[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797NXRMNA0TYHR5G6ZDJ3CS":3,"skill-same:01M797NXRMNA0TYHR5G6ZDJ3CS":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},"01M797NXRMNA0TYHR5G6ZDJ3CS","deployment-and-configuration",null,"Boot, configure, and operate Yuxi Docker, Lite, production, and service-topology workflows safely.","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\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deployment-and-configuration\ndescription: \"Boot, configure, and operate Yuxi Docker, Lite, production, and\n  service-topology workflows safely.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Deployment and Configuration\n\nLoad this sub-skill when the task is about starting, diagnosing, or safely\noperating a Yuxi deployment rather than changing agent, knowledge-base, CLI, or\nfrontend code.\n\n## Owns\n\n- Docker Compose development, Lite, production, and optional OCR profile\n  topology.\n- `.env` \u002F `.env.prod`, startup environment variables, administrator system\n  options, model-provider credentials, CORS, reverse proxy, MinIO public assets,\n  sandbox-provisioner, and OCR service configuration.\n- Read-only runtime checks for an already started stack.\n- Deployment troubleshooting, including logs, health endpoints, image pulls,\n  service dependencies, and service-required verification candidates.\n\n## Route elsewhere\n\n- Agent run lifecycle, Skills\u002FMCP\u002FSubAgent behavior, streaming internals, and\n  sandbox tool semantics: use the `agent-runtime` sub-skill after confirming the\n  stack is healthy.\n- Knowledge-base ingestion, parser behavior, OCR engine output, graph retrieval,\n  or chunking details: use `knowledge-and-ocr` after confirming required\n  services and credentials.\n- `yuxi` CLI usage, external API\u002FSSE client examples, and Langfuse evaluation\n  commands: use `cli-and-external-integration` after confirming base URL and\n  authentication assumptions.\n- Repository editing, tests, lint, release, or changelog workflow: use\n  `repo-development`.\n\n## Safety gates\n\n- Do not print, paste, commit, or summarize real `.env`, `.env.prod`, JWT,\n  sandbox, database, MinIO, model-provider, API-key, OCR, or Langfuse secrets.\n  Report only variable names and whether values are missing when necessary.\n- Treat initialization, image-pull, reset, seed, and service restart commands as\n  side-effectful. Run them only after explicit user approval and only in the\n  intended deployment directory.\n- Use `scripts\u002Fcheck-runtime-health.sh` for read-only checks. It does not start,\n  stop, rebuild, seed, or edit configuration.\n- Production API-key traffic must use HTTPS at the external boundary. Do not\n  recommend sending `yxkey_...` tokens over plain HTTP except for local-only\n  development.\n- External model-provider connectivity, Langfuse tracing\u002Fevaluation, cloud OCR,\n  and web search checks require credentials, network access, and explicit opt-in.\n- GPU-backed OCR services (`mineru-api`, `paddlex`) are optional service profiles;\n  do not represent them as core verified CPU capabilities.\n\n## Fast operating workflow\n\n1. Identify the deployment flavor:\n   - Development: `docker-compose.yml`, web on `http:\u002F\u002Flocalhost:5173`, API on\n     `http:\u002F\u002Flocalhost:5050`.\n   - Lite: `make up-lite`, intended to skip heavy knowledge\u002Fgraph services.\n   - Production: `docker-compose.prod.yml`, web and API behind Nginx on port 80.\n   - Optional OCR profile: `--profile all` adds MinerU and PaddleX services.\n2. Check configuration readiness without exposing values. Use\n   `references\u002Fconfiguration-and-secrets.md` for required variables and where\n   each layer is read.\n3. If a stack is already running, run the bundled read-only probe from a Yuxi\n   deployment directory:\n\n   ```bash\n   # development stack\n   scripts\u002Fcheck-runtime-health.sh --project-dir . --dev\n\n   # production stack\n   scripts\u002Fcheck-runtime-health.sh --project-dir . --prod\n   ```\n\n   If the script is copied outside the skill tree, keep its relative path local\n   to the copied location and pass `--project-dir` to the deployment directory.