[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWEEQFRQ0672Q83P9DFFYF":3,"skill-same:01M6NWEEQFRQ0672Q83P9DFFYF":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":28,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6NWEEQFRQ0672Q83P9DFFYF","skill-developer",null,"Meta-skill for creating and managing Claude Code skills","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fskill-developer\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39],"developer","skill developer","claude code skills","code","Meta","Bash","read","write","edit","meta-skill","for","2026-11-10 10:12:30",false,"---\nname: skill-developer\ndescription: Meta-skill for creating and managing Claude Code skills\nallowed-tools: [Bash, Read, Write, Edit]\n---\n\n# Skill Developer\n\nMeta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.\n\n## When to Use\n\n- \"Create a skill for X\"\n- \"Help me make a new skill\"\n- \"Turn this script into a skill\"\n- \"How do I create a skill?\"\n\n## Skill Structure\n\nSkills live in `.claude\u002Fskills\u002F\u003Cskill-name>\u002F`:\n\n```\n.claude\u002Fskills\u002Fmy-skill\u002F\n├── SKILL.md          # Required: Main skill definition\n├── scripts\u002F          # Optional: Supporting scripts\n└── templates\u002F        # Optional: Templates, examples\n```\n\n### SKILL.md Format\n\n```yaml\n---\nname: skill-name\ndescription: Brief description (shown in skill list)\nallowed-tools: [Bash, Read, Write]  # Optional: restrict tools\n---\n\n# Skill Name\n\n## When to Use\n[When Claude should discover this skill]\n\n## Instructions\n[Step-by-step instructions for Claude to follow]\n\n## Examples\n[Usage examples]\n```\n\n## Creating an MCP Pipeline Skill\n\nTo create a new MCP chain script and wrap it as a skill:\n\n### Step 1: Use the Template\n\nCopy the multi-tool-pipeline template:\n\n```bash\ncp $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmulti_tool_pipeline.py $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmy_pipeline.py\n```\n\nReference the template pattern:\n\n```bash\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Fmulti-tool-pipeline\u002FSKILL.md\ncat $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmulti_tool_pipeline.py\n```\n\n### Step 2: Customize the Script\n\nEdit your new script to chain the MCP tools you need:\n\n```python\nasync def main():\n    from runtime.mcp_client import call_mcp_tool\n    args = parse_args()\n\n    # Chain your MCP tools (serverName__toolName)\n    result1 = await call_mcp_tool(\"server1__tool1\", {\"param\": args.arg1})\n    result2 = await call_mcp_tool(\"server2__tool2\", {\"input\": result1})\n\n    print(result2)\n```\n\n### Step 2: Create the Skill\n\nCreate `.claude\u002Fskills\u002Fmy-pipeline\u002FSKILL.md`:\n\n```markdown\n---\nname: my-pipeline\ndescription: What the pipeline does\nallowed-tools: [Bash, Read]\n---\n\n# My Pipeline Skill\n\n## When to Use\n- [Trigger conditions]\n\n## Instructions\n\nRun the pipeline:\n\n\\`\\`\\`bash\nuv run python -m runtime.harness scripts\u002Fmy_pipeline.py --arg1 \"value\"\n\\`\\`\\`\n\n### Parameters\n- `--arg1`: Description\n\n## MCP Servers Required\n- server1: For tool1\n- server2: For tool2\n```\n\n### Step 3: Add Triggers (Optional)\n\nAdd to `.claude\u002Fskills\u002Fskill-rules.json`:\n\n```json\n{\n  \"skills\": {\n    \"my-pipeline\": {\n      \"type\": \"domain\",\n      \"enforcement\": \"suggest\",\n      \"priority\": \"medium\",\n      \"description\": \"What it does\",\n      \"promptTriggers\": {\n        \"keywords\": [\"keyword1\", \"keyword2\"],\n        \"intentPatterns\": [\"(pattern).*?(match)\"]\n      }\n    }\n  }\n}\n```\n\n## Reference Files\n\nFor full details, read:\n\n```bash\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Frules\u002Fskill-development.md\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Frules\u002Fmcp-scripts.md\n```\n\n## Quick Checklist\n\n- [ ] SKILL.md has frontmatter (name, description)\n- [ ] \"When to Use\" section is clear\n- [ ] Instructions are copy-paste ready\n- [ ] MCP servers documented if needed\n- [ ] Triggers added to skill-rules.json (optional)\n\n## Examples in This Repo\n\nLook at existing skills for patterns:\n\n```bash\nls $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002F\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Fcommit\u002FSKILL.md\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Ffirecrawl-scrape\u002FSKILL.md\n```\n","# Skill Developer\n\nMeta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.\n\n## When to Use\n\n- \"Create a skill for X\"\n- \"Help me make a new skill\"\n- \"Turn this script into a skill\"\n- \"How do I create a skill?