[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WCV8CFP6VGX177CVHKWN0":3,"skill-same:01M78WCV8CFP6VGX177CVHKWN0":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},"01M78WCV8CFP6VGX177CVHKWN0","deploy-configure",null,"Guides DocsGPT development, deployment, service topology, model configuration, authentication, storage, observability, and upgrades.","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\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deploy-configure\ndescription: \"Guides DocsGPT development, deployment, service topology, model configuration, authentication, storage, observability, and upgrades.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Deploy and Configure DocsGPT\n\nUse this sub-skill for environment setup, application topology, provider\u002Fmodel configuration, auth, storage, database, queue, observability, and upgrade work.\n\n## Choose the path\n\n- **Source development**: read [development and deployment](references\u002Fdevelopment-and-deployment.md). Reuse an existing Python environment, Postgres, and Redis when healthy; use explicit dependency commands rather than setup bootstrap scripts.\n- **Container or Kubernetes deployment**: read the same reference for service topology, health gates, worker queues, reverse proxy, and rollout order.\n- **Environment\u002Fmodel configuration**: read [configuration](references\u002Fconfiguration.md), then validate custom model YAML before restart.\n- **OIDC, SCIM, RBAC, S3, migrations, or observability**: read [auth, storage, and observability](references\u002Fauth-storage-observability.md).\n- **Failure or upgrade**: read [troubleshooting](references\u002Ftroubleshooting.md) before mutating data or identity configuration.\n\n## Baseline source-development workflow\n\n1. Confirm Python 3.12, a project-local environment, and existing service health.\n2. Configure a root `.env`; do not commit it.\n3. Install the bundled 0.18.0 backend dependency snapshot explicitly (run from this sub-skill directory):\n\n   ```bash\n   python -m pip install -r ..\u002F..\u002Freferences\u002Fbackend-requirements-0.18.0.txt\n   ```\n\n   For another DocsGPT release, compare [repository provenance](..\u002F..\u002Freferences\u002Frepo-provenance.md) and refresh the skill rather than silently mixing dependency versions.\n\n4. Run the full ASGI target:\n\n   ```bash\n   uvicorn application.asgi:asgi_app --host 0.0.0.0 --port 7091 --reload\n   ```\n\n5. Start a worker in another terminal when ingestion, parsing, schedules, titles, or other background jobs are needed:\n\n   ```bash\n   celery -A application.app.celery worker -l INFO\n   ```\n\n   On macOS, use `python -m celery -A application.app.celery worker -l INFO --pool=solo`.\n6. Run the frontend separately with its local npm dependencies.\n7. Verify `\u002Fapi\u002Fhealth`, `\u002Fapi\u002Fconfig`, one model listing, and one bounded task before broader testing.\n\nFlask-only development is a reduced mode: `\u002Fmcp` and native-async message-event reconnect are absent.\n\n## Service preflight\n\nUse the bundled checker before blaming application code:\n\n```bash\npython scripts\u002Fcheck_services.py \\\n  --postgres-uri \"$POSTGRES_URI\" \\\n  --redis-url \"$CELERY_BROKER_URL\" \\\n  --api-url http:\u002F\u002Flocalhost:7091\n```\n\nThe helper performs connection\u002Freadiness probes only. Omit secrets from pasted output.\n\n## Model catalog changes\n\nUse operator YAML through `MODELS_CONFIG_DIR` for OpenAI-compatible endpoints or extensions to registered providers. Preserve model ids after users select them.\n\n```bash\npython scripts\u002Fvalidate_model_catalog.py .\u002Fmodels-config\n```\n\nValidation checks shape, duplicate ids, supported capability fields, attachment aliases, reasoning effort, and OpenAI-compatible metadata. It does not contact providers.\n\n## Production rules\n\n- Run the ASGI app through an ASGI-capable worker. Forward SSE without proxy buffering and preserve long request timeouts deliberately.\n- Use Postgres as the user-data store. Set `AUTO_CREATE_DB=false` and `AUTO_MIGRATE=false` when migrations are controlled by CI\u002FCD.\n- Use Redis URLs consistently across web and workers. A worker without `-Q` consumes all configured queues; split `docsgpt` and `parsing` only with matching workers.\n- Treat `LOCAL_MODE_ADMIN=true` as local no-auth mode only; never use it on a networked deployment.\n- Mount model catalogs read-only, keep secrets in the platform secret store, and separate public base URLs from internal service URLs.\n- Back up Postgres and object storage before schema or data migrations.\n- Add optional services only for selected features: pgvector\u002Fvector database, S3-compatible storage, sandbox runner, OAuth connectors, telemetry collector.\n\n## Cross-skill routes\n\n- Source ingestion and worker behavior: [ingest-sources](..\u002Fingest-sources\u002FSKILL.md)\n- Vector-store and retrieval compatibility: [retrieval-vectorstores](..\u002Fretrieval-vectorstores\u002FSKILL.md)\n- Client\u002FAPI verification: [api-client-operations](..\u002Fapi-client-operations\u002FSKILL.md)\n- Sandbox and remote-device services: [tools-integrations](..\u002Ftools-integrations\u002FSKILL.md)\n","# Deploy and Configure DocsGPT\n\nUse this sub-skill for environment setup, application topology, provider\u002Fmodel configuration, auth, storage, database, queue, observability, and upgrade work.\n\n## Choose the path\n\n- **Source development**: read [development and deployment](references\u002Fdevelopment-and-deployment.md). Reuse an existing Python environment, Postgres, and Redis when healthy; use explicit dependency commands rather than setup bootstrap scripts.