[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VC8MFBWM2D8J69TXY7HM8":3,"skill-same:01M78VC8MFBWM2D8J69TXY7HM8":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},"01M78VC8MFBWM2D8J69TXY7HM8","components-projects",null,"Create and troubleshoot Dagster component-ready projects, component scaffolding, Definitions-backed components, component YAML\u002Ftemplates, and dg\u002Fcreate-dagster caveats.","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\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: components-projects\ndescription: \"Create and troubleshoot Dagster component-ready projects,\n  component scaffolding, Definitions-backed components, component\n  YAML\u002Ftemplates, and dg\u002Fcreate-dagster caveats.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Components Projects\n\nUse this sub-skill when a coding agent needs to create or inspect component-ready Dagster projects, scaffold reusable or inline components, load component trees, validate component YAML\u002Ftemplates, test component-built definitions, or explain why `dg`\u002F`create-dagster` is unavailable in a checkout.\n\n## Route Here\n\n- Creating a component-ready project or workspace with `create-dagster`, or comparing that flow with legacy `dagster project` commands.\n- Using `dg list`, `dg scaffold`, `dg check yaml`, `dg check toml`, or `dg check defs` for component projects.\n- Writing custom classes based on `dagster.components.Component`, `Resolvable`, `Model`, `ComponentLoadContext`, `Scaffolder`, or `scaffold_with`.\n- Building definitions from components, including `DefinitionsComponent`, component trees, `defs.yaml`, `component.py`, template variables, and component tests.\n- Debugging missing `dg`\u002F`create-dagster` entry points, unpublished dev dependency gaps, component import failures, schema errors, and YAML\u002Ftemplate misuse.\n\n## Route Elsewhere\n\n- Core asset, job, `Definitions`, partition, selection, and materialization design: use `..\u002Fasset-definitions\u002FSKILL.md` if that sub-skill exists.\n- General `dagster` CLI execution, `dagster dev`, and non-component local commands: use `..\u002Fcli-local-development\u002FSKILL.md` if that sub-skill exists.\n- Resource\u002Fconfig\u002Fenv-var modeling outside component YAML\u002Ftemplate loading: use `..\u002Fconfiguration-resources\u002FSKILL.md` if that sub-skill exists.\n- Broad integration libraries and provider-specific components are outside this sub-skill unless the task is about generic component registration or YAML shape.\n- Cloud-only `dg` flows requiring `dagster-cloud-cli` are intentionally treated as caveats, not as supported runtime workflows here.\n\n## Start Here\n\n1. Run `python scripts\u002Fcomponent_project_doctor.py` from this sub-skill directory, or run the script path from elsewhere, to check `dagster.components` importability and whether `dg`\u002F`create-dagster` command entry points are visible.\n2. For new projects, prefer `create-dagster project \u003Cpath>` or `create-dagster workspace \u003Cpath>` when that command is installed; use legacy `dagster project scaffold` only for older local project bootstrapping.\n3. For component authoring, create custom component types under the project package's `components` module and component instances under the project package's `defs` tree.\n4. Validate in layers: `dg check toml`, `dg check yaml`, then `dg check defs`; if `dg` is unavailable, validate Python imports and route full local CLI validation to `..\u002Fcli-local-development\u002FSKILL.md`.\n5. Keep generated component examples minimal and offline-safe; do not run cloud deployment commands or install missing unpublished dev packages unless the user explicitly approves environment mutation.\n\n## References\n\n- [Component project workflows](references\u002Fworkflows.md) for command patterns, project layout, component scaffolding, YAML\u002Ftemplate validation, component tree loading, and component tests.\n- [Component API reference](references\u002Fapi-reference.md) for the public component classes, decorators, schema models, loading helpers, and scaffolding hooks future agents most often need.\n- [Component troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport errors, optional dependency gaps, `dg`\u002F`create-dagster` caveats, schema\u002Ftemplate failures, CLI misuse, and test-loading failures.\n- [Component project doctor](scripts\u002Fcomponent_project_doctor.py) for a safe non-mutating import and command-availability probe.\n\n## Safety Notes\n\n- `create-dagster project --uv-sync` and `create-dagster workspace --uv-sync` can create virtual environments and lockfiles; ask before using install-mutating options.\n- `dg dev` starts services; do not use it as a smoke test unless the user asked to run a local server.\n- `dg` and `create-dagster` may be absent in source checkouts because their dev dependencies include unpublished or optional packages; diagnose first instead of assuming the project is broken.