[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JVHSMN47FNGWTR7RGZG08":3,"skill-same:01M71JVHSMN47FNGWTR7RGZG08":71},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M71JVHSMN47FNGWTR7RGZG08","pmstudio-sync",null,"Use when linked docs drift, when a source file changes and downstream PRDs, decks, or notes must follow, or when a .sync-report.md exists. Diffs the proposed edits, applies them only after approval, and never overwrites a target file.","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\u002Fskills\u002Fdoc-sync\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"pmstudio sync","sync","approval","docs","report","changes","file","use","target","source","notes","drift","when","only","pm","diffs","docs drift","never","2026-11-10 10:12:30",false,"---\nname: pmstudio-sync\ndescription: \"Use when linked docs drift, when a source file changes and downstream PRDs, decks, or notes must follow, or when a .sync-report.md exists. Diffs the proposed edits, applies them only after approval, and never overwrites a target file.\"\ndomain: pm\n---\n\n# Doc Sync — Cascading Document Updater\n\n## What This Skill Does\n\nMaintains consistency across a documentation ecosystem where one source change (e.g., a new meeting note) should cascade updates to multiple downstream documents (PRD, presentation, project memory).\n\n**This is NOT a background watcher.** This skill is the Claude-side processor that:\n1. Reads a sync report or detects changes directly\n2. Extracts actionable content from new\u002Fmodified source files\n3. Proposes specific edits to each downstream target\n4. Applies changes only after user approval\n\n## Prerequisites\n\n### Infrastructure (one-time setup)\n\nThe persistent detection layer runs outside Claude Code via `\u002Fpm:sync-init`:\n\n| Component | Path | Purpose |\n|-----------|------|---------|\n| Orchestrator | `~\u002F.claude\u002Fscripts\u002Fproject-sync-orchestrator.sh` | Email search + file detection + report generation |\n| launchd agent | `~\u002FLibrary\u002FLaunchAgents\u002Fcom.claude.project-sync.\u003Cname>.plist` | Background scheduler (every 2 hours) |\n| State dir | `~\u002F.claude\u002Fstate\u002F\u003Cproject-name>\u002F` | Logs, timestamps, cached config (outside OneDrive) |\n\n### Per-Project Config\n\nEach project needs `.sync-watch.json` in its root:\n\n```json\n{\n  \"project_name\": \"My Project\",\n  \"watch_dirs\": [\"docs\u002Fmeeting-notes\", \"docs\u002Fresearch\"],\n  \"target_docs\": {\n    \"tier1\": [\n      {\n        \"path\": \"docs\u002FPRD.html\",\n        \"name\": \"Product Requirements\",\n        \"update_from\": [\"meeting-notes\", \"research\"],\n        \"what\": \"Requirements, user stories, decisions\"\n      }\n    ],\n    \"tier2\": [\n      {\n        \"path\": \"docs\u002Fpresentation.html\",\n        \"name\": \"Stakeholder Deck\",\n        \"update_from\": [\"meeting-notes\"],\n        \"what\": \"Stakeholder updates, timeline changes\"\n      }\n    ]\n  },\n  \"ignore_patterns\": [\".*\", \"*.tmp\", \"~$*\"],\n  \"file_types\": [\".md\", \".html\", \".docx\", \".xlsx\", \".pdf\"]\n}\n```\n\n## Invocation\n\n### Automatic (via session hook)\nWhen you start a Claude Code session in a watched project with pending changes:\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n SYNC WATCHER ► 3 new\u002Fmodified file(s) detected\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSay \"process sync report\" to review and apply updates.\n```\n\n### Manual\n- `\u002Fdoc-sync` — check for changes now and process\n- `\u002Fdoc-sync path\u002Fto\u002Fnew-file.md` — process a specific source file\n- `process sync report` — process a pending `.sync-report.md`\n\n## Process\n\n### Step 1: Detect Changes\n\n**If `.sync-report.md` exists:** Read it — it lists all changed files with timestamps.\n\n**If no report (manual invocation):**\n```bash\n!