[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71K58D4ZR4JB01DYF25536M":3,"skill-same:01M71K58D4ZR4JB01DYF25536M":77},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M71K58D4ZR4JB01DYF25536M","gsd-intel",null,"Use when the user asks what the codebase intel knows, or runs \u002Fgsd-intel query, status, diff, or refresh. Queries or rebuilds the .planning\u002Fintel\u002F files, and stops with a disabled message when intel is off in .planning\u002Fconfig.json.","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\u002Fgsd\u002Fskills\u002Fgsd-intel\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"intel","gsd","gsd intel","files","when","with","message","query","task","what the","queries","config","diff","use","refresh","read","json","Bash","planning","status","2026-11-10 10:12:30",false,"---\nname: gsd-intel\ndescription: \"Use when the user asks what the codebase intel knows, or runs \u002Fgsd-intel query, status, diff, or refresh. Queries or rebuilds the .planning\u002Fintel\u002F files, and stops with a disabled message when intel is off in .planning\u002Fconfig.json.\"\nargument-hint: \"[query \u003Cterm>|status|diff|refresh]\"\nallowed-tools:\n  - Read\n  - Bash\n  - Task\n---\n\n\n**STOP -- DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's command system. Using the Read tool on this file wastes tokens. Begin executing Step 0 immediately.**\n\n## Step 0 -- Banner\n\n**Before ANY tool calls**, display this banner:\n\n```\nGSD > INTEL\n```\n\nThen proceed to Step 1.\n\n## Step 1 -- Config Gate\n\nCheck if intel is enabled by reading `.planning\u002Fconfig.json` directly using the Read tool.\n\n**DO NOT use the gsd-tools config get-value command** -- it hard-exits on missing keys.\n\n1. Read `.planning\u002Fconfig.json` using the Read tool\n2. If the file does not exist: display the disabled message below and **STOP**\n3. Parse the JSON content. Check if `config.intel && config.intel.enabled === true`\n4. If `intel.enabled` is NOT explicitly `true`: display the disabled message below and **STOP**\n5. If `intel.enabled` is `true`: proceed to Step 2\n\n**Disabled message:**\n\n```\nGSD > INTEL\n\nIntel system is disabled. To activate:\n\n  node $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs config-set intel.enabled true\n\nThen run \u002Fgsd-intel refresh to build the initial index.\n```\n\n---\n\n## Step 2 -- Parse Argument\n\nParse `$ARGUMENTS` to determine the operation mode:\n\n| Argument | Action |\n|----------|--------|\n| `query \u003Cterm>` | Run inline query (Step 2a) |\n| `status` | Run inline status check (Step 2b) |\n| `diff` | Run inline diff check (Step 2c) |\n| `refresh` | Spawn intel-updater agent (Step 3) |\n| No argument or unknown | Show usage message |\n\n**Usage message** (shown when no argument or unrecognized argument):\n\n```\nGSD > INTEL\n\nUsage: \u002Fgsd-intel \u003Cmode>\n\nModes:\n  query \u003Cterm>  Search intel files for a term\n  status        Show intel file freshness and staleness\n  diff          Show changes since last snapshot\n  refresh       Rebuild all intel files from codebase analysis\n```\n\n### Step 2a -- Query\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel query \u003Cterm>\n```\n\nParse the JSON output and display results:\n- If the output contains `\"disabled\": true`, display the disabled message from Step 1 and **STOP**\n- If no matches found, display: `No intel matches for '\u003Cterm>'. Try \u002Fgsd-intel refresh to build the index.`\n- Otherwise, display matching entries grouped by intel file\n\n**STOP** after displaying results. Do not spawn an agent.\n\n### Step 2b -- Status\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel status\n```\n\nParse the JSON output and display each intel file with:\n- File name\n- Last `updated_at` timestamp\n- STALE or FRESH status (stale if older than 24 hours or missing)\n\n**STOP** after displaying status. Do not spawn an agent.\n\n### Step 2c -- Diff\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel diff\n```\n\nParse the JSON output and display:\n- Added entries since last snapshot\n- Removed entries since last snapshot\n- Changed entries since last snapshot\n\nIf no snapshot exists, suggest running `refresh` first.\n\n**STOP** after displaying diff. Do not spawn an agent.\n\n---\n\n## Step 3 -- Refresh (Agent Spawn)\n\nDisplay before spawning:\n\n```\nGSD > Spawning intel-updater agent to analyze codebase...\n```\n\nSpawn a Task:\n\n```\nTask(\n  description=\"Refresh codebase intelligence files\",\n  prompt=\"You are the gsd-intel-updater agent. Your job is to analyze this codebase and write\u002Fupdate intelligence files in .planning\u002Fintel\u002F.