\n- **Container or Kubernetes deployment**: read the same reference for service topology, health gates, worker queues, reverse proxy, and rollout order.\n- **Environment\u002Fmodel configuration**: read [configuration](references\u002Fconfiguration.md), then validate custom model YAML before restart.\n- **OIDC, SCIM, RBAC, S3, migrations, or observability**: read [auth, storage, and observability](references\u002Fauth-storage-observability.md).\n- **Failure or upgrade**: read [troubleshooting](references\u002Ftroubleshooting.md) before mutating data or identity configuration.\n\n## Baseline source-development workflow\n\n1. Confirm Python 3.12, a project-local environment, and existing service health.\n2. Configure a root `.env`; do not commit it.\n3. Install the bundled 0.18.0 backend dependency snapshot explicitly (run from this sub-skill directory):\n\n   ```bash\n   python -m pip install -r ..\u002F..\u002Freferences\u002Fbackend-requirements-0.18.0.txt\n   ```\n\n   For another DocsGPT release, compare [repository provenance](..\u002F..\u002Freferences\u002Frepo-provenance.md) and refresh the skill rather than silently mixing dependency versions.\n\n4. Run the full ASGI target:\n\n   ```bash\n   uvicorn application.asgi:asgi_app --host 0.0.0.0 --port 7091 --reload\n   ```\n\n5. Start a worker in another terminal when ingestion, parsing, schedules, titles, or other background jobs are needed:\n\n   ```bash\n   celery -A application.app.celery worker -l INFO\n   ```\n\n   On macOS, use `python -m celery -A application.app.celery worker -l INFO --pool=solo`.\n6. Run the frontend separately with its local npm dependencies.\n7. Verify `\u002Fapi\u002Fhealth`, `\u002Fapi\u002Fconfig`, one model listing, and one bounded task before broader testing.\n\nFlask-only development is a reduced mode: `\u002Fmcp` and native-async message-event reconnect are absent.\n\n## Service preflight\n\nUse the bundled checker before blaming application code:\n\n```bash\npython scripts\u002Fcheck_services.py \\\n  --postgres-uri \"$POSTGRES_URI\" \\\n  --redis-url \"$CELERY_BROKER_URL\" \\\n  --api-url http:\u002F\u002Flocalhost:7091\n```\n\nThe helper performs connection\u002Freadiness probes only. Omit secrets from pasted output.\n\n## Model catalog changes\n\nUse operator YAML through `MODELS_CONFIG_DIR` for OpenAI-compatible endpoints or extensions to registered providers. Preserve model ids after users select them.\n\n```bash\npython scripts\u002Fvalidate_model_catalog.py .\u002Fmodels-config\n```\n\nValidation checks shape, duplicate ids, supported capability fields, attachment aliases, reasoning effort, and OpenAI-compatible metadata. It does not contact providers.\n\n## Production rules\n\n- Run the ASGI app through an ASGI-capable worker. Forward SSE without proxy buffering and preserve long request timeouts deliberately.\n- Use Postgres as the user-data store. Set `AUTO_CREATE_DB=false` and `AUTO_MIGRATE=false` when migrations are controlled by CI\u002FCD.\n- Use Redis URLs consistently across web and workers. A worker without `-Q` consumes all configured queues; split `docsgpt` and `parsing` only with matching workers.\n- Treat `LOCAL_MODE_ADMIN=true` as local no-auth mode only; never use it on a networked deployment.\n- Mount model catalogs read-only, keep secrets in the platform secret store, and separate public base URLs from internal service URLs.\n- Back up Postgres and object storage before schema or data migrations.\n- Add optional services only for selected features: pgvector\u002Fvector database, S3-compatible storage, sandbox runner, OAuth connectors, telemetry collector.\n\n## Cross-skill routes\n\n- Source ingestion and worker behavior: [ingest-sources](..\u002Fingest-sources\u002FSKILL.md)\n- Vector-store and retrieval compatibility: [retrieval-vectorstores](..\u002Fretrieval-vectorstores\u002FSKILL.md)\n- Client\u002FAPI verification: [api-client-operations](..\u002Fapi-client-operations\u002FSKILL.md)\n- Sandbox and remote-device services: [tools-integrations](..\u002Ftools-integrations\u002FSKILL.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\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure",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 deploy-configure",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deploy-configure",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deploy-configure","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fauth-storage-observability.md","REFERENCE","参考文档",3495,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Freferences\u002Fauth-storage-observability.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fconfiguration.md",4002,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Freferences\u002Fconfiguration.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdevelopment-and-deployment.md",3600,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Freferences\u002Fdevelopment-and-deployment.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",2849,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_services.py","SCRIPT","脚本",3191,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Fscripts\u002Fcheck_services.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fvalidate_model_catalog.py",6236,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocsgpt\u002Fsub-skills\u002Fdeploy-configure\u002Fscripts\u002Fvalidate_model_catalog.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",[],[]]