\n4. For failures, gather only bounded diagnostics:\n   - `docker compose ps`\n   - `docker compose logs --tail=100 api worker web sandbox-provisioner`\n   - API health endpoint response from `\u002Fapi\u002Fsystem\u002Fhealth`\n   - Browser-visible web entrypoint status\n5. Escalate to the routed sub-skill only after the relevant service health and\n   credential gate is understood.\n\n## References\n\n- `references\u002Fruntime-topology.md` — service maps, Compose flavors, ports,\n  Makefile entries, optional profiles, and native service-required candidates.\n- `references\u002Fconfiguration-and-secrets.md` — startup env, administrator system\n  options, model providers, CORS\u002Fproxy, MinIO, sandbox, OCR, API key, and\n  Langfuse safety rules.\n- `references\u002Ftroubleshooting.md` — symptom-driven diagnosis and safe next\n  commands.\n- `scripts\u002Fcheck-runtime-health.sh` — read-only health\u002Flog probe for a running\n  deployment.\n\n## Native verification candidates\n\nUse these only as verification candidates in an active Yuxi checkout or\nservice environment; this sub-skill remains self-contained for operating\ncontext.\n\n| Candidate | Requirement | Proves |\n| --- | --- | --- |\n| `docker-dev-runtime` | Docker Compose development stack; service-required | Compose health and container logs support dev deployment guidance. |\n| `docker-prod-runtime` | Production Compose plus `.env.prod` secrets; service-required\u002Freference-checked | Production topology, Nginx proxy path, and secret gates are understood. |\n| `model-provider-connectivity` | Network and explicit provider credentials; optional\u002Fexternal | Real provider calls are only tested when the user enables them. |\n| `ocr-config-center-e2e` | Running API\u002FPostgres and authenticated user; optional\u002Fservice-required | OCR configuration endpoints reflect runtime env\u002Fadmin settings. |\n","# Deployment and Configuration\n\nLoad this sub-skill when the task is about starting, diagnosing, or safely\noperating a Yuxi deployment rather than changing agent, knowledge-base, CLI, or\nfrontend code.\n\n## Owns\n\n- Docker Compose development, Lite, production, and optional OCR profile\n  topology.\n- `.env` \u002F `.env.prod`, startup environment variables, administrator system\n  options, model-provider credentials, CORS, reverse proxy, MinIO public assets,\n  sandbox-provisioner, and OCR service configuration.\n- Read-only runtime checks for an already started stack.\n- Deployment troubleshooting, including logs, health endpoints, image pulls,\n  service dependencies, and service-required verification candidates.\n\n## Route elsewhere\n\n- Agent run lifecycle, Skills\u002FMCP\u002FSubAgent behavior, streaming internals, and\n  sandbox tool semantics: use the `agent-runtime` sub-skill after confirming the\n  stack is healthy.\n- Knowledge-base ingestion, parser behavior, OCR engine output, graph retrieval,\n  or chunking details: use `knowledge-and-ocr` after confirming required\n  services and credentials.\n- `yuxi` CLI usage, external API\u002FSSE client examples, and Langfuse evaluation\n  commands: use `cli-and-external-integration` after confirming base URL and\n  authentication assumptions.\n- Repository editing, tests, lint, release, or changelog workflow: use\n  `repo-development`.\n\n## Safety gates\n\n- Do not print, paste, commit, or summarize real `.env`, `.env.prod`, JWT,\n  sandbox, database, MinIO, model-provider, API-key, OCR, or Langfuse secrets.\n  Report only variable names and whether values are missing when necessary.\n- Treat initialization, image-pull, reset, seed, and service restart commands as\n  side-effectful. Run them only after explicit user approval and only in the\n  intended deployment directory.\n- Use `scripts\u002Fcheck-runtime-health.sh` for read-only checks. It does not start,\n  stop, rebuild, seed, or edit configuration.\n- Production API-key traffic must use HTTPS at the external boundary. Do not\n  recommend sending `yxkey_...` tokens over plain HTTP except for local-only\n  development.\n- External model-provider connectivity, Langfuse tracing\u002Fevaluation, cloud OCR,\n  and web search checks require credentials, network access, and explicit opt-in.