[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z0ZACQVFK2JS3J30K81CQ":3,"skill-same:01M78Z0ZACQVFK2JS3J30K81CQ":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78Z0ZACQVFK2JS3J30K81CQ","integrations-mcp-chainlit",null,"Connect Langroid agents to MCP tools, web\u002Fsearch\u002Ffile tools, Chainlit callbacks\u002FUI, HTML logging, and external-service integrations.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: integrations-mcp-chainlit\ndescription: \"Connect Langroid agents to MCP tools, web\u002Fsearch\u002Ffile tools,\n  Chainlit callbacks\u002FUI, HTML logging, and external-service integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# integrations-mcp-chainlit\n\nUse this sub-skill when a Langroid task needs to connect agents to external tools or service-facing integration layers: MCP servers, built-in web\u002Fsearch tools, safe local file tools, Chainlit UI callbacks, HTML task logs, quiet\u002Fstatus output control, or deterministic local smoke checks for those integrations.\n\n## Route before acting\n\n- For Langroid custom `ToolMessage` design, handler signatures, task done sequences, or multi-agent delegation mechanics, route to [`..\u002Fagents-tasks-tools\u002FSKILL.md`](..\u002Fagents-tasks-tools\u002FSKILL.md).\n- For LLM provider configuration, model names, API gateways, or provider authentication, route to [`..\u002Fllm-provider-config\u002FSKILL.md`](..\u002Fllm-provider-config\u002FSKILL.md).\n- For RAG ingestion, document parsing, vector stores, or document-chat agents, route to [`..\u002Fretrieval-doc-chat\u002FSKILL.md`](..\u002Fretrieval-doc-chat\u002FSKILL.md).\n- Stay here for external tool integration wiring, callback\u002FUI integration, search\u002Ffile tool enablement, MCP transport lifecycle, logging\u002Foutput controls, and integration troubleshooting.\n\n## Operating map\n\n1. Identify which integration boundary is needed: MCP, search, file tools, Chainlit UI, or logging\u002Foutput.\n2. Load the narrow reference for that boundary:\n   - [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) for MCP tool generation, transports, async\u002Fdecorator choices, and resource forwarding.\n   - [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) for DuckDuckGo, Tavily, Exa, Google, Seltz, Twitter\u002FX-over-MCP, and local file tools.\n   - [`references\u002Fchainlit-and-ui.md`](references\u002Fchainlit-and-ui.md) for Chainlit callback injection and UI session patterns.\n   - [`references\u002Flogging-and-output.md`](references\u002Flogging-and-output.md) for HTML logs, quiet mode, streaming, and status output.\n   - [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common event-loop, credential, subprocess, Chainlit, logging, and quiet-mode failures.\n3. Prefer async APIs inside any async app, Chainlit callback, notebook, or test: use `get_tool_async()` \u002F `get_tools_async()` and never wrap them in `asyncio.run()` from a running loop.\n4. Keep external-service checks bounded: verify imports, environment variables, local `--help` availability, and schemas before making live network calls. Do not require network for smoke tests.\n5. When validating MCP availability without external side effects, run the bundled smoke script:\n\n```bash\npython scripts\u002Fmcp_tool_smoke.py\n```\n\n## Minimal decision table\n\n| Need | Preferred Langroid entry point | Reference |\n| --- | --- | --- |\n| Build one MCP tool inside async code | `await get_tool_async(server, \"tool_name\")` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Build all MCP tools | `await get_tools_async(server)` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Customize MCP result formatting | subclass generated tool or use `@mcp_tool` with `handle_async()` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Web search tool | enable `DuckduckgoSearchTool`, `TavilySearchTool`, `ExaSearchTool`, `GoogleSearchTool`, or `SeltzSearchTool` | [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) |\n| Safe local file read\u002Fwrite\u002Flist | `ReadFileTool.create`, `WriteFileTool.create`, `ListDirTool.create` | [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) |\n| Chainlit UI around an agent\u002Ftask | `ChainlitAgentCallbacks` or `ChainlitTaskCallbacks` | [`references\u002Fchainlit-and-ui.md`](references\u002Fchainlit-and-ui.md) |\n| Suppress terminal noise or inspect logs | `quiet_mode`, `async_stream_quiet`, `TaskConfig(enable_html_logging=...)` | [`references\u002Flogging-and-output.md`](references\u002Flogging-and-output.md) |\n","# integrations-mcp-chainlit\n\nUse this sub-skill when a Langroid task needs to connect agents to external tools or service-facing integration layers: MCP servers, built-in web\u002Fsearch tools, safe local file tools, Chainlit UI callbacks, HTML task logs, quiet\u002Fstatus output control, or deterministic local smoke checks for those integrations.