[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791QVQJQ7RHC4XFC59JB6CB":3,"skill-same:01M791QVQJQ7RHC4XFC59JB6CB":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},"01M791QVQJQ7RHC4XFC59JB6CB","open-wearables",null,"Operating router for the Open Wearables FastAPI backend, wearable provider integrations, React portal, and FastMCP server.","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\u002Fopen-wearables\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: open-wearables\ndescription: \"Operating router for the Open Wearables FastAPI backend, wearable\n  provider integrations, React portal, and FastMCP server.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Open Wearables\n\nUse this repo skill for Open Wearables, a monorepo that aggregates wearable and health data through a Python\u002FFastAPI backend, React\u002FTanStack Start portal, and FastMCP server for AI assistants.\n\n## Route the task\n\n- Backend API, auth\u002Fdeveloper credentials, users, connections, summaries, events, timeseries, sync status, seed data, outgoing webhooks, service\u002Frepository\u002Fmodel\u002Fschema work, migrations, DB\u002FRedis\u002FCelery\u002FSvix\u002FAWS config, and backend tests → [backend-core](sub-skills\u002Fbackend-core\u002FSKILL.md).\n- Wearable provider strategies, provider enum\u002Ffactory registration, OAuth handlers, workout\u002F24-7 data handlers, incoming provider webhooks, coverage declarations, coverage docs, provider sync\u002Fbackfill, and provider-specific tests → [provider-integrations](sub-skills\u002Fprovider-integrations\u002FSKILL.md).\n- React portal routes, protected auth layout, dashboard\u002Fusers\u002Fsettings\u002Fcoverage\u002Fsync\u002Fwebhooks pages, API hooks\u002Fservices\u002Fquery keys, runtime `VITE_API_URL`, TanStack Router\u002FQuery, components, styling, and frontend test\u002Flint\u002Fbuild work → [frontend-portal](sub-skills\u002Ffrontend-portal\u002FSKILL.md).\n- FastMCP server startup, assistant configuration, MCP tools, REST client behavior, prompts, mocked MCP tests, and MCP API-key\u002Fbackend failure handling → [mcp-server](sub-skills\u002Fmcp-server\u002FSKILL.md).\n\n## Read shared references\n\n- [setup.md](references\u002Fsetup.md) — prerequisites, install commands, service topology, and safe validation commands.\n- [architecture.md](references\u002Farchitecture.md) — monorepo package map, backend\u002Fprovider\u002Ffrontend\u002FMCP data flow, and cross-skill ownership.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) — shared install\u002Fimport\u002Fservice\u002Fconfig\u002Fcredential failures and where to route deeper debugging.\n- [repo-provenance.md](references\u002Frepo-provenance.md) — source snapshot for staleness checks before refreshing this skill.\n\nRun the safe root checker when a checkout is available:\n\n```bash\npython skills\u002Fdisco\u002Fopen-wearables\u002Fscripts\u002Fcheck_open_wearables_install.py --repo-root .\n```\n\nThis checker is read-only. It verifies package metadata, expected directories, docs navigation presence, and local tool availability; it does not start services, install packages, call provider APIs, or read real secrets.\n\n## Package and service baseline\n\n- Backend package: `open-wearables==0.7.0`, Python `>=3.13`, FastAPI, SQLAlchemy 2.0, PostgreSQL, Redis, Celery, Svix, AWS\u002FS3 optional storage, Ruff, Ty, Pytest.\n- Frontend package: `frontend-app==0.7.0`, Node `>=22`, pnpm `>=10`, React 19, TanStack Start\u002FRouter\u002FQuery, Tailwind CSS 4, shadcn\u002Fui, Vitest, oxlint, Prettier.\n- MCP package: `open-wearables-mcp==0.1.0`, Python `>=3.13`, FastMCP, httpx, Pydantic settings, `start = app.main:main`.\n- Local stack: Docker Compose starts backend, frontend, PostgreSQL, Redis, Celery workers\u002Fbeat\u002FFlower, and Svix services. Use a disposable dev\u002Ftest stack for seed\u002Freset\u002Freplay utilities.\n\n## Boundary rules\n\n- Do not commit real provider credentials, API keys, JWTs, OAuth tokens, Svix secrets, AWS keys, master encryption keys, or `.env` files.\n- Keep backend endpoint changes synchronized with frontend\u002FMCP callers and docs. External API endpoints tagged `External: *` require API Reference navigation updates.\n- Provider coverage is the source of truth for `\u002Fapi\u002Fv1\u002Fmeta\u002Fcoverage` and the portal coverage matrix; changes belong in `provider-integrations` even when surfaced in backend routes or frontend UI.\n- MCP is REST-client-driven. Do not bypass the backend by importing backend database models or direct DB access into the MCP package.\n- Runtime frontend API URL must go through `resolveApiUrl()` \u002F `API_CONFIG.baseUrl`; do not inline `import.meta.env.VITE_API_URL` in application code.\n- Prefer focused native checks after edits: backend targeted pytest, provider coverage\u002Fimport tests, frontend Vitest\u002Flint\u002Fbuild when dependencies are installed, and MCP mocked pytest.\n\n## Staleness check\n\nBefore relying on this skill for a different checkout, read [repo-provenance.md](references\u002Frepo-provenance.md). If the commit, package versions, route\u002Fplugin entry points, provider inventory, frontend scripts, or MCP tool names changed, use `refresh-repo-skill` rather than patching this skill by hand.\n","# Open Wearables\n\nUse this repo skill for Open Wearables, a monorepo that aggregates wearable and health data through a Python\u002FFastAPI backend, React\u002FTanStack Start portal, and FastMCP server for AI assistants.