[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VEF545DSQP3TF8R8WW2SF":3,"skill-same:01M78VEF545DSQP3TF8R8WW2SF":70},{"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},"01M78VEF545DSQP3TF8R8WW2SF","server-backends-and-async",null,"Use for Dash backend selection, async callbacks, WebSocket callbacks, background callbacks, hooks, and MCP server configuration.","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\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: server-backends-and-async\ndescription: \"Use for Dash backend selection, async callbacks, WebSocket\n  callbacks, background callbacks, hooks, and MCP server configuration.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Dash Server Backends and Async Workflows\n\nUse this sub-skill when a task depends on Dash's server runtime rather than the\nlayout\u002Fcallback API alone: backend selection, async callbacks, background\ncallbacks, WebSocket callbacks, hooks, or MCP exposure.\n\n## Start here\n\n1. Read [references\u002Fbackend-workflows.md](references\u002Fbackend-workflows.md) for\n   backend selection, adapters, and constructor\u002Fruntime facts.\n2. Read [references\u002Fbackground-and-websocket-callbacks.md](references\u002Fbackground-and-websocket-callbacks.md)\n   for async, background, and WebSocket behavior.\n3. Read [references\u002Fmcp-and-hooks.md](references\u002Fmcp-and-hooks.md) for hooks and\n   MCP configuration.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a\n   backend import or optional-extra path fails.\n5. Run [scripts\u002Finspect_backends.py](scripts\u002Finspect_backends.py) for a safe\n   optional-backend diagnostic before promising backend coverage.\n\n## Main routes\n\n### Choose or inspect a backend\n\nDash defaults to Flask but can also run on FastAPI or Quart. Use this sub-skill\nwhen you need to know which backend constructor to use, which extras are needed,\nor how to create a Dash app around an existing server instance.\n\n### Write async or background callbacks\n\nUse this sub-skill for `async def` callbacks, `background=True`,\n`DiskcacheManager`, `CeleryManager`, `progress`, `running`, `cancel`, and cache\nkeys.\n\n### Use WebSocket callbacks\n\nRoute WebSocket tasks here when the callback depends on `websocket_callbacks`,\n`websocket=True`, `persistent=True`, `ctx.websocket`, `set_props`, or browser\u002F\nserver disconnect behavior. FastAPI is the backend surface that exposes the\nWebSocket path in Dash.\n\n### Expose hooks or MCP content\n\nUse this sub-skill for `hooks.setup`, `hooks.layout`, `hooks.route`,\n`hooks.error`, `hooks.callback`, `hooks.websocket_connect`,\n`hooks.websocket_message`, `configure_mcp_server`, and `mcp_enabled`.\n\n## Route elsewhere\n\n- Plain callback, layout, page, asset, and clientside app behavior:\n  [app callback workflows](..\u002Fapp-callback-workflows\u002FSKILL.md).\n- Component wrapper generation, `dash-renderer`, and resource loading:\n  [component renderer development](..\u002Fcomponent-renderer-development\u002FSKILL.md).\n- Test selection and browser command strategy:\n  [testing and maintenance](..\u002Ftesting-and-maintenance\u002FSKILL.md).\n\n## Validation checklist\n\nBefore marking a backend workflow solved:\n\n- The installed extra or backend package is present.\n- If the workflow requires Flask async, `dash[async]` is installed.\n- If the workflow requires FastAPI or Quart, the relevant extra is installed and\n  a safe app\u002Fbackend construction check passes.\n- If the workflow requires Diskcache or Celery, the corresponding dependency set\n  is installed and the service requirement is called out when applicable.\n- If the workflow uses WebSocket callbacks, the backend and browser\u002Fruntime\n  prerequisites are explicitly named.\n- If a hook or MCP change alters route exposure, the sub-skill references explain\n  the request\u002Fsession\u002Fcontent-type rules and the expected failure modes.\n","# Dash Server Backends and Async Workflows\n\nUse this sub-skill when a task depends on Dash's server runtime rather than the\nlayout\u002Fcallback API alone: backend selection, async callbacks, background\ncallbacks, WebSocket callbacks, hooks, or MCP exposure.