[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NVNXK38VH5VJSZ856G0SEG":3,"skill-same:01M6NVNXK38VH5VJSZ856G0SEG":67},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6NVNXK38VH5VJSZ856G0SEG","mcp-chaining",null,"Research-to-implement pipeline chaining 5 MCP tools with graceful degradation","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\u002Fmcp-chaining\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],"MCP","chaining","mcp chaining","implement","research","mcp tools","pipeline","Tools","Bash","read","false","degradation","with","graceful degradation","2026-11-10 10:12:30",false,"---\nname: mcp-chaining\ndescription: Research-to-implement pipeline chaining 5 MCP tools with graceful degradation\nallowed-tools: [Bash, Read]\nuser-invocable: false\n---\n\n# MCP Chaining Pipeline\n\nA research-to-implement pipeline that chains 5 MCP tools for end-to-end workflows.\n\n## When to Use\n\n- Building multi-tool MCP pipelines\n- Understanding how to chain MCP calls with graceful degradation\n- Debugging MCP environment variable issues\n- Learning the tool naming conventions for different MCP servers\n\n## What We Built\n\nA pipeline that chains these tools:\n\n| Step | Server | Tool ID | Purpose |\n|------|--------|---------|---------|\n| 1 | nia | `nia__search` | Search library documentation |\n| 2 | ast-grep | `ast-grep__find_code` | Find AST code patterns |\n| 3 | morph | `morph__warpgrep_codebase_search` | Fast codebase search |\n| 4 | qlty | `qlty__qlty_check` | Code quality validation |\n| 5 | git | `git__git_status` | Git operations |\n\n## Key Files\n\n- `scripts\u002Fresearch_implement_pipeline.py` - Main pipeline implementation\n- `scripts\u002Ftest_research_pipeline.py` - Test harness with isolated sandbox\n- `workspace\u002Fpipeline-test\u002Fsample_code.py` - Test sample code\n\n## Usage Examples\n\n```bash\n# Dry-run pipeline (preview plan without changes)\nuv run python -m runtime.harness scripts\u002Fresearch_implement_pipeline.py \\\n    --topic \"async error handling python\" \\\n    --target-dir \".\u002Fworkspace\u002Fpipeline-test\" \\\n    --dry-run --verbose\n\n# Run tests\nuv run python -m runtime.harness scripts\u002Ftest_research_pipeline.py --test all\n\n# View the pipeline script\ncat scripts\u002Fresearch_implement_pipeline.py\n```\n\n## Critical Fix: Environment Variables\n\nThe MCP SDK's `get_default_environment()` only includes basic vars (PATH, HOME, etc.), NOT `os.environ`. We fixed `src\u002Fruntime\u002Fmcp_client.py` to pass full environment:\n\n```python\n# In _connect_stdio method:\nfull_env = {**os.environ, **(resolved_env or {})}\n```\n\nThis ensures API keys from `~\u002F.claude\u002F.env` reach subprocesses.\n\n## Graceful Degradation Pattern\n\nEach tool is optional. If unavailable (disabled, no API key, etc.), the pipeline continues:\n\n```python\nasync def check_tool_available(tool_id: str) -> bool:\n    \"\"\"Check if an MCP tool is available.\"\"\"\n    server_name = tool_id.split(\"__\")[0]\n    server_config = manager._config.get_server(server_name)\n    if not server_config or server_config.disabled:\n        return False\n    return True\n\n# In step function:\nif not await check_tool_available(\"nia__search\"):\n    return StepResult(status=StepStatus.SKIPPED, message=\"Nia not available\")\n```\n\n## Tool Name Reference\n\n### nia (Documentation Search)\n```\nnia__search              - Universal documentation search\nnia__nia_research        - Research with sources\nnia__nia_grep            - Grep-style doc search\nnia__nia_explore         - Explore package structure\n```\n\n### ast-grep (Structural Code Search)\n```\nast-grep__find_code      - Find code by AST pattern\nast-grep__find_code_by_rule - Find by YAML rule\nast-grep__scan_code      - Scan with multiple patterns\n```\n\n### morph (Fast Text Search + Edit)\n```\nmorph__warpgrep_codebase_search  - 20x faster grep\nmorph__edit_file                 - Smart file editing\n```\n\n### qlty (Code Quality)\n```\nqlty__qlty_check         - Run quality checks\nqlty__qlty_fmt           - Auto-format code\nqlty__qlty_metrics       - Get code metrics\nqlty__smells             - Detect code smells\n```\n\n### git (Version Control)\n```\ngit__git_status          - Get repo status\ngit__git_diff            - Show differences\ngit__git_log             - View commit history\ngit__git_add             - Stage files\n```\n\n## Pipeline Architecture\n\n```\n                    +----------------+\n                    |   CLI Args     |\n                    | (topic, dir)   |\n                    +-------+--------+\n                            |\n                    +-------v--------+\n                    | PipelineContext|\n                    | (shared state) |\n                    +-------+--------+\n                            |\n    +-------+-------+-------+-------+-------+\n    |       |       |       |       |       |\n+---v---+---v---+---v---+---v---+---v---+\n| nia   |ast-grp| morph | qlty  | git   |\n|search |pattern|search |check  |status |\n+---+---+---+---+---+---+---+---+---+---+\n    |       |       |       |       |\n    +-------v-------v-------v-------+\n                    |\n            +-------v--------+\n            | StepResult[]   |\n            | (aggregated)   |\n            +----------------+\n```\n\n## Error Handling\n\nThe pipeline captures errors without failing the entire run:\n\n```python\ntry:\n    result = await call_mcp_tool(\"nia__search\", {\"query\": topic})\n    return StepResult(status=StepStatus.SUCCESS, data=result)\nexcept Exception as e:\n    ctx.errors.append(f\"nia: {e}\")\n    return StepResult(status=StepStatus.FAILED, error=str(e))\n```\n\n## Creating Your Own Pipeline\n\n1. Copy the pattern from `scripts\u002Fresearch_implement_pipeline.py`\n2. Define your steps as async functions\n3. Use `check_tool_available()` for graceful degradation\n4. Chain results through `PipelineContext`\n5. Aggregate with `print_summary()`\n","# MCP Chaining Pipeline\n\nA research-to-implement pipeline that chains 5 MCP tools for end-to-end workflows.\n\n## When to Use\n\n- Building multi-tool MCP pipelines\n- Understanding how to chain MCP calls with graceful degradation\n- Debugging MCP environment variable issues\n- Learning the tool naming conventions for different MCP servers\n\n## What We Built\n\nA pipeline that chains these tools:\n\n| Step | Server | Tool ID | Purpose |\n|------|--------|---------|---------|\n| 1 | nia | `nia__search` | Search library documentation |\n| 2 | ast-grep | `ast-grep__find_code` | Find AST code patterns |\n| 3 | morph | `morph__warpgrep_codebase_search` | Fast codebase search |\n| 4 | qlty | `qlty__qlty_check` | Code quality validation |\n| 5 | git | `git__git_status` | Git operations |\n\n## Key Files\n\n- `scripts\u002Fresearch_implement_pipeline.py` - Main pipeline implementation\n- `scripts\u002Ftest_research_pipeline.py` - Test harness with isolated sandbox\n- `workspace\u002Fpipeline-test\u002Fsample_code.py` - Test sample code\n\n## Usage Examples\n\n```bash\n# Dry-run pipeline (preview plan without changes)\nuv run python -m runtime.harness scripts\u002Fresearch_implement_pipeline.py \\\n    --topic \"async error handling python\" \\\n    --target-dir \".\u002Fworkspace\u002Fpipeline-test\" \\\n    --dry-run --verbose\n\n# Run tests\nuv run python -m runtime.harness scripts\u002Ftest_research_pipeline.py --test all\n\n# View the pipeline script\ncat scripts\u002Fresearch_implement_pipeline.py\n```\n\n## Critical Fix: Environment Variables\n\nThe MCP SDK's `get_default_environment()` only includes basic vars (PATH, HOME, etc.), NOT `os.environ`. We fixed `src\u002Fruntime\u002Fmcp_client.py` to pass full environment:\n\n```python\n# In _connect_stdio method:\nfull_env = {**os.environ, **(resolved_env or {})}\n```\n\nThis ensures API keys from `~\u002F.claude\u002F.env` reach subprocesses.\n\n## Graceful Degradation Pattern\n\nEach tool is optional. If unavailable (disabled, no API key, etc.), the pipeline continues:\n\n```python\nasync def check_tool_available(tool_id: str) -> bool:\n    \"\"\"Check if an MCP tool is available.