`bash ~\u002F.claude\u002Fscripts\u002Fproject-sync-orchestrator.sh \"$(pwd)\"`\n```\nThen read the generated `.sync-report.md` (written to project root or `~\u002F.claude\u002Fstate\u002F\u003Cproject-name>\u002Fsync-report.md`).\n\n**If a specific file was passed as `$ARGUMENTS`:** Use that file as the sole source.\n\n**If no changes detected:** Report \"All documents are in sync.\" and stop.\n\n### Step 2: Read Source Files\n\nFor each new\u002Fmodified file detected:\n\n1. **Skip binaries** (`.docx`, `.xlsx`, `.pptx`, `.pdf`) — note them but don't read. Tell user: \"Binary file detected — paste key content or convert to text.\"\n2. **Read text files** (`.md`, `.html`) in full\n3. **Extract structured data** from each:\n\n```\nFor each source file, extract:\n- NEW STAKEHOLDERS: Name, Role, Email, Group\n- NEW DECISIONS: What was decided, by whom, date, impact\n- NEW REQUIREMENTS: Functional\u002Fnon-functional, priority, acceptance criteria\n- NEW ACTION ITEMS: Owner, deadline, status\n- NEW ARCHITECTURE: Design changes, module updates, integration changes\n- NEW RISKS: Description, impact, mitigation\n- VERSION CHANGES: What changed from previous version\n```\n\n### Step 3: Read Config & Map Dependencies\n\nRead `.sync-watch.json` to determine which target docs need which types of updates.\n\nFor each target doc in `tier1` and `tier2`:\n- Check if any source file matches its `update_from` patterns\n- If yes → read the target doc to understand current state\n- Identify exactly WHERE in the target doc the new content should go\n\n### Step 4: Propose Updates\n\nPresent a structured proposal — DO NOT edit anything yet:\n\n```markdown\n## Sync Proposal\n\n### Source: Meeting-Notes-2026-03-17.md\n**New content extracted:**\n- 2 new stakeholders (Jane Doe, John Smith)\n- 1 decision (moved go-live to Q4)\n- 3 action items\n\n### Updates Needed:\n\n**1. PRD.html** (Tier 1)\n- Section 05 Stakeholders: Add Jane Doe (Tax Director), John Smith (IT Lead)\n- Section 12 Timeline: Update go-live from Q3 → Q4\n- Change log: Add v1.1 entry\n- [Show exact diff preview for each change]\n\n**2. Presentation.html** (Tier 1)\n- Slide 7 (Team): Add 2 stakeholder cards\n- Slide 12 (Timeline): Update milestone date\n- [Show exact diff preview]\n\n**3. CLAUDE.local.md** (Tier 1)\n- Recent Changes: Add dated entry\n- [Show exact content to append]\n\n**4. Stakeholder-Directory.xlsx** (Tier 2)\n- SKIP — binary file, manual update needed\n```\n\n### Step 5: Get Approval\n\nAsk user:\n- \"Apply all updates?\" → proceed with all\n- \"Apply selectively?\" → let user pick which targets\n- \"Skip for now?\" → clean up report, do nothing\n- User may also request modifications to the proposal\n\n### Step 6: Apply Updates\n\nFor each approved target:\n1. **Read the target file** (always re-read before editing — it may have changed)\n2. **Apply edits** using the Edit tool (not Write — preserve unchanged content)\n3. **Verify** the edit was applied correctly\n4. **Log** what was changed\n\n### Step 7: Clean Up & Update Memory\n\nAfter all edits applied:\n1. **Delete `.sync-report.md`** (consumed)\n2. **Update `_temp\u002F.last-sync-check`** timestamp\n3. **Update `CLAUDE.local.md`** Recent Changes section with a dated entry summarizing what was synced\n4. **Report** summary to user:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n DOC SYNC ► COMPLETE ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSource files processed: 3\nDocuments updated: 4\n  ✓ PRD.html — 3 edits (stakeholders, timeline, changelog)\n  ✓ Presentation.html — 2 edits (team slide, timeline)\n  ✓ CLAUDE.local.md — 1 edit (recent changes)\n  ⚠ Stakeholder-Directory.xlsx — skipped (binary)\n\nManual follow-up needed:\n  - Update Stakeholder-Directory.xlsx with 2 new contacts\n```\n\n## Critical Rules\n\n1. **NEVER edit without approval.** Always show the proposal first. The user must explicitly approve.