[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797PD75VVF29TFTZKP12ZW0":3,"skill-same:01M797PD75VVF29TFTZKP12ZW0":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M797PD75VVF29TFTZKP12ZW0","deployments-and-agents",null,"Build, adapt, validate, and troubleshoot ZenML pipeline deployments, model or agent services, DeploymentSettings, DockerSettings packaging, deployer selection, service discovery, and credential-free ML or LLM workflow smoke patterns.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deployments-and-agents\ndescription: \"Build, adapt, validate, and troubleshoot ZenML pipeline\n  deployments, model or agent services, DeploymentSettings, DockerSettings\n  packaging, deployer selection, service discovery, and credential-free ML or\n  LLM workflow smoke patterns.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ZenML Deployments and Agents\n\nUse this sub-skill when a task mentions ZenML pipeline deployments, deployed HTTP services, real-time inference, serving ML models, deployed agents, LLM or agent examples, `DeploymentSettings`, deployment `DockerSettings`, deployers, model deployers, services, dashboard\u002Fstatic UI files, deployment invocation, or credential-free adaptation of production examples.\n\n## Route First\n\n1. Read [Agent and deployment workflows](references\u002Fagent-and-deployment-workflows.md) to choose between pipeline deployments, model-deployer\u002Fservice workflows, agent examples, deterministic fallbacks, and production-readiness checks.\n2. Read [Deployment settings](references\u002Fdeployment-settings.md) before editing `DeploymentSettings`, `DockerSettings`, CORS, secure headers, endpoint paths, dashboard files, app extensions, or deployer-specific settings.\n3. Read [Troubleshooting](references\u002Ftroubleshooting.md) before running examples, changing stack\u002Fdeployer configuration, debugging local-vs-remote behavior, or interpreting missing API keys, Docker, registries, services, and cloud credentials.\n4. Run [validate_deployment_settings.py](scripts\u002Fvalidate_deployment_settings.py) with `--example` or `--json \u003Csettings.json>` for safe schema-level validation without deploying anything.\n\n## Boundary Rules\n\n- Own example-backed production model, agent, and service workflows; pipeline deployments; `DeploymentSettings`; deployer\u002Fmodel-deployer\u002Fservice usage; HTTP invocation shape; embedded UI patterns; credential-free smoke adaptation; and deployment-specific troubleshooting.\n- Route low-level stack component implementation, integration flavor imports, service connectors, image builders, container registries, Docker daemon\u002Fbackend issues, and cloud component registration to [stacks-and-integrations](..\u002Fstacks-and-integrations\u002FSKILL.md).\n- Route basic `@step`, `@pipeline`, artifacts, materializers, schedules, hooks as authoring primitives, and local pipeline semantics to [pipeline-authoring](..\u002Fpipeline-authoring\u002FSKILL.md).\n- Route FastAPI server\u002Fstore internals, REST routers, SQLModel schemas, migrations, RBAC, triggers, and server dependency wiring to [server-and-stores](..\u002Fserver-and-stores\u002FSKILL.md).\n- Route CLI\u002Fclient resource audits, `zenml deployment list\u002Fdescribe\u002Finvoke` command behavior, login\u002Fconnect, filters, secrets, and project\u002Fstack listing to [cli-and-client](..\u002Fcli-and-client\u002FSKILL.md).\n- Route repository test selection, formatting, linting, docs maintenance, and CI-equivalent checks to [maintenance](..\u002Fmaintenance\u002FSKILL.md).\n\n## Working Pattern\n\n- Classify the serving target first: pipeline deployment for a long-running HTTP service, batch\u002Fsnapshot execution for one-off work, or legacy\u002Fspecialized model deployer only when an integration explicitly requires model-server semantics.\n- Make deployable pipelines accept explicit JSON-serializable parameters with defaults, return JSON-serializable outputs or stable artifacts, and keep heavyweight models\u002Fresources loaded through startup hooks or deployment-service state.\n- Keep agent workflows credential-aware: use deterministic fallbacks, stubs, or skipped branches when API keys, network, LLM providers, Docker, services, or cloud credentials are unavailable.\n- Treat `DeploymentSettings` as ASGI application configuration and `DockerSettings` as image\u002Fruntime packaging; validate both before changing stack\u002Fdeployer infrastructure.\n- Prefer local, credential-free checks first: static code review, `py_compile`, settings validation, import checks, and small synthetic payloads. Deploy, invoke, start services, build images, or call LLMs only after the user explicitly authorizes the environment and credentials.\n\n## Safe Validation\n\n- `python scripts\u002Fvalidate_deployment_settings.py --help` shows supported validation modes.\n- `python scripts\u002Fvalidate_deployment_settings.py --example` prints and validates a tiny, credential-free deployment plus Docker settings payload.\n- `python scripts\u002Fvalidate_deployment_settings.py --json deployment_settings.json` validates a user-supplied JSON payload containing `deployment` and\u002For `docker` settings without loading source hooks, running pipelines, starting servers, using Docker, or reading credentials.