE.local.md:\n  Entities:    N (list: name [type])\n  Decisions:   N (list: short text)\n  Events:      N (list: title)\n\nFrom memory files:\n  Decisions:   N (list: short text)\n  Entities:    N (list: name [type])\n\nDocument inventory:\n  Documents:   N (list: filename [doc|email|reference])\n\nTotal proposed writes: NN\n```\n\nAsk: **\"Write all to brain? [Y\u002Fn\u002Fadjust]\"**\n\n### Step 6: Execute writes\n\nOn confirmation, write in this order using Python:\n```python\nimport sys\nsys.path.insert(0, '$HOME\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts')\nfrom brain.schema import get_db\nfrom brain.operations import *\n```\n\n1. **Entities** — use `upsert_entity` (idempotent, safe to re-run)\n2. **Relationships** — use `create_relationship` (also idempotent)\n3. **Decisions** — use `create_decision` (check for duplicates by matching decision text before inserting)\n4. **Events** — use `create_event` (check for duplicates by matching title + date)\n5. **Document entities** — use `upsert_entity` with type=\"document\"\n\nAfter all writes, sync to MemPalace and brain.json:\n```python\nfrom brain.memory_bridge import full_sync\nfull_sync(\"project_brain.db\", project_slug)\n```\n\nAfter writes complete, update the manifest:\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fbrain\u002Fscripts\u002Fbrain\u002Fbrain_cli.py scan-update\n```\n\n### Step 7: Report\n\n```\nBRAIN INITIALIZED\n=================\nDB:            {path}\u002Fproject_brain.db\nProject:       {name} ({slug})\nSchema:        v1 (11 tables)\n\nBootstrapped from existing knowledge:\n  Entities:      +N (total: N)\n  Decisions:     +N (total: N)\n  Events:        +N (total: N)\n  Documents:     +N (total: N)\n  Relationships: +N (total: N)\n\nManifest updated: N files tracked\n\nNext: Run \u002Fbrain-update at end of session, or \u002Fbrain-rescan when files change.\n```\n\n### Step 8: Generate knowledge articles\n\nAfter completing brain writes (Step 6) and confirming the manifest is updated (Step 6\nscan-update), initialize the knowledge engine for this project.\n\n**First, register the project with the knowledge engine:**\n\n```python\nimport sys, os\nsys.path.insert(0, os.path.expanduser(\"~\u002F.coco\u002Fknowledge\"))\nfrom engine import KnowledgeEngine\n\nengine = KnowledgeEngine()\nengine.register_project(\"{slug}\", os.path.abspath(\"project_brain.db\"))\n```\n\nThis is required before the cron can harvest the project. (FIX M1: register_project\nmust be called before running any cron phases.)\n\n**Then, bootstrap article generation:**\n\n```python\nengine.full_refresh(\"{slug}\")\n```\n\nOr equivalently via CLI:\n\n```bash\npython3 ~\u002F.coco\u002Fknowledge\u002Fcron.py --run --project {slug} --phases 2,3,5\n```\n\nThis runs:\n- Phase 2 (harvest evidence from the brain DB you just populated + infer relationships)\n- Phase 3 (generate articles for all entities — first run will generate all)\n- Phase 5 (FTS5 index the new articles)\n\nShow the user:\n```\nKNOWLEDGE ENGINE\n================\nArticles generated:  N\nFTS5 indexed:        N\nEstimated cost:      $0.XXX\n\nArticles written to: ~\u002F.coco\u002Fknowledge\u002Farticles\u002F\nSearch with: \u002Fbrain-wiki search \"{project_name}\"\n```\n\n**Skip this step silently if:**\n- `~\u002F.coco\u002Fknowledge\u002F` does not exist (knowledge engine not installed)\n- The `cron.py` call fails for any reason (non-blocking — brain init still succeeds)\n\n---\n\n## Important Rules\n\n- **Dedup before writing.** Always check what exists in the DB before proposing new writes. Use `upsert_entity` which handles this automatically for entities.\n- **Don't read every file.** For doc inventory, just register the file — don't parse 130KB HTML files to extract content. That's what `\u002Fbrain-update` is for (conversation-driven).\n- **Date everything.** Decisions and events need dates. Parse from the source if available, fall back to file modification date, then today.\n- **Memory files are structured.** They have frontmatter — use the `type` field to decide what to extract.\n- **Manifest tracks scan state.** Always run `scan-update` after writes so the next scan is incremental.\n",{"name":5,"description":7},"main","cd89f013b617f7eea982a9bbc60e992974fda2aa","systems\u002Fbrain\u002Fskills\u002Fbrain-init",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:init\"",{"tool":64,"command":65},"bunx","bunx skills add coco-research\u002Fcoco --skill \"brain:init\"",{"tool":67,"command":68},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill \"brain:init\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fbrain\u002Fskills\u002Fbrain-init\u002FSKILL.md",true,[],[73,96,106,124,158,177],{"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},[81,82,83,84,85,86,37,87,88,89,90,91,41,92,93,94,95],"super","trading super intelligence","intelligence","trading","validator","personas","composites","studio","team","across","world","gated","2026","lm studio","local-first",{"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":103,"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",[102],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[104,81,105,83,85,86,37,87,88,89,90,91,41,92,93,94,95],"strategy","strategy super intelligence",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":118,"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",[112,113],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[119,81,120,121,122,83,85,86,37,87,123,88,89,90,91,41,92,93,94,95],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":143,"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",[130,133,136,137,140],{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":134,"categoryName":135,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":138,"categoryName":139,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":141,"categoryName":142,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000032","设计师",[144,145,83,146,81,147,148,149,150,151,152,89,90,153,154,93,24,155,156,157],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","craft","metrics","trust",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":166,"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",[164,165],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},[167,81,168,83,169,170,157,171,86,172,173,174,104,89,90,175,121,176,93,24],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":184,"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",[183],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[185,81,186,187,83,170,157,188,189,86,190,191,104,89,90,192,193,194,195,93],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]