\n2. **NEVER fabricate content.** Only extract what's actually written in source files. If a meeting note doesn't mention a stakeholder's email, don't guess it.\n3. **NEVER overwrite — always append\u002Finsert.** Use Edit tool with precise `old_string` matching. Never rewrite entire files.\n4. **ALWAYS read target docs before editing.** They may have been modified since the report was generated.\n5. **ALWAYS preserve existing formatting.** Match the target doc's style (HTML structure, CSS classes, indentation patterns).\n6. **Binary files are report-only.** Flag them for manual update, don't attempt to modify.\n7. **Version bumps:** If the target doc has a version badge\u002Fnumber, increment it and add a changelog entry.\n\n## Adding This to a New Project\n\n1. Create `.sync-watch.json` in the project root (use template above)\n2. Run `\u002Fpm:sync-init` to set up the launchd cron job\n3. Done — the background orchestrator runs every 2 hours and generates `.sync-report.md` when changes are detected\n\n## Dependency Graph Pattern\n\nFor complex projects, document the update cascade in `.sync-watch.json`:\n\n```\nMeeting Notes ──→ PRD ──→ PRD Presentation\n       │                         │\n       ├──→ Main Presentation ←──┘\n       │\n       └──→ CLAUDE.local.md ←── (all changes)\n```\n\nThis ensures that when a meeting note creates a PRD change, and that PRD change should also update the presentation, the full cascade is handled in one sync pass.\n","# Doc Sync — Cascading Document Updater\n\n## What This Skill Does\n\nMaintains consistency across a documentation ecosystem where one source change (e.g., a new meeting note) should cascade updates to multiple downstream documents (PRD, presentation, project memory).\n\n**This is NOT a background watcher.** This skill is the Claude-side processor that:\n1. Reads a sync report or detects changes directly\n2. Extracts actionable content from new\u002Fmodified source files\n3. Proposes specific edits to each downstream target\n4. Applies changes only after user approval\n\n## Prerequisites\n\n### Infrastructure (one-time setup)\n\nThe persistent detection layer runs outside Claude Code via `\u002Fpm:sync-init`:\n\n| Component | Path | Purpose |\n|-----------|------|---------|\n| Orchestrator | `~\u002F.claude\u002Fscripts\u002Fproject-sync-orchestrator.sh` | Email search + file detection + report generation |\n| launchd agent | `~\u002FLibrary\u002FLaunchAgents\u002Fcom.claude.project-sync.\u003Cname>.plist` | Background scheduler (every 2 hours) |\n| State dir | `~\u002F.claude\u002Fstate\u002F\u003Cproject-name>\u002F` | Logs, timestamps, cached config (outside OneDrive) |\n\n### Per-Project Config\n\nEach project needs `.sync-watch.json` in its root:\n\n```json\n{\n  \"project_name\": \"My Project\",\n  \"watch_dirs\": [\"docs\u002Fmeeting-notes\", \"docs\u002Fresearch\"],\n  \"target_docs\": {\n    \"tier1\": [\n      {\n        \"path\": \"docs\u002FPRD.html\",\n        \"name\": \"Product Requirements\",\n        \"update_from\": [\"meeting-notes\", \"research\"],\n        \"what\": \"Requirements, user stories, decisions\"\n      }\n    ],\n    \"tier2\": [\n      {\n        \"path\": \"docs\u002Fpresentation.html\",\n        \"name\": \"Stakeholder Deck\",\n        \"update_from\": [\"meeting-notes\"],\n        \"what\": \"Stakeholder updates, timeline changes\"\n      }\n    ]\n  },\n  \"ignore_patterns\": [\".*\", \"*.tmp\", \"~$*\"],\n  \"file_types\": [\".md\", \".html\", \".docx\", \".xlsx\", \".pdf\"]\n}\n```\n\n## Invocation\n\n### Automatic (via session hook)\nWhen you start a Claude Code session in a watched project with pending changes:\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n SYNC WATCHER ► 3 new\u002Fmodified file(s) detected\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSay \"process sync report\" to review and apply updates.