\n\nProject root: ${CWD}\ngsd-tools path: $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs\n\nInstructions:\n1. Analyze the codebase structure, dependencies, APIs, and architecture\n2. Write JSON intel files to .planning\u002Fintel\u002F (stack.json, api-map.json, dependency-graph.json, file-roles.json, arch-decisions.json)\n3. Each file must have a _meta object with updated_at timestamp\n4. Use gsd-tools intel extract-exports \u003Cfile> to analyze source files\n5. Use gsd-tools intel patch-meta \u003Cfile> to update timestamps after writing\n6. Use gsd-tools intel validate to check your output\n\nWhen complete, output: ## INTEL UPDATE COMPLETE\nIf something fails, output: ## INTEL UPDATE FAILED with details.\"\n)\n```\n\nWait for the agent to complete.\n\n---\n\n## Step 4 -- Post-Refresh Summary\n\nAfter the agent completes, run:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel status\n```\n\nDisplay a summary showing:\n- Which intel files were written or updated\n- Last update timestamps\n- Overall health of the intel index\n\n---\n\n## Anti-Patterns\n\n1. DO NOT spawn an agent for query\u002Fstatus\u002Fdiff operations -- these are inline CLI calls\n2. DO NOT modify intel files directly -- the agent handles writes during refresh\n3. DO NOT skip the config gate check\n4. DO NOT use the gsd-tools config get-value CLI for the config gate -- it exits on missing keys\n","**STOP -- DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's command system. Using the Read tool on this file wastes tokens. Begin executing Step 0 immediately.**\n\n## Step 0 -- Banner\n\n**Before ANY tool calls**, display this banner:\n\n```\nGSD > INTEL\n```\n\nThen proceed to Step 1.\n\n## Step 1 -- Config Gate\n\nCheck if intel is enabled by reading `.planning\u002Fconfig.json` directly using the Read tool.\n\n**DO NOT use the gsd-tools config get-value command** -- it hard-exits on missing keys.\n\n1. Read `.planning\u002Fconfig.json` using the Read tool\n2. If the file does not exist: display the disabled message below and **STOP**\n3. Parse the JSON content. Check if `config.intel && config.intel.enabled === true`\n4. If `intel.enabled` is NOT explicitly `true`: display the disabled message below and **STOP**\n5. If `intel.enabled` is `true`: proceed to Step 2\n\n**Disabled message:**\n\n```\nGSD > INTEL\n\nIntel system is disabled. To activate:\n\n  node $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs config-set intel.enabled true\n\nThen run \u002Fgsd-intel refresh to build the initial index.\n```\n\n---\n\n## Step 2 -- Parse Argument\n\nParse `$ARGUMENTS` to determine the operation mode:\n\n| Argument | Action |\n|----------|--------|\n| `query \u003Cterm>` | Run inline query (Step 2a) |\n| `status` | Run inline status check (Step 2b) |\n| `diff` | Run inline diff check (Step 2c) |\n| `refresh` | Spawn intel-updater agent (Step 3) |\n| No argument or unknown | Show usage message |\n\n**Usage message** (shown when no argument or unrecognized argument):\n\n```\nGSD > INTEL\n\nUsage: \u002Fgsd-intel \u003Cmode>\n\nModes:\n  query \u003Cterm>  Search intel files for a term\n  status        Show intel file freshness and staleness\n  diff          Show changes since last snapshot\n  refresh       Rebuild all intel files from codebase analysis\n```\n\n### Step 2a -- Query\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel query \u003Cterm>\n```\n\nParse the JSON output and display results:\n- If the output contains `\"disabled\": true`, display the disabled message from Step 1 and **STOP**\n- If no matches found, display: `No intel matches for '\u003Cterm>'. Try \u002Fgsd-intel refresh to build the index.`\n- Otherwise, display matching entries grouped by intel file\n\n**STOP** after displaying results. Do not spawn an agent.\n\n### Step 2b -- Status\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel status\n```\n\nParse the JSON output and display each intel file with:\n- File name\n- Last `updated_at` timestamp\n- STALE or FRESH status (stale if older than 24 hours or missing)\n\n**STOP** after displaying status. Do not spawn an agent.\n\n### Step 2c -- Diff\n\nRun:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel diff\n```\n\nParse the JSON output and display:\n- Added entries since last snapshot\n- Removed entries since last snapshot\n- Changed entries since last snapshot\n\nIf no snapshot exists, suggest running `refresh` first.