[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794FMM9H0RVTBP9M3AR8HDM":3,"skill-same:01M794FMM9H0RVTBP9M3AR8HDM":60},{"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},"01M794FMM9H0RVTBP9M3AR8HDM","runtime-deployment",null,"Start, self-host, debug, and deploy RocketRide runtime and engine.","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\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: runtime-deployment\ndescription: \"Start, self-host, debug, and deploy RocketRide runtime and engine.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Runtime Deployment\n\nUse this sub-skill when a task is about starting a RocketRide engine, choosing\nCloud versus self-hosting, checking runtime connectivity, explaining the native\nWebSocket\u002FDAP protocol, or deploying the engine with a release archive, source\nbuild, Docker Compose, or Helm.\n\n## Use this for\n\n- Starting a local or on-prem RocketRide engine on port `5565`\n- Choosing the right client URI for Cloud, a local binary, Docker, or Kubernetes\n- Debugging `\u002Fping`, `\u002Ftask\u002Fservice`, WebSocket upgrades, auth, and task events\n- Explaining which SDK calls map to which DAP-style runtime commands\n- Planning release-archive, source-build, Docker Compose, or Helm deployments\n- Reasoning about observability events, trace levels, and runtime metrics\n- Placing provider API keys, database credentials, and vector-store settings in\n  the engine environment without hardcoding secrets in `.pipe` files\n\n## Do not use for\n\n- Python or TypeScript SDK method details and code examples → `..\u002Fsdk-clients\u002F`\n- `.pipe` design, lane wiring, or pipeline recipes → `..\u002Fpipeline-authoring\u002F`\n- Node provider schemas and generated node docs → `..\u002Fnodes-catalog\u002F`\n- VS Code extension\u002Fruntime UX and visual app surfaces → `..\u002Fide-and-apps\u002F`\n- MCP server, n8n, assistant-tool, or webhook integration details → `..\u002Fmcp-and-integrations\u002F`\n\n## Route first\n\n- Read [self-hosting and protocol](references\u002Fself-hosting-and-protocol.md) for\n  release archives, source builds, Linux runtime dependencies, the `engine`\n  command, Cloud\u002Flocal URI rules, `\u002Fping`, `\u002Ftask\u002Fservice`, DAP frames, SDK-to-\n  command mapping, auth, and observability.\n- Read [Docker and Helm](references\u002Fdocker-helm.md) for Compose services, host\n  versus container networking, Kubernetes values, secrets, external databases,\n  GPU scheduling, HA, probes, and deployment validation.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) when a runtime does not\n  listen, a client cannot connect, auth fails, observability is silent, Docker\n  networking is wrong, Helm rendering\u002Fdeployment fails, or provider credentials\n  are missing.\n\n## Safety and execution guardrails\n\n- Do not start long-running engines, Docker stacks, Kubernetes deployments, or\n  source builds unless the user explicitly asks for that action and accepts the\n  local side effects.\n- Prefer static review and command planning when the user only asks what to run.\n- Never test real provider credentials or Cloud tokens unless the user supplies\n  them for that purpose.\n- Treat source builds, Docker, Helm, GPU, database, and external-provider paths\n  as optional deployment workflows, not required smoke checks for ordinary skill\n  use.\n\n## Quick triage order\n\n1. Identify target: Cloud, release archive, source-built runtime directory,\n   Docker Compose, or Helm.\n2. Check the expected endpoint:\n   - Health: `http:\u002F\u002F\u003Chost>:5565\u002Fping`\n   - Task socket: `ws:\u002F\u002F\u003Chost>:5565\u002Ftask\u002Fservice`\n   - Cloud base URI: `https:\u002F\u002Fapi.rocketride.ai` with token auth\n3. Verify whether the problem is a listening\u002Fbinding issue, URI\u002Fscheme issue,\n   authentication issue, proxy\u002FWebSocket-upgrade issue, or provider\u002Fruntime\n   dependency issue.\n4. Use runtime events only for live observation: RocketRide observability is a\n   WebSocket event stream, not a durable metrics database.\n\n## Good output for deployment tasks\n\n- Names the target mode and exact endpoint scheme\n- Shows a health check and expected signal\n- Separates local auth assumptions from Cloud\u002Fproduction auth requirements\n- Keeps provider secrets in environment variables or Kubernetes Secrets\n- Notes when a command is heavy or starts services\n- Includes rollback\u002Fstop or dry-run guidance for Docker and Helm\n","# Runtime Deployment\n\nUse this sub-skill when a task is about starting a RocketRide engine, choosing\nCloud versus self-hosting, checking runtime connectivity, explaining the native\nWebSocket\u002FDAP protocol, or deploying the engine with a release archive, source\nbuild, Docker Compose, or Helm.