[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SC0J1DSX2RE9CG16SWJB7":3,"skill-same:01M78SC0J1DSX2RE9CG16SWJB7":62},{"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},"01M78SC0J1DSX2RE9CG16SWJB7","local-development",null,"Operate the Airweave local Docker stack safely: start, reuse, restart, recreate, destroy, seed environment, check ports, and recover health failures.","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\u002Flocal-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: local-development\ndescription: \"Operate the Airweave local Docker stack safely: start, reuse,\n  restart, recreate, destroy, seed environment, check ports, and recover health\n  failures.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Airweave Local Development\n\nUse this sub-skill when a future Airweave task needs the local Docker stack running or diagnosed. It owns stack bootstrap, restart\u002Frecreate\u002Fdestroy decisions, `.env` seeding, service profiles, port checks, and health recovery.\n\nDo not use this sub-skill for backend endpoint details, connector implementation, frontend page logic, MCP transport behavior, or Monke connector orchestration. After the stack is healthy, route search, collection, source-connection, connect-session, and webhook workflows to `..\u002Fbackend-api\u002FSKILL.md`.\n\n## Safe operating rules\n\n1. Work from an explicit repository root. The bundled helper accepts `--repo-root \u002Fpath\u002Fto\u002Fairweave` and works from any current directory.\n2. Prefer `status` before mutation:\n   ```bash\n   bash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n     --repo-root \"$AIRWEAVE_REPO\" status\n   ```\n3. A plain `start` is state-preserving: it seeds `.env` only when needed, starts missing\u002Fstopped services, and reuses running containers instead of deleting data.\n4. Use `restart` for already-created containers when you want to preserve Postgres\u002FRedis\u002FVespa volumes.\n5. Use `recreate` only when container state is stale or service definitions changed; it removes compose containers and volumes, then starts fresh from the current `.env`.\n6. Use `destroy` only with explicit user intent. It removes compose containers and Docker volumes; it does not intentionally edit `.env` or purge manually managed host files.\n\n## Common commands\n\n```bash\n# Fresh or reuse-safe start, including backend, frontend, connect widget, Vespa, Temporal, Redis, Postgres, Svix.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" start\n\n# Backend\u002Fservice stack without frontend UI.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" start --skip-frontend\n\n# Preserve data; restart existing containers and rerun health checks.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" restart\n\n# Recreate containers and compose volumes from current repo config.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" recreate\n\n# Destructive cleanup; add --yes for noninteractive confirmation.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" destroy\n```\n\nEquivalent environment toggles are supported for automation: `NONINTERACTIVE=1`, `SKIP_FRONTEND=1`, `SKIP_CONNECT=1`, `SKIP_LOCAL_EMBEDDINGS=1`, `ENABLE_DOCLING=1`, `VERBOSE=1`, and `QUIET=1`.\n\n## Startup decisions\n\n- Fresh checkout with no `.env`: the helper copies `.env.example`, generates missing `ENCRYPTION_KEY`, `STATE_SECRET`, `SVIX_JWT_SECRET`, `FIRST_SUPERUSER_PASSWORD`, and `POSTGRES_PASSWORD`, fills safe local defaults such as `FIRST_SUPERUSER=admin@example.com`, `POSTGRES_USER=airweave`, `SKIP_AZURE_STORAGE=true`, `STORAGE_BACKEND=filesystem`, and `SPARSE_EMBEDDER=fastembed_bm25`.\n- Embeddings: OpenAI keys prefer `openai_text_embedding_3_small` with 1536 dimensions and skip the local embeddings container. Mistral keys prefer `mistral_embed` with 1024 dimensions. No API key on a freshly seeded env uses `local_minilm` with 384 dimensions and starts the local embeddings container. An existing `.env` is not overwritten except for missing required values.\n- Reusing containers: if Airweave containers already run, `start` reports status instead of recreating them. If containers exist but are stopped, `start` brings them back up and runs health checks.\n- Optional profiles: `--skip-frontend`, `--skip-connect`, `--skip-local-embeddings`, and `--enable-docling` map to the compose profiles for frontend, connect widget, local embeddings, and Docling OCR.