\n\n## Route the task\n\n- Backend API, auth\u002Fdeveloper credentials, users, connections, summaries, events, timeseries, sync status, seed data, outgoing webhooks, service\u002Frepository\u002Fmodel\u002Fschema work, migrations, DB\u002FRedis\u002FCelery\u002FSvix\u002FAWS config, and backend tests → [backend-core](sub-skills\u002Fbackend-core\u002FSKILL.md).\n- Wearable provider strategies, provider enum\u002Ffactory registration, OAuth handlers, workout\u002F24-7 data handlers, incoming provider webhooks, coverage declarations, coverage docs, provider sync\u002Fbackfill, and provider-specific tests → [provider-integrations](sub-skills\u002Fprovider-integrations\u002FSKILL.md).\n- React portal routes, protected auth layout, dashboard\u002Fusers\u002Fsettings\u002Fcoverage\u002Fsync\u002Fwebhooks pages, API hooks\u002Fservices\u002Fquery keys, runtime `VITE_API_URL`, TanStack Router\u002FQuery, components, styling, and frontend test\u002Flint\u002Fbuild work → [frontend-portal](sub-skills\u002Ffrontend-portal\u002FSKILL.md).\n- FastMCP server startup, assistant configuration, MCP tools, REST client behavior, prompts, mocked MCP tests, and MCP API-key\u002Fbackend failure handling → [mcp-server](sub-skills\u002Fmcp-server\u002FSKILL.md).\n\n## Read shared references\n\n- [setup.md](references\u002Fsetup.md) — prerequisites, install commands, service topology, and safe validation commands.\n- [architecture.md](references\u002Farchitecture.md) — monorepo package map, backend\u002Fprovider\u002Ffrontend\u002FMCP data flow, and cross-skill ownership.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) — shared install\u002Fimport\u002Fservice\u002Fconfig\u002Fcredential failures and where to route deeper debugging.\n- [repo-provenance.md](references\u002Frepo-provenance.md) — source snapshot for staleness checks before refreshing this skill.\n\nRun the safe root checker when a checkout is available:\n\n```bash\npython skills\u002Fdisco\u002Fopen-wearables\u002Fscripts\u002Fcheck_open_wearables_install.py --repo-root .\n```\n\nThis checker is read-only. It verifies package metadata, expected directories, docs navigation presence, and local tool availability; it does not start services, install packages, call provider APIs, or read real secrets.\n\n## Package and service baseline\n\n- Backend package: `open-wearables==0.7.0`, Python `>=3.13`, FastAPI, SQLAlchemy 2.0, PostgreSQL, Redis, Celery, Svix, AWS\u002FS3 optional storage, Ruff, Ty, Pytest.\n- Frontend package: `frontend-app==0.7.0`, Node `>=22`, pnpm `>=10`, React 19, TanStack Start\u002FRouter\u002FQuery, Tailwind CSS 4, shadcn\u002Fui, Vitest, oxlint, Prettier.\n- MCP package: `open-wearables-mcp==0.1.0`, Python `>=3.13`, FastMCP, httpx, Pydantic settings, `start = app.main:main`.\n- Local stack: Docker Compose starts backend, frontend, PostgreSQL, Redis, Celery workers\u002Fbeat\u002FFlower, and Svix services. Use a disposable dev\u002Ftest stack for seed\u002Freset\u002Freplay utilities.\n\n## Boundary rules\n\n- Do not commit real provider credentials, API keys, JWTs, OAuth tokens, Svix secrets, AWS keys, master encryption keys, or `.env` files.\n- Keep backend endpoint changes synchronized with frontend\u002FMCP callers and docs. External API endpoints tagged `External: *` require API Reference navigation updates.\n- Provider coverage is the source of truth for `\u002Fapi\u002Fv1\u002Fmeta\u002Fcoverage` and the portal coverage matrix; changes belong in `provider-integrations` even when surfaced in backend routes or frontend UI.\n- MCP is REST-client-driven. Do not bypass the backend by importing backend database models or direct DB access into the MCP package.\n- Runtime frontend API URL must go through `resolveApiUrl()` \u002F `API_CONFIG.baseUrl`; do not inline `import.meta.env.VITE_API_URL` in application code.\n- Prefer focused native checks after edits: backend targeted pytest, provider coverage\u002Fimport tests, frontend Vitest\u002Flint\u002Fbuild when dependencies are installed, and MCP mocked pytest.\n\n## Staleness check\n\nBefore relying on this skill for a different checkout, read [repo-provenance.md](references\u002Frepo-provenance.md). If the commit, package versions, route\u002Fplugin entry points, provider inventory, frontend scripts, or MCP tool names changed, use `refresh-repo-skill` rather than patching this skill by hand.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables",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 open-wearables",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill open-wearables",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill open-wearables","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Farchitecture.md","REFERENCE","参考文档",6443,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Freferences\u002Farchitecture.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",3161,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",418,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsetup.md",5544,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Freferences\u002Fsetup.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",5338,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_open_wearables_install.py","SCRIPT","脚本",10052,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-wearables\u002Fscripts\u002Fcheck_open_wearables_install.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",[],[]]