\n\n**STOP** after displaying diff. Do not spawn an agent.\n\n---\n\n## Step 3 -- Refresh (Agent Spawn)\n\nDisplay before spawning:\n\n```\nGSD > Spawning intel-updater agent to analyze codebase...\n```\n\nSpawn a Task:\n\n```\nTask(\n  description=\"Refresh codebase intelligence files\",\n  prompt=\"You are the gsd-intel-updater agent. Your job is to analyze this codebase and write\u002Fupdate intelligence files in .planning\u002Fintel\u002F.\n\nProject root: ${CWD}\ngsd-tools path: $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs\n\nInstructions:\n1. Analyze the codebase structure, dependencies, APIs, and architecture\n2. Write JSON intel files to .planning\u002Fintel\u002F (stack.json, api-map.json, dependency-graph.json, file-roles.json, arch-decisions.json)\n3. Each file must have a _meta object with updated_at timestamp\n4. Use gsd-tools intel extract-exports \u003Cfile> to analyze source files\n5. Use gsd-tools intel patch-meta \u003Cfile> to update timestamps after writing\n6. Use gsd-tools intel validate to check your output\n\nWhen complete, output: ## INTEL UPDATE COMPLETE\nIf something fails, output: ## INTEL UPDATE FAILED with details.\"\n)\n```\n\nWait for the agent to complete.\n\n---\n\n## Step 4 -- Post-Refresh Summary\n\nAfter the agent completes, run:\n\n```bash\nnode $HOME\u002F.claude\u002Fget-shit-done\u002Fbin\u002Fgsd-tools.cjs intel status\n```\n\nDisplay a summary showing:\n- Which intel files were written or updated\n- Last update timestamps\n- Overall health of the intel index\n\n---\n\n## Anti-Patterns\n\n1. DO NOT spawn an agent for query\u002Fstatus\u002Fdiff operations -- these are inline CLI calls\n2. DO NOT modify intel files directly -- the agent handles writes during refresh\n3. DO NOT skip the config gate check\n4. DO NOT use the gsd-tools config get-value CLI for the config gate -- it exits on missing keys\n",{"name":5,"description":7,"allowed-tools":49,"argument-hint":52},[50,41,51],"Read","Task","[query \u003Cterm>|status|diff|refresh]","main","cd89f013b617f7eea982a9bbc60e992974fda2aa","systems\u002Fgsd\u002Fskills\u002Fgsd-intel",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":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add coco-research\u002Fcoco --skill gsd-intel",{"tool":69,"command":70},"bunx","bunx skills add coco-research\u002Fcoco --skill gsd-intel",{"tool":72,"command":73},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill gsd-intel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fgsd\u002Fskills\u002Fgsd-intel\u002FSKILL.md",true,[],[78,103,113,131,166,185],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":85,"publishedAt":44},"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",[84],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"super","trading super intelligence","intelligence","trading","validator","personas","local","composites","studio","team","across","world","first","gated","2026","lm studio","local-first",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":44},"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",[109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[111,86,112,88,90,91,92,93,94,95,96,97,98,99,100,101,102],"strategy","strategy super intelligence",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":44},"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",[119,120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[126,86,127,128,129,88,90,91,92,93,130,94,95,96,97,98,99,100,101,102],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":150,"publishedAt":44},"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",[137,140,143,144,147],{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":141,"categoryName":142,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":145,"categoryName":146,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":148,"categoryName":149,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000032","设计师",[151,152,88,153,86,154,155,156,157,158,159,95,96,160,161,100,162,163,164,165],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":174,"publishedAt":44},"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",[172,173],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[175,86,176,88,177,178,165,179,91,180,181,182,111,95,96,183,128,184,100,162],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":44},"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",[191],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[193,86,194,195,88,178,165,196,197,91,198,199,111,95,96,200,201,202,203,100],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]