\n\n## Use this for\n\n- Starting a local or on-prem RocketRide engine on port `5565`\n- Choosing the right client URI for Cloud, a local binary, Docker, or Kubernetes\n- Debugging `\u002Fping`, `\u002Ftask\u002Fservice`, WebSocket upgrades, auth, and task events\n- Explaining which SDK calls map to which DAP-style runtime commands\n- Planning release-archive, source-build, Docker Compose, or Helm deployments\n- Reasoning about observability events, trace levels, and runtime metrics\n- Placing provider API keys, database credentials, and vector-store settings in\n  the engine environment without hardcoding secrets in `.pipe` files\n\n## Do not use for\n\n- Python or TypeScript SDK method details and code examples → `..\u002Fsdk-clients\u002F`\n- `.pipe` design, lane wiring, or pipeline recipes → `..\u002Fpipeline-authoring\u002F`\n- Node provider schemas and generated node docs → `..\u002Fnodes-catalog\u002F`\n- VS Code extension\u002Fruntime UX and visual app surfaces → `..\u002Fide-and-apps\u002F`\n- MCP server, n8n, assistant-tool, or webhook integration details → `..\u002Fmcp-and-integrations\u002F`\n\n## Route first\n\n- Read [self-hosting and protocol](references\u002Fself-hosting-and-protocol.md) for\n  release archives, source builds, Linux runtime dependencies, the `engine`\n  command, Cloud\u002Flocal URI rules, `\u002Fping`, `\u002Ftask\u002Fservice`, DAP frames, SDK-to-\n  command mapping, auth, and observability.\n- Read [Docker and Helm](references\u002Fdocker-helm.md) for Compose services, host\n  versus container networking, Kubernetes values, secrets, external databases,\n  GPU scheduling, HA, probes, and deployment validation.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) when a runtime does not\n  listen, a client cannot connect, auth fails, observability is silent, Docker\n  networking is wrong, Helm rendering\u002Fdeployment fails, or provider credentials\n  are missing.\n\n## Safety and execution guardrails\n\n- Do not start long-running engines, Docker stacks, Kubernetes deployments, or\n  source builds unless the user explicitly asks for that action and accepts the\n  local side effects.\n- Prefer static review and command planning when the user only asks what to run.\n- Never test real provider credentials or Cloud tokens unless the user supplies\n  them for that purpose.\n- Treat source builds, Docker, Helm, GPU, database, and external-provider paths\n  as optional deployment workflows, not required smoke checks for ordinary skill\n  use.\n\n## Quick triage order\n\n1. Identify target: Cloud, release archive, source-built runtime directory,\n   Docker Compose, or Helm.\n2. Check the expected endpoint:\n   - Health: `http:\u002F\u002F\u003Chost>:5565\u002Fping`\n   - Task socket: `ws:\u002F\u002F\u003Chost>:5565\u002Ftask\u002Fservice`\n   - Cloud base URI: `https:\u002F\u002Fapi.rocketride.ai` with token auth\n3. Verify whether the problem is a listening\u002Fbinding issue, URI\u002Fscheme issue,\n   authentication issue, proxy\u002FWebSocket-upgrade issue, or provider\u002Fruntime\n   dependency issue.\n4. Use runtime events only for live observation: RocketRide observability is a\n   WebSocket event stream, not a durable metrics database.\n\n## Good output for deployment tasks\n\n- Names the target mode and exact endpoint scheme\n- Shows a health check and expected signal\n- Separates local auth assumptions from Cloud\u002Fproduction auth requirements\n- Keeps provider secrets in environment variables or Kubernetes Secrets\n- Notes when a command is heavy or starts services\n- Includes rollback\u002Fstop or dry-run guidance for Docker and Helm\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment",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 runtime-deployment",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill runtime-deployment",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill runtime-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdocker-helm.md","REFERENCE","参考文档",10558,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment\u002Freferences\u002Fdocker-helm.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fself-hosting-and-protocol.md",11316,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment\u002Freferences\u002Fself-hosting-and-protocol.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",11917,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fruntime-deployment\u002Freferences\u002Ftroubleshooting.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]