[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SC3B8KBW5AS69B293CZYD":3,"skill-same:01M78SC3B8KBW5AS69B293CZYD":66},{"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},"01M78SC3B8KBW5AS69B293CZYD","mcp-search",null,"Operate the Airweave MCP search server in stdio and Streamable HTTP modes, including tool registration, collection and organization resolution, auth modes, Prometheus metrics, deployment knobs, and search-tool behavior.","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\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp-search\ndescription: \"Operate the Airweave MCP search server in stdio and Streamable\n  HTTP modes, including tool registration, collection and organization\n  resolution, auth modes, Prometheus metrics, deployment knobs, and search-tool\n  behavior.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# mcp-search\n\nUse this sub-skill when you need to start, configure, inspect, or troubleshoot the Airweave MCP search server.\n\n## Covers\n- stdio and Streamable HTTP entrypoints\n- MCP tool registration and tool naming\n- collection resolution and organization resolution\n- API key and OAuth\u002FBearer auth paths\n- Prometheus metrics and health endpoints\n- deployment knobs, env vars, and safe smoke checks\n\n## Does not cover\n- backend endpoint implementation details\n- dashboard UI or frontend internals\n- Connect widget internals\n- Monke orchestration\n\n## Start here\n1. Read `references\u002Fmcp-overview.md` for entrypoints, env vars, and deployment knobs.\n2. Read `references\u002Ftransport-and-tools.md` for the collection-specific tool surface and search behavior; use `tools\u002Flist` or `get-config` before calling a search.\n3. Read `references\u002Fauth-and-troubleshooting.md` for auth, org resolution, metrics, and common failures.\n4. Use `scripts\u002Fmcp-smoke.sh` for a safe version\u002Fbuild\u002Ftest\u002Fentrypoint smoke pass.\n\n## Cross-links\n- Use `backend-api` for backend search-route and collection semantics.\n- Use `frontend-dashboard` only when a dashboard-driven setup or auth-context issue changes how MCP credentials or collection IDs are obtained.\n\n## Working notes\n- stdio requires `AIRWEAVE_API_KEY` and `AIRWEAVE_COLLECTION`; `AIRWEAVE_BASE_URL` is optional.\n- HTTP mode serves `\u002Fmcp`, `\u002Fhealth`, `\u002Fmetrics`, and `GET \u002F` server info.\n- HTTP auth can use `X-API-Key` or `Authorization: Bearer ...`; OAuth mode adds Auth0, Redis, and org resolution.\n- Search tools are collection-specific (`search-\u003Ccollection>`), with `get-config` as the second tool.\n\n## Verification expectations\n- Missing stdio credentials should fail fast with a clear config error.\n- HTTP OAuth requests should resolve the organization for the target collection.\n- Tool lists, metrics, and search responses should remain readable and non-secret.\n","# mcp-search\n\nUse this sub-skill when you need to start, configure, inspect, or troubleshoot the Airweave MCP search server.\n\n## Covers\n- stdio and Streamable HTTP entrypoints\n- MCP tool registration and tool naming\n- collection resolution and organization resolution\n- API key and OAuth\u002FBearer auth paths\n- Prometheus metrics and health endpoints\n- deployment knobs, env vars, and safe smoke checks\n\n## Does not cover\n- backend endpoint implementation details\n- dashboard UI or frontend internals\n- Connect widget internals\n- Monke orchestration\n\n## Start here\n1. Read `references\u002Fmcp-overview.md` for entrypoints, env vars, and deployment knobs.\n2. Read `references\u002Ftransport-and-tools.md` for the collection-specific tool surface and search behavior; use `tools\u002Flist` or `get-config` before calling a search.\n3. Read `references\u002Fauth-and-troubleshooting.md` for auth, org resolution, metrics, and common failures.\n4. Use `scripts\u002Fmcp-smoke.sh` for a safe version\u002Fbuild\u002Ftest\u002Fentrypoint smoke pass.\n\n## Cross-links\n- Use `backend-api` for backend search-route and collection semantics.\n- Use `frontend-dashboard` only when a dashboard-driven setup or auth-context issue changes how MCP credentials or collection IDs are obtained.\n\n## Working notes\n- stdio requires `AIRWEAVE_API_KEY` and `AIRWEAVE_COLLECTION`; `AIRWEAVE_BASE_URL` is optional.\n- HTTP mode serves `\u002Fmcp`, `\u002Fhealth`, `\u002Fmetrics`, and `GET \u002F` server info.\n- HTTP auth can use `X-API-Key` or `Authorization: Bearer ...`; OAuth mode adds Auth0, Redis, and org resolution.\n- Search tools are collection-specific (`search-\u003Ccollection>`), with `get-config` as the second tool.\n\n## Verification expectations\n- Missing stdio credentials should fail fast with a clear config error.\n- HTTP OAuth requests should resolve the organization for the target collection.\n- Tool lists, metrics, and search responses should remain readable and non-secret.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search",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 mcp-search",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-search",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fauth-and-troubleshooting.md","REFERENCE","参考文档",2442,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002Freferences\u002Fauth-and-troubleshooting.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmcp-overview.md",2904,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002Freferences\u002Fmcp-overview.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftransport-and-tools.md",2132,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002Freferences\u002Ftransport-and-tools.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fmcp-smoke.sh","SCRIPT","脚本",8257,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Fmcp-search\u002Fscripts\u002Fmcp-smoke.sh",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]