\n\n## Expected local service surface\n\nSee `references\u002Flocal-stack.md` for the service graph, ports, startup modes, and health commands. The primary expected endpoints are:\n\n- Backend API: `http:\u002F\u002Flocalhost:8001`, health at `\u002Fhealth` and readiness at `\u002Fhealth\u002Fready`\n- Frontend UI: `http:\u002F\u002Flocalhost:8080` unless skipped\n- Connect widget: `http:\u002F\u002Flocalhost:8082` unless skipped\n- Vespa document\u002Fquery API: `http:\u002F\u002Flocalhost:8081`, config server on `19071`\n- Temporal gRPC\u002FUI: `7233`, `8233`, and `http:\u002F\u002Flocalhost:8088`\n- PostgreSQL: `localhost:5432`; Redis: `localhost:6379`; Svix: `http:\u002F\u002Flocalhost:8071`\n- Local embeddings: host `9878` when `DENSE_EMBEDDER=local_minilm`; Docling: `5001` only when enabled\n\n## Verification hooks\n\nFor command-level checks before a real stack run:\n\n```bash\nbash -n skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh --help\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh --repo-root \"$AIRWEAVE_REPO\" status\n```\n\nFor a backend-native smoke after the stack is healthy and a Python 3.13 backend environment with `pytest`\u002F`pytest-asyncio` is active:\n\n```bash\ncd \"$AIRWEAVE_REPO\u002Fbackend\"\nTEST_ENV=local python -m pytest tests\u002Fe2e\u002Fsmoke\u002Ftest_storage_backend.py -q\n```\n\nThis storage smoke verifies the backend health endpoint, stub-source sync, ARF files, manifests, and entity files. If it fails because `stub` is unavailable, check whether internal sources are enabled for the local test environment before treating storage as broken.\n\n## Troubleshooting entry points\n\n- Docker or Compose missing, daemon down, or port conflicts: `references\u002Ftroubleshooting.md#docker-compose-and-port-failures`\n- Missing or invalid env values, including `STATE_SECRET` and `SVIX_JWT_SECRET` length validation: `references\u002Ftroubleshooting.md#environment-and-settings-failures`\n- Vespa init or schema dimension mismatch: `references\u002Ftroubleshooting.md#vespa-failures`\n- Backend, Temporal worker, Svix, or storage smoke failures: `references\u002Ftroubleshooting.md#backend-worker-svix-and-storage-failures`\n","# Airweave Local Development\n\nUse this sub-skill when a future Airweave task needs the local Docker stack running or diagnosed. It owns stack bootstrap, restart\u002Frecreate\u002Fdestroy decisions, `.env` seeding, service profiles, port checks, and health recovery.\n\nDo not use this sub-skill for backend endpoint details, connector implementation, frontend page logic, MCP transport behavior, or Monke connector orchestration. After the stack is healthy, route search, collection, source-connection, connect-session, and webhook workflows to `..\u002Fbackend-api\u002FSKILL.md`.\n\n## Safe operating rules\n\n1. Work from an explicit repository root. The bundled helper accepts `--repo-root \u002Fpath\u002Fto\u002Fairweave` and works from any current directory.\n2. Prefer `status` before mutation:\n   ```bash\n   bash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n     --repo-root \"$AIRWEAVE_REPO\" status\n   ```\n3. A plain `start` is state-preserving: it seeds `.env` only when needed, starts missing\u002Fstopped services, and reuses running containers instead of deleting data.\n4. Use `restart` for already-created containers when you want to preserve Postgres\u002FRedis\u002FVespa volumes.\n5. Use `recreate` only when container state is stale or service definitions changed; it removes compose containers and volumes, then starts fresh from the current `.env`.\n6. Use `destroy` only with explicit user intent. It removes compose containers and Docker volumes; it does not intentionally edit `.env` or purge manually managed host files.\n\n## Common commands\n\n```bash\n# Fresh or reuse-safe start, including backend, frontend, connect widget, Vespa, Temporal, Redis, Postgres, Svix.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" start\n\n# Backend\u002Fservice stack without frontend UI.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" start --skip-frontend\n\n# Preserve data; restart existing containers and rerun health checks.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" restart\n\n# Recreate containers and compose volumes from current repo config.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" recreate\n\n# Destructive cleanup; add --yes for noninteractive confirmation.