\n```\n\n### Manual\n- `\u002Fdoc-sync` — check for changes now and process\n- `\u002Fdoc-sync path\u002Fto\u002Fnew-file.md` — process a specific source file\n- `process sync report` — process a pending `.sync-report.md`\n\n## Process\n\n### Step 1: Detect Changes\n\n**If `.sync-report.md` exists:** Read it — it lists all changed files with timestamps.\n\n**If no report (manual invocation):**\n```bash\n!`bash ~\u002F.claude\u002Fscripts\u002Fproject-sync-orchestrator.sh \"$(pwd)\"`\n```\nThen read the generated `.sync-report.md` (written to project root or `~\u002F.claude\u002Fstate\u002F\u003Cproject-name>\u002Fsync-report.md`).\n\n**If a specific file was passed as `$ARGUMENTS`:** Use that file as the sole source.\n\n**If no changes detected:** Report \"All documents are in sync.\" and stop.\n\n### Step 2: Read Source Files\n\nFor each new\u002Fmodified file detected:\n\n1. **Skip binaries** (`.docx`, `.xlsx`, `.pptx`, `.pdf`) — note them but don't read. Tell user: \"Binary file detected — paste key content or convert to text.\"\n2. **Read text files** (`.md`, `.html`) in full\n3. **Extract structured data** from each:\n\n```\nFor each source file, extract:\n- NEW STAKEHOLDERS: Name, Role, Email, Group\n- NEW DECISIONS: What was decided, by whom, date, impact\n- NEW REQUIREMENTS: Functional\u002Fnon-functional, priority, acceptance criteria\n- NEW ACTION ITEMS: Owner, deadline, status\n- NEW ARCHITECTURE: Design changes, module updates, integration changes\n- NEW RISKS: Description, impact, mitigation\n- VERSION CHANGES: What changed from previous version\n```\n\n### Step 3: Read Config & Map Dependencies\n\nRead `.sync-watch.json` to determine which target docs need which types of updates.\n\nFor each target doc in `tier1` and `tier2`:\n- Check if any source file matches its `update_from` patterns\n- If yes → read the target doc to understand current state\n- Identify exactly WHERE in the target doc the new content should go\n\n### Step 4: Propose Updates\n\nPresent a structured proposal — DO NOT edit anything yet:\n\n```markdown\n## Sync Proposal\n\n### Source: Meeting-Notes-2026-03-17.md\n**New content extracted:**\n- 2 new stakeholders (Jane Doe, John Smith)\n- 1 decision (moved go-live to Q4)\n- 3 action items\n\n### Updates Needed:\n\n**1. PRD.html** (Tier 1)\n- Section 05 Stakeholders: Add Jane Doe (Tax Director), John Smith (IT Lead)\n- Section 12 Timeline: Update go-live from Q3 → Q4\n- Change log: Add v1.1 entry\n- [Show exact diff preview for each change]\n\n**2. Presentation.html** (Tier 1)\n- Slide 7 (Team): Add 2 stakeholder cards\n- Slide 12 (Timeline): Update milestone date\n- [Show exact diff preview]\n\n**3. CLAUDE.local.md** (Tier 1)\n- Recent Changes: Add dated entry\n- [Show exact content to append]\n\n**4. Stakeholder-Directory.xlsx** (Tier 2)\n- SKIP — binary file, manual update needed\n```\n\n### Step 5: Get Approval\n\nAsk user:\n- \"Apply all updates?\" → proceed with all\n- \"Apply selectively?\" → let user pick which targets\n- \"Skip for now?\" → clean up report, do nothing\n- User may also request modifications to the proposal\n\n### Step 6: Apply Updates\n\nFor each approved target:\n1. **Read the target file** (always re-read before editing — it may have changed)\n2. **Apply edits** using the Edit tool (not Write — preserve unchanged content)\n3. **Verify** the edit was applied correctly\n4. **Log** what was changed\n\n### Step 7: Clean Up & Update Memory\n\nAfter all edits applied:\n1. **Delete `.sync-report.md`** (consumed)\n2. **Update `_temp\u002F.last-sync-check`** timestamp\n3. **Update `CLAUDE.local.md`** Recent Changes section with a dated entry summarizing what was synced\n4. **Report** summary to user:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n DOC SYNC ► COMPLETE ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSource files processed: 3\nDocuments updated: 4\n  ✓ PRD.html — 3 edits (stakeholders, timeline, changelog)\n  ✓ Presentation.html — 2 edits (team slide, timeline)\n  ✓ CLAUDE.local.md — 1 edit (recent changes)\n  ⚠ Stakeholder-Directory.xlsx — skipped (binary)\n\nManual follow-up needed:\n  - Update Stakeholder-Directory.xlsx with 2 new contacts\n```\n\n## Critical Rules\n\n1. **NEVER edit without approval.