\n- GPU-backed OCR services (`mineru-api`, `paddlex`) are optional service profiles;\n  do not represent them as core verified CPU capabilities.\n\n## Fast operating workflow\n\n1. Identify the deployment flavor:\n   - Development: `docker-compose.yml`, web on `http:\u002F\u002Flocalhost:5173`, API on\n     `http:\u002F\u002Flocalhost:5050`.\n   - Lite: `make up-lite`, intended to skip heavy knowledge\u002Fgraph services.\n   - Production: `docker-compose.prod.yml`, web and API behind Nginx on port 80.\n   - Optional OCR profile: `--profile all` adds MinerU and PaddleX services.\n2. Check configuration readiness without exposing values. Use\n   `references\u002Fconfiguration-and-secrets.md` for required variables and where\n   each layer is read.\n3. If a stack is already running, run the bundled read-only probe from a Yuxi\n   deployment directory:\n\n   ```bash\n   # development stack\n   scripts\u002Fcheck-runtime-health.sh --project-dir . --dev\n\n   # production stack\n   scripts\u002Fcheck-runtime-health.sh --project-dir . --prod\n   ```\n\n   If the script is copied outside the skill tree, keep its relative path local\n   to the copied location and pass `--project-dir` to the deployment directory.\n4. For failures, gather only bounded diagnostics:\n   - `docker compose ps`\n   - `docker compose logs --tail=100 api worker web sandbox-provisioner`\n   - API health endpoint response from `\u002Fapi\u002Fsystem\u002Fhealth`\n   - Browser-visible web entrypoint status\n5. Escalate to the routed sub-skill only after the relevant service health and\n   credential gate is understood.\n\n## References\n\n- `references\u002Fruntime-topology.md` — service maps, Compose flavors, ports,\n  Makefile entries, optional profiles, and native service-required candidates.\n- `references\u002Fconfiguration-and-secrets.md` — startup env, administrator system\n  options, model providers, CORS\u002Fproxy, MinIO, sandbox, OCR, API key, and\n  Langfuse safety rules.\n- `references\u002Ftroubleshooting.md` — symptom-driven diagnosis and safe next\n  commands.\n- `scripts\u002Fcheck-runtime-health.sh` — read-only health\u002Flog probe for a running\n  deployment.\n\n## Native verification candidates\n\nUse these only as verification candidates in an active Yuxi checkout or\nservice environment; this sub-skill remains self-contained for operating\ncontext.\n\n| Candidate | Requirement | Proves |\n| --- | --- | --- |\n| `docker-dev-runtime` | Docker Compose development stack; service-required | Compose health and container logs support dev deployment guidance. |\n| `docker-prod-runtime` | Production Compose plus `.env.prod` secrets; service-required\u002Freference-checked | Production topology, Nginx proxy path, and secret gates are understood. |\n| `model-provider-connectivity` | Network and explicit provider credentials; optional\u002Fexternal | Real provider calls are only tested when the user enables them. |\n| `ocr-config-center-e2e` | Running API\u002FPostgres and authenticated user; optional\u002Fservice-required | OCR configuration endpoints reflect runtime env\u002Fadmin settings. |\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration",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 deployment-and-configuration",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-and-configuration",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-and-configuration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconfiguration-and-secrets.md","REFERENCE","参考文档",9121,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002Freferences\u002Fconfiguration-and-secrets.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fruntime-topology.md",6715,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002Freferences\u002Fruntime-topology.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6172,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck-runtime-health.sh","SCRIPT","脚本",6587,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyuxi\u002Fsub-skills\u002Fdeployment-and-configuration\u002Fscripts\u002Fcheck-runtime-health.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",[],[]]