\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh \\\n  --repo-root \"$AIRWEAVE_REPO\" destroy\n```\n\nEquivalent environment toggles are supported for automation: `NONINTERACTIVE=1`, `SKIP_FRONTEND=1`, `SKIP_CONNECT=1`, `SKIP_LOCAL_EMBEDDINGS=1`, `ENABLE_DOCLING=1`, `VERBOSE=1`, and `QUIET=1`.\n\n## Startup decisions\n\n- Fresh checkout with no `.env`: the helper copies `.env.example`, generates missing `ENCRYPTION_KEY`, `STATE_SECRET`, `SVIX_JWT_SECRET`, `FIRST_SUPERUSER_PASSWORD`, and `POSTGRES_PASSWORD`, fills safe local defaults such as `FIRST_SUPERUSER=admin@example.com`, `POSTGRES_USER=airweave`, `SKIP_AZURE_STORAGE=true`, `STORAGE_BACKEND=filesystem`, and `SPARSE_EMBEDDER=fastembed_bm25`.\n- Embeddings: OpenAI keys prefer `openai_text_embedding_3_small` with 1536 dimensions and skip the local embeddings container. Mistral keys prefer `mistral_embed` with 1024 dimensions. No API key on a freshly seeded env uses `local_minilm` with 384 dimensions and starts the local embeddings container. An existing `.env` is not overwritten except for missing required values.\n- Reusing containers: if Airweave containers already run, `start` reports status instead of recreating them. If containers exist but are stopped, `start` brings them back up and runs health checks.\n- Optional profiles: `--skip-frontend`, `--skip-connect`, `--skip-local-embeddings`, and `--enable-docling` map to the compose profiles for frontend, connect widget, local embeddings, and Docling OCR.\n\n## Expected local service surface\n\nSee `references\u002Flocal-stack.md` for the service graph, ports, startup modes, and health commands. The primary expected endpoints are:\n\n- Backend API: `http:\u002F\u002Flocalhost:8001`, health at `\u002Fhealth` and readiness at `\u002Fhealth\u002Fready`\n- Frontend UI: `http:\u002F\u002Flocalhost:8080` unless skipped\n- Connect widget: `http:\u002F\u002Flocalhost:8082` unless skipped\n- Vespa document\u002Fquery API: `http:\u002F\u002Flocalhost:8081`, config server on `19071`\n- Temporal gRPC\u002FUI: `7233`, `8233`, and `http:\u002F\u002Flocalhost:8088`\n- PostgreSQL: `localhost:5432`; Redis: `localhost:6379`; Svix: `http:\u002F\u002Flocalhost:8071`\n- Local embeddings: host `9878` when `DENSE_EMBEDDER=local_minilm`; Docling: `5001` only when enabled\n\n## Verification hooks\n\nFor command-level checks before a real stack run:\n\n```bash\nbash -n skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh --help\nbash skills\u002Fdisco\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh --repo-root \"$AIRWEAVE_REPO\" status\n```\n\nFor a backend-native smoke after the stack is healthy and a Python 3.13 backend environment with `pytest`\u002F`pytest-asyncio` is active:\n\n```bash\ncd \"$AIRWEAVE_REPO\u002Fbackend\"\nTEST_ENV=local python -m pytest tests\u002Fe2e\u002Fsmoke\u002Ftest_storage_backend.py -q\n```\n\nThis storage smoke verifies the backend health endpoint, stub-source sync, ARF files, manifests, and entity files. If it fails because `stub` is unavailable, check whether internal sources are enabled for the local test environment before treating storage as broken.\n\n## Troubleshooting entry points\n\n- Docker or Compose missing, daemon down, or port conflicts: `references\u002Ftroubleshooting.md#docker-compose-and-port-failures`\n- Missing or invalid env values, including `STATE_SECRET` and `SVIX_JWT_SECRET` length validation: `references\u002Ftroubleshooting.md#environment-and-settings-failures`\n- Vespa init or schema dimension mismatch: `references\u002Ftroubleshooting.md#vespa-failures`\n- Backend, Temporal worker, Svix, or storage smoke failures: `references\u002Ftroubleshooting.md#backend-worker-svix-and-storage-failures`\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\u002Flocal-development",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 local-development",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill local-development",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill local-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Flocal-stack.md","REFERENCE","参考文档",7953,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Freferences\u002Flocal-stack.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",8102,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Flocal-stack.sh","SCRIPT","脚本",25758,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fairweave\u002Fsub-skills\u002Flocal-development\u002Fscripts\u002Flocal-stack.sh",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]