\n\n## Route before acting\n\n- For Langroid custom `ToolMessage` design, handler signatures, task done sequences, or multi-agent delegation mechanics, route to [`..\u002Fagents-tasks-tools\u002FSKILL.md`](..\u002Fagents-tasks-tools\u002FSKILL.md).\n- For LLM provider configuration, model names, API gateways, or provider authentication, route to [`..\u002Fllm-provider-config\u002FSKILL.md`](..\u002Fllm-provider-config\u002FSKILL.md).\n- For RAG ingestion, document parsing, vector stores, or document-chat agents, route to [`..\u002Fretrieval-doc-chat\u002FSKILL.md`](..\u002Fretrieval-doc-chat\u002FSKILL.md).\n- Stay here for external tool integration wiring, callback\u002FUI integration, search\u002Ffile tool enablement, MCP transport lifecycle, logging\u002Foutput controls, and integration troubleshooting.\n\n## Operating map\n\n1. Identify which integration boundary is needed: MCP, search, file tools, Chainlit UI, or logging\u002Foutput.\n2. Load the narrow reference for that boundary:\n   - [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) for MCP tool generation, transports, async\u002Fdecorator choices, and resource forwarding.\n   - [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) for DuckDuckGo, Tavily, Exa, Google, Seltz, Twitter\u002FX-over-MCP, and local file tools.\n   - [`references\u002Fchainlit-and-ui.md`](references\u002Fchainlit-and-ui.md) for Chainlit callback injection and UI session patterns.\n   - [`references\u002Flogging-and-output.md`](references\u002Flogging-and-output.md) for HTML logs, quiet mode, streaming, and status output.\n   - [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common event-loop, credential, subprocess, Chainlit, logging, and quiet-mode failures.\n3. Prefer async APIs inside any async app, Chainlit callback, notebook, or test: use `get_tool_async()` \u002F `get_tools_async()` and never wrap them in `asyncio.run()` from a running loop.\n4. Keep external-service checks bounded: verify imports, environment variables, local `--help` availability, and schemas before making live network calls. Do not require network for smoke tests.\n5. When validating MCP availability without external side effects, run the bundled smoke script:\n\n```bash\npython scripts\u002Fmcp_tool_smoke.py\n```\n\n## Minimal decision table\n\n| Need | Preferred Langroid entry point | Reference |\n| --- | --- | --- |\n| Build one MCP tool inside async code | `await get_tool_async(server, \"tool_name\")` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Build all MCP tools | `await get_tools_async(server)` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Customize MCP result formatting | subclass generated tool or use `@mcp_tool` with `handle_async()` | [`references\u002Fmcp-workflows.md`](references\u002Fmcp-workflows.md) |\n| Web search tool | enable `DuckduckgoSearchTool`, `TavilySearchTool`, `ExaSearchTool`, `GoogleSearchTool`, or `SeltzSearchTool` | [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) |\n| Safe local file read\u002Fwrite\u002Flist | `ReadFileTool.create`, `WriteFileTool.create`, `ListDirTool.create` | [`references\u002Fsearch-and-file-tools.md`](references\u002Fsearch-and-file-tools.md) |\n| Chainlit UI around an agent\u002Ftask | `ChainlitAgentCallbacks` or `ChainlitTaskCallbacks` | [`references\u002Fchainlit-and-ui.md`](references\u002Fchainlit-and-ui.md) |\n| Suppress terminal noise or inspect logs | `quiet_mode`, `async_stream_quiet`, `TaskConfig(enable_html_logging=...)` | [`references\u002Flogging-and-output.md`](references\u002Flogging-and-output.md) |\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill integrations-mcp-chainlit",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill integrations-mcp-chainlit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill integrations-mcp-chainlit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fchainlit-and-ui.md","REFERENCE","参考文档",6045,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Freferences\u002Fchainlit-and-ui.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flogging-and-output.md",4023,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Freferences\u002Flogging-and-output.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fmcp-workflows.md",8738,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Freferences\u002Fmcp-workflows.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsearch-and-file-tools.md",6048,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Freferences\u002Fsearch-and-file-tools.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",7764,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmcp_tool_smoke.py","SCRIPT","脚本",4505,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangroid\u002Fsub-skills\u002Fintegrations-mcp-chainlit\u002Fscripts\u002Fmcp_tool_smoke.py",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]