\n","# Components Projects\n\nUse this sub-skill when a coding agent needs to create or inspect component-ready Dagster projects, scaffold reusable or inline components, load component trees, validate component YAML\u002Ftemplates, test component-built definitions, or explain why `dg`\u002F`create-dagster` is unavailable in a checkout.\n\n## Route Here\n\n- Creating a component-ready project or workspace with `create-dagster`, or comparing that flow with legacy `dagster project` commands.\n- Using `dg list`, `dg scaffold`, `dg check yaml`, `dg check toml`, or `dg check defs` for component projects.\n- Writing custom classes based on `dagster.components.Component`, `Resolvable`, `Model`, `ComponentLoadContext`, `Scaffolder`, or `scaffold_with`.\n- Building definitions from components, including `DefinitionsComponent`, component trees, `defs.yaml`, `component.py`, template variables, and component tests.\n- Debugging missing `dg`\u002F`create-dagster` entry points, unpublished dev dependency gaps, component import failures, schema errors, and YAML\u002Ftemplate misuse.\n\n## Route Elsewhere\n\n- Core asset, job, `Definitions`, partition, selection, and materialization design: use `..\u002Fasset-definitions\u002FSKILL.md` if that sub-skill exists.\n- General `dagster` CLI execution, `dagster dev`, and non-component local commands: use `..\u002Fcli-local-development\u002FSKILL.md` if that sub-skill exists.\n- Resource\u002Fconfig\u002Fenv-var modeling outside component YAML\u002Ftemplate loading: use `..\u002Fconfiguration-resources\u002FSKILL.md` if that sub-skill exists.\n- Broad integration libraries and provider-specific components are outside this sub-skill unless the task is about generic component registration or YAML shape.\n- Cloud-only `dg` flows requiring `dagster-cloud-cli` are intentionally treated as caveats, not as supported runtime workflows here.\n\n## Start Here\n\n1. Run `python scripts\u002Fcomponent_project_doctor.py` from this sub-skill directory, or run the script path from elsewhere, to check `dagster.components` importability and whether `dg`\u002F`create-dagster` command entry points are visible.\n2. For new projects, prefer `create-dagster project \u003Cpath>` or `create-dagster workspace \u003Cpath>` when that command is installed; use legacy `dagster project scaffold` only for older local project bootstrapping.\n3. For component authoring, create custom component types under the project package's `components` module and component instances under the project package's `defs` tree.\n4. Validate in layers: `dg check toml`, `dg check yaml`, then `dg check defs`; if `dg` is unavailable, validate Python imports and route full local CLI validation to `..\u002Fcli-local-development\u002FSKILL.md`.\n5. Keep generated component examples minimal and offline-safe; do not run cloud deployment commands or install missing unpublished dev packages unless the user explicitly approves environment mutation.\n\n## References\n\n- [Component project workflows](references\u002Fworkflows.md) for command patterns, project layout, component scaffolding, YAML\u002Ftemplate validation, component tree loading, and component tests.\n- [Component API reference](references\u002Fapi-reference.md) for the public component classes, decorators, schema models, loading helpers, and scaffolding hooks future agents most often need.\n- [Component troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport errors, optional dependency gaps, `dg`\u002F`create-dagster` caveats, schema\u002Ftemplate failures, CLI misuse, and test-loading failures.\n- [Component project doctor](scripts\u002Fcomponent_project_doctor.py) for a safe non-mutating import and command-availability probe.\n\n## Safety Notes\n\n- `create-dagster project --uv-sync` and `create-dagster workspace --uv-sync` can create virtual environments and lockfiles; ask before using install-mutating options.\n- `dg dev` starts services; do not use it as a smoke test unless the user asked to run a local server.\n- `dg` and `create-dagster` may be absent in source checkouts because their dev dependencies include unpublished or optional packages; diagnose first instead of assuming the project is broken.\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\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects",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 components-projects",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill components-projects",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill components-projects","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8994,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",10366,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",10351,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcomponent_project_doctor.py","SCRIPT","脚本",4902,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdagster\u002Fsub-skills\u002Fcomponents-projects\u002Fscripts\u002Fcomponent_project_doctor.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",[],[]]