** Always show the proposal first. The user must explicitly approve.\n2. **NEVER fabricate content.** Only extract what's actually written in source files. If a meeting note doesn't mention a stakeholder's email, don't guess it.\n3. **NEVER overwrite — always append\u002Finsert.** Use Edit tool with precise `old_string` matching. Never rewrite entire files.\n4. **ALWAYS read target docs before editing.** They may have been modified since the report was generated.\n5. **ALWAYS preserve existing formatting.** Match the target doc's style (HTML structure, CSS classes, indentation patterns).\n6. **Binary files are report-only.** Flag them for manual update, don't attempt to modify.\n7. **Version bumps:** If the target doc has a version badge\u002Fnumber, increment it and add a changelog entry.\n\n## Adding This to a New Project\n\n1. Create `.sync-watch.json` in the project root (use template above)\n2. Run `\u002Fpm:sync-init` to set up the launchd cron job\n3. Done — the background orchestrator runs every 2 hours and generates `.sync-report.md` when changes are detected\n\n## Dependency Graph Pattern\n\nFor complex projects, document the update cascade in `.sync-watch.json`:\n\n```\nMeeting Notes ──→ PRD ──→ PRD Presentation\n       │                         │\n       ├──→ Main Presentation ←──┘\n       │\n       └──→ CLAUDE.local.md ←── (all changes)\n```\n\nThis ensures that when a meeting note creates a PRD change, and that PRD change should also update the presentation, the full cascade is handled in one sync pass.\n",{"name":5,"domain":38,"description":7},"main","cd89f013b617f7eea982a9bbc60e992974fda2aa","skills\u002Fdoc-sync",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":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add coco-research\u002Fcoco --skill pmstudio-sync",{"tool":63,"command":64},"bunx","bunx skills add coco-research\u002Fcoco --skill pmstudio-sync",{"tool":66,"command":67},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill pmstudio-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fdoc-sync\u002FSKILL.md",true,[],[72,97,107,125,160,179],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":79,"publishedAt":42},"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",[78],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96],"super","trading super intelligence","intelligence","trading","validator","personas","local","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":42},"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},[105,80,106,82,84,85,86,87,88,89,90,91,92,93,94,95,96],"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":42},"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",[120,80,121,122,123,82,84,85,86,87,124,88,89,90,91,92,93,94,95,96],"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":42},"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",[145,146,82,147,80,148,149,150,151,152,153,89,90,154,155,94,156,157,158,159],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":168,"publishedAt":42},"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",[166,167],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[169,80,170,82,171,172,159,173,85,174,175,176,105,89,90,177,122,178,94,156],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":186,"publishedAt":42},"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",[185],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[187,80,188,189,82,172,159,190,191,85,192,193,105,89,90,194,195,196,197,94],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]