\"\"\"\n    server_name = tool_id.split(\"__\")[0]\n    server_config = manager._config.get_server(server_name)\n    if not server_config or server_config.disabled:\n        return False\n    return True\n\n# In step function:\nif not await check_tool_available(\"nia__search\"):\n    return StepResult(status=StepStatus.SKIPPED, message=\"Nia not available\")\n```\n\n## Tool Name Reference\n\n### nia (Documentation Search)\n```\nnia__search              - Universal documentation search\nnia__nia_research        - Research with sources\nnia__nia_grep            - Grep-style doc search\nnia__nia_explore         - Explore package structure\n```\n\n### ast-grep (Structural Code Search)\n```\nast-grep__find_code      - Find code by AST pattern\nast-grep__find_code_by_rule - Find by YAML rule\nast-grep__scan_code      - Scan with multiple patterns\n```\n\n### morph (Fast Text Search + Edit)\n```\nmorph__warpgrep_codebase_search  - 20x faster grep\nmorph__edit_file                 - Smart file editing\n```\n\n### qlty (Code Quality)\n```\nqlty__qlty_check         - Run quality checks\nqlty__qlty_fmt           - Auto-format code\nqlty__qlty_metrics       - Get code metrics\nqlty__smells             - Detect code smells\n```\n\n### git (Version Control)\n```\ngit__git_status          - Get repo status\ngit__git_diff            - Show differences\ngit__git_log             - View commit history\ngit__git_add             - Stage files\n```\n\n## Pipeline Architecture\n\n```\n                    +----------------+\n                    |   CLI Args     |\n                    | (topic, dir)   |\n                    +-------+--------+\n                            |\n                    +-------v--------+\n                    | PipelineContext|\n                    | (shared state) |\n                    +-------+--------+\n                            |\n    +-------+-------+-------+-------+-------+\n    |       |       |       |       |       |\n+---v---+---v---+---v---+---v---+---v---+\n| nia   |ast-grp| morph | qlty  | git   |\n|search |pattern|search |check  |status |\n+---+---+---+---+---+---+---+---+---+---+\n    |       |       |       |       |\n    +-------v-------v-------v-------+\n                    |\n            +-------v--------+\n            | StepResult[]   |\n            | (aggregated)   |\n            +----------------+\n```\n\n## Error Handling\n\nThe pipeline captures errors without failing the entire run:\n\n```python\ntry:\n    result = await call_mcp_tool(\"nia__search\", {\"query\": topic})\n    return StepResult(status=StepStatus.SUCCESS, data=result)\nexcept Exception as e:\n    ctx.errors.append(f\"nia: {e}\")\n    return StepResult(status=StepStatus.FAILED, error=str(e))\n```\n\n## Creating Your Own Pipeline\n\n1. Copy the pattern from `scripts\u002Fresearch_implement_pipeline.py`\n2. Define your steps as async functions\n3. Use `check_tool_available()` for graceful degradation\n4. Chain results through `PipelineContext`\n5. Aggregate with `print_summary()`\n",{"name":5,"description":7,"allowed-tools":43,"user-invocable":39},[32,44],"Read","main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fmcp-chaining","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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add rubicanjr\u002FFinCognis --skill mcp-chaining",{"tool":59,"command":60},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill mcp-chaining",{"tool":62,"command":63},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill mcp-chaining","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-chaining\u002FSKILL.md",true,[],[68,85,93,113,143,162],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":75,"publishedAt":38},"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",[74],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[76,77,78,79,80,81,82,83,84],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":38},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[87,92,34],"verification",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":102,"publishedAt":38},"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",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[103,104,105,106,107,108,109,110,111,112],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"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":123,"publishedAt":38},"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",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[124,125,126,127,128,129,130,131,132,133,134,135,136,106,137,138,139,140,141,142],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":38},"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",[],[150,151,92,152,153,154,155,156,157,158,159,160,161],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":38},"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",[],[169,170,171,172,104,173,174,175,176,110,177,178,179,180,181,133,182,183],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]