\"\n\n## Skill Structure\n\nSkills live in `.claude\u002Fskills\u002F\u003Cskill-name>\u002F`:\n\n```\n.claude\u002Fskills\u002Fmy-skill\u002F\n├── SKILL.md          # Required: Main skill definition\n├── scripts\u002F          # Optional: Supporting scripts\n└── templates\u002F        # Optional: Templates, examples\n```\n\n### SKILL.md Format\n\n```yaml\n---\nname: skill-name\ndescription: Brief description (shown in skill list)\nallowed-tools: [Bash, Read, Write]  # Optional: restrict tools\n---\n\n# Skill Name\n\n## When to Use\n[When Claude should discover this skill]\n\n## Instructions\n[Step-by-step instructions for Claude to follow]\n\n## Examples\n[Usage examples]\n```\n\n## Creating an MCP Pipeline Skill\n\nTo create a new MCP chain script and wrap it as a skill:\n\n### Step 1: Use the Template\n\nCopy the multi-tool-pipeline template:\n\n```bash\ncp $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmulti_tool_pipeline.py $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmy_pipeline.py\n```\n\nReference the template pattern:\n\n```bash\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Fmulti-tool-pipeline\u002FSKILL.md\ncat $CLAUDE_PROJECT_DIR\u002Fscripts\u002Fmulti_tool_pipeline.py\n```\n\n### Step 2: Customize the Script\n\nEdit your new script to chain the MCP tools you need:\n\n```python\nasync def main():\n    from runtime.mcp_client import call_mcp_tool\n    args = parse_args()\n\n    # Chain your MCP tools (serverName__toolName)\n    result1 = await call_mcp_tool(\"server1__tool1\", {\"param\": args.arg1})\n    result2 = await call_mcp_tool(\"server2__tool2\", {\"input\": result1})\n\n    print(result2)\n```\n\n### Step 2: Create the Skill\n\nCreate `.claude\u002Fskills\u002Fmy-pipeline\u002FSKILL.md`:\n\n```markdown\n---\nname: my-pipeline\ndescription: What the pipeline does\nallowed-tools: [Bash, Read]\n---\n\n# My Pipeline Skill\n\n## When to Use\n- [Trigger conditions]\n\n## Instructions\n\nRun the pipeline:\n\n\\`\\`\\`bash\nuv run python -m runtime.harness scripts\u002Fmy_pipeline.py --arg1 \"value\"\n\\`\\`\\`\n\n### Parameters\n- `--arg1`: Description\n\n## MCP Servers Required\n- server1: For tool1\n- server2: For tool2\n```\n\n### Step 3: Add Triggers (Optional)\n\nAdd to `.claude\u002Fskills\u002Fskill-rules.json`:\n\n```json\n{\n  \"skills\": {\n    \"my-pipeline\": {\n      \"type\": \"domain\",\n      \"enforcement\": \"suggest\",\n      \"priority\": \"medium\",\n      \"description\": \"What it does\",\n      \"promptTriggers\": {\n        \"keywords\": [\"keyword1\", \"keyword2\"],\n        \"intentPatterns\": [\"(pattern).*?(match)\"]\n      }\n    }\n  }\n}\n```\n\n## Reference Files\n\nFor full details, read:\n\n```bash\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Frules\u002Fskill-development.md\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Frules\u002Fmcp-scripts.md\n```\n\n## Quick Checklist\n\n- [ ] SKILL.md has frontmatter (name, description)\n- [ ] \"When to Use\" section is clear\n- [ ] Instructions are copy-paste ready\n- [ ] MCP servers documented if needed\n- [ ] Triggers added to skill-rules.json (optional)\n\n## Examples in This Repo\n\nLook at existing skills for patterns:\n\n```bash\nls $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002F\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Fcommit\u002FSKILL.md\ncat $CLAUDE_PROJECT_DIR\u002F.claude\u002Fskills\u002Ffirecrawl-scrape\u002FSKILL.md\n```\n",{"name":5,"description":7,"allowed-tools":45},[34,46,47,48],"Read","Write","Edit","main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fskill-developer","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add rubicanjr\u002FFinCognis --skill skill-developer",{"tool":63,"command":64},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill skill-developer",{"tool":66,"command":67},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill skill-developer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fskill-developer\u002FSKILL.md",true,[],[72,89,98,118,147,166],{"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":40},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[78],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[80,81,82,83,84,85,86,87,88],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":40},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[91,96,97],"verification","false",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":40},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[108,109,110,111,112,113,114,115,116,117],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":128,"publishedAt":40},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,130,131,132,133,134,135,136,137,39,138,139,140,111,141,142,143,144,145,146],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":40},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[154,155,96,156,157,158,159,160,161,162,163,164,165],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"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":172,"publishedAt":40},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[173,174,175,176,109,177,178,179,180,115,181,182,183,184,185,39,186,187],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]