[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y6DPNDASY6NW5CD3XJNK1":3,"skill-same:01M78Y6DPNDASY6NW5CD3XJNK1":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},"01M78Y6DPNDASY6NW5CD3XJNK1","auto-ml",null,"Use Igel's AutoKeras-backed Auto-ML helpers for image, text, and structured-data task selection, IgelCNN train\u002Fevaluate\u002Fpredict behavior, and current Auto-ML CLI caveats.","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\u002Figel\u002Fsub-skills\u002Fauto-ml\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: auto-ml\ndescription: \"Use Igel's AutoKeras-backed Auto-ML helpers for image, text, and\n  structured-data task selection, IgelCNN train\u002Fevaluate\u002Fpredict behavior, and\n  current Auto-ML CLI caveats.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Auto-ML\n\nUse this sub-skill when the task is about Igel's AutoKeras path: `IgelCNN`, `igel.auto.models.Models.get`, image classification\u002Fregression, text classification\u002Fregression, structured-data AutoKeras task names, or the documented-but-missing `igel auto-train` command.\n\nStart here:\n\n- Use [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for exact `IgelCNN` constructor\u002Fmethod behavior, save\u002Fload assumptions, and supported task names.\n- Use [references\u002Fworkflows.md](references\u002Fworkflows.md) for the safe operating sequence, directory layouts, and bounded examples.\n- Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, task names, data layout, artifacts, or CLI expectations fail.\n- Use [scripts\u002Finspect_auto_ml.py](scripts\u002Finspect_auto_ml.py) for an import\u002Fsignature\u002Ftask-selector smoke check that does not train, download data, or require the original source checkout.\n\nRoute boundaries:\n\n1. Route classic CSV\u002Ftabular `igel fit`, `evaluate`, `predict`, `experiment`, `models`, `metrics`, and ONNX\u002Fexport work to [tabular-workflows](..\u002Ftabular-workflows\u002FSKILL.md); those are not AutoKeras workflows.\n2. Route repo-wide skill selection back to the [root router](..\u002F..\u002FSKILL.md) when the user is not clearly asking for Auto-ML.\n3. Route FastAPI serving, Docker, GUI, and client-request tasks away from this sub-skill; this sub-skill only covers the AutoKeras-backed training\u002Fevaluation\u002Fprediction helpers and task registry.\n4. Treat AutoKeras training as potentially expensive. Prefer import\u002Fsignature and task-selector checks before starting any run, and never make dataset downloads or long tuning loops the default helper path.\n5. Do not rely on `igel auto-train` as a real current Click CLI command. The docs mention it, but the current CLI surface does not expose that command; use the programmatic `IgelCNN` path or route to classic tabular commands when appropriate.\n","# Auto-ML\n\nUse this sub-skill when the task is about Igel's AutoKeras path: `IgelCNN`, `igel.auto.models.Models.get`, image classification\u002Fregression, text classification\u002Fregression, structured-data AutoKeras task names, or the documented-but-missing `igel auto-train` command.\n\nStart here:\n\n- Use [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for exact `IgelCNN` constructor\u002Fmethod behavior, save\u002Fload assumptions, and supported task names.\n- Use [references\u002Fworkflows.md](references\u002Fworkflows.md) for the safe operating sequence, directory layouts, and bounded examples.\n- Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, task names, data layout, artifacts, or CLI expectations fail.\n- Use [scripts\u002Finspect_auto_ml.py](scripts\u002Finspect_auto_ml.py) for an import\u002Fsignature\u002Ftask-selector smoke check that does not train, download data, or require the original source checkout.\n\nRoute boundaries:\n\n1. Route classic CSV\u002Ftabular `igel fit`, `evaluate`, `predict`, `experiment`, `models`, `metrics`, and ONNX\u002Fexport work to [tabular-workflows](..\u002Ftabular-workflows\u002FSKILL.md); those are not AutoKeras workflows.\n2. Route repo-wide skill selection back to the [root router](..\u002F..\u002FSKILL.md) when the user is not clearly asking for Auto-ML.\n3. Route FastAPI serving, Docker, GUI, and client-request tasks away from this sub-skill; this sub-skill only covers the AutoKeras-backed training\u002Fevaluation\u002Fprediction helpers and task registry.\n4. Treat AutoKeras training as potentially expensive. Prefer import\u002Fsignature and task-selector checks before starting any run, and never make dataset downloads or long tuning loops the default helper path.\n5. Do not rely on `igel auto-train` as a real current Click CLI command. The docs mention it, but the current CLI surface does not expose that command; use the programmatic `IgelCNN` path or route to classic tabular commands when appropriate.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml",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 auto-ml",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill auto-ml",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill auto-ml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",6248,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",5662,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",5248,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_auto_ml.py","SCRIPT","脚本",6957,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Figel\u002Fsub-skills\u002Fauto-ml\u002Fscripts\u002Finspect_auto_ml.py",[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",[],[]]