\n","# ZenML Deployments and Agents\n\nUse this sub-skill when a task mentions ZenML pipeline deployments, deployed HTTP services, real-time inference, serving ML models, deployed agents, LLM or agent examples, `DeploymentSettings`, deployment `DockerSettings`, deployers, model deployers, services, dashboard\u002Fstatic UI files, deployment invocation, or credential-free adaptation of production examples.\n\n## Route First\n\n1. Read [Agent and deployment workflows](references\u002Fagent-and-deployment-workflows.md) to choose between pipeline deployments, model-deployer\u002Fservice workflows, agent examples, deterministic fallbacks, and production-readiness checks.\n2. Read [Deployment settings](references\u002Fdeployment-settings.md) before editing `DeploymentSettings`, `DockerSettings`, CORS, secure headers, endpoint paths, dashboard files, app extensions, or deployer-specific settings.\n3. Read [Troubleshooting](references\u002Ftroubleshooting.md) before running examples, changing stack\u002Fdeployer configuration, debugging local-vs-remote behavior, or interpreting missing API keys, Docker, registries, services, and cloud credentials.\n4. Run [validate_deployment_settings.py](scripts\u002Fvalidate_deployment_settings.py) with `--example` or `--json \u003Csettings.json>` for safe schema-level validation without deploying anything.\n\n## Boundary Rules\n\n- Own example-backed production model, agent, and service workflows; pipeline deployments; `DeploymentSettings`; deployer\u002Fmodel-deployer\u002Fservice usage; HTTP invocation shape; embedded UI patterns; credential-free smoke adaptation; and deployment-specific troubleshooting.\n- Route low-level stack component implementation, integration flavor imports, service connectors, image builders, container registries, Docker daemon\u002Fbackend issues, and cloud component registration to [stacks-and-integrations](..\u002Fstacks-and-integrations\u002FSKILL.md).\n- Route basic `@step`, `@pipeline`, artifacts, materializers, schedules, hooks as authoring primitives, and local pipeline semantics to [pipeline-authoring](..\u002Fpipeline-authoring\u002FSKILL.md).\n- Route FastAPI server\u002Fstore internals, REST routers, SQLModel schemas, migrations, RBAC, triggers, and server dependency wiring to [server-and-stores](..\u002Fserver-and-stores\u002FSKILL.md).\n- Route CLI\u002Fclient resource audits, `zenml deployment list\u002Fdescribe\u002Finvoke` command behavior, login\u002Fconnect, filters, secrets, and project\u002Fstack listing to [cli-and-client](..\u002Fcli-and-client\u002FSKILL.md).\n- Route repository test selection, formatting, linting, docs maintenance, and CI-equivalent checks to [maintenance](..\u002Fmaintenance\u002FSKILL.md).\n\n## Working Pattern\n\n- Classify the serving target first: pipeline deployment for a long-running HTTP service, batch\u002Fsnapshot execution for one-off work, or legacy\u002Fspecialized model deployer only when an integration explicitly requires model-server semantics.\n- Make deployable pipelines accept explicit JSON-serializable parameters with defaults, return JSON-serializable outputs or stable artifacts, and keep heavyweight models\u002Fresources loaded through startup hooks or deployment-service state.\n- Keep agent workflows credential-aware: use deterministic fallbacks, stubs, or skipped branches when API keys, network, LLM providers, Docker, services, or cloud credentials are unavailable.\n- Treat `DeploymentSettings` as ASGI application configuration and `DockerSettings` as image\u002Fruntime packaging; validate both before changing stack\u002Fdeployer infrastructure.\n- Prefer local, credential-free checks first: static code review, `py_compile`, settings validation, import checks, and small synthetic payloads. Deploy, invoke, start services, build images, or call LLMs only after the user explicitly authorizes the environment and credentials.\n\n## Safe Validation\n\n- `python scripts\u002Fvalidate_deployment_settings.py --help` shows supported validation modes.\n- `python scripts\u002Fvalidate_deployment_settings.py --example` prints and validates a tiny, credential-free deployment plus Docker settings payload.\n- `python scripts\u002Fvalidate_deployment_settings.py --json deployment_settings.json` validates a user-supplied JSON payload containing `deployment` and\u002For `docker` settings without loading source hooks, running pipelines, starting servers, using Docker, or reading credentials.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill deployments-and-agents",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deployments-and-agents",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deployments-and-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-and-deployment-workflows.md","REFERENCE","参考文档",8705,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002Freferences\u002Fagent-and-deployment-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdeployment-settings.md",8379,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002Freferences\u002Fdeployment-settings.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9119,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_deployment_settings.py","SCRIPT","脚本",7251,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzenml\u002Fsub-skills\u002Fdeployments-and-agents\u002Fscripts\u002Fvalidate_deployment_settings.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]