\n\n## Start here\n\n1. Read [references\u002Fbackend-workflows.md](references\u002Fbackend-workflows.md) for\n   backend selection, adapters, and constructor\u002Fruntime facts.\n2. Read [references\u002Fbackground-and-websocket-callbacks.md](references\u002Fbackground-and-websocket-callbacks.md)\n   for async, background, and WebSocket behavior.\n3. Read [references\u002Fmcp-and-hooks.md](references\u002Fmcp-and-hooks.md) for hooks and\n   MCP configuration.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a\n   backend import or optional-extra path fails.\n5. Run [scripts\u002Finspect_backends.py](scripts\u002Finspect_backends.py) for a safe\n   optional-backend diagnostic before promising backend coverage.\n\n## Main routes\n\n### Choose or inspect a backend\n\nDash defaults to Flask but can also run on FastAPI or Quart. Use this sub-skill\nwhen you need to know which backend constructor to use, which extras are needed,\nor how to create a Dash app around an existing server instance.\n\n### Write async or background callbacks\n\nUse this sub-skill for `async def` callbacks, `background=True`,\n`DiskcacheManager`, `CeleryManager`, `progress`, `running`, `cancel`, and cache\nkeys.\n\n### Use WebSocket callbacks\n\nRoute WebSocket tasks here when the callback depends on `websocket_callbacks`,\n`websocket=True`, `persistent=True`, `ctx.websocket`, `set_props`, or browser\u002F\nserver disconnect behavior. FastAPI is the backend surface that exposes the\nWebSocket path in Dash.\n\n### Expose hooks or MCP content\n\nUse this sub-skill for `hooks.setup`, `hooks.layout`, `hooks.route`,\n`hooks.error`, `hooks.callback`, `hooks.websocket_connect`,\n`hooks.websocket_message`, `configure_mcp_server`, and `mcp_enabled`.\n\n## Route elsewhere\n\n- Plain callback, layout, page, asset, and clientside app behavior:\n  [app callback workflows](..\u002Fapp-callback-workflows\u002FSKILL.md).\n- Component wrapper generation, `dash-renderer`, and resource loading:\n  [component renderer development](..\u002Fcomponent-renderer-development\u002FSKILL.md).\n- Test selection and browser command strategy:\n  [testing and maintenance](..\u002Ftesting-and-maintenance\u002FSKILL.md).\n\n## Validation checklist\n\nBefore marking a backend workflow solved:\n\n- The installed extra or backend package is present.\n- If the workflow requires Flask async, `dash[async]` is installed.\n- If the workflow requires FastAPI or Quart, the relevant extra is installed and\n  a safe app\u002Fbackend construction check passes.\n- If the workflow requires Diskcache or Celery, the corresponding dependency set\n  is installed and the service requirement is called out when applicable.\n- If the workflow uses WebSocket callbacks, the backend and browser\u002Fruntime\n  prerequisites are explicitly named.\n- If a hook or MCP change alters route exposure, the sub-skill references explain\n  the request\u002Fsession\u002Fcontent-type rules and the expected failure modes.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async",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 server-backends-and-async",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill server-backends-and-async",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill server-backends-and-async","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fbackend-workflows.md","REFERENCE","参考文档",2490,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002Freferences\u002Fbackend-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fbackground-and-websocket-callbacks.md",3927,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002Freferences\u002Fbackground-and-websocket-callbacks.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fmcp-and-hooks.md",2458,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002Freferences\u002Fmcp-and-hooks.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3454,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Finspect_backends.py","SCRIPT","脚本",3060,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdash\u002Fsub-skills\u002Fserver-backends-and-async\u002Fscripts\u002Finspect_backends.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]