[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T1ASBAMC4CBEXZ35EVCTC":3,"skill-same:01M78T1ASBAMC4CBEXZ35EVCTC":70},{"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},"01M78T1ASBAMC4CBEXZ35EVCTC","automl-gs",null,"Routes automl_gs tabular AutoML searches and the generated runtime artifacts that those searches produce.","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\u002Fautoml-gs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automl-gs\ndescription: \"Routes automl_gs tabular AutoML searches and the generated runtime\n  artifacts that those searches produce.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# automl-gs\n\nUse this root skill when the request names `automl_gs`, asks for an AutoML search on a CSV plus target field, or points at a timestamped generated folder from a previous search.\n\n## What this skill covers\n\n- Starting a bounded `automl_gs` \u002F `automl_grid_search(...)` run.\n- Choosing between the supported search frameworks: TensorFlow or XGBoost.\n- Inspecting the generated `model.py`, `pipeline.py`, encoders, metadata, and prediction outputs.\n- Troubleshooting package import problems, backend mismatches, and generated-folder runtime issues.\n\n## Route to a sub-skill\n\n- Use [grid-search](sub-skills\u002Fgrid-search\u002FSKILL.md) for a new search from `CSV + target`.\n- Use [generated-artifacts](sub-skills\u002Fgenerated-artifacts\u002FSKILL.md) for a completed timestamped folder and its `train` \u002F `predict` commands.\n\n## Read these references when needed\n\n- [workflow-overview](references\u002Fworkflow-overview.md) for the quick package map, supported outputs, and when to choose each route.\n- [troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport issues, backend mismatches, and other cross-cutting failures.\n- [repo-provenance](references\u002Frepo-provenance.md) when checking whether this skill matches the current repository revision or before refreshing it.\n\n## Install and smoke check\n\nInstall the package in the active environment, then add the backend you actually plan to use:\n\n```bash\npip install -e .\npython -m pip install xgboost\n```\n\nUse TensorFlow only when you need to exercise the legacy TensorFlow-generated path.\n\nFor a quick sanity check, run the bundled helper. Pass the backend you actually installed when you want a backend import check:\n\n```bash\npython scripts\u002Fcheck_install.py --backend xgboost\n```\n\n## Fast routing hints\n\n- If the user says “run automl-gs on this CSV”, “search hyperparameters”, or “pick a framework”, route to **grid-search**.\n- If the user says “train the generated model”, “predict from the exported folder”, or mentions `model.py` \u002F `pipeline.py`, route to **generated-artifacts**.\n- If import fails, `automl_gs -h` fails, or a subprocess launches the wrong Python, read **troubleshooting** first.\n\n## Public surface in one line\n\n`automl_gs` turns a CSV and target field into a generated model folder plus `automl_results.csv`; the exported folder then owns training, prediction, and encoder loading.\n","# automl-gs\n\nUse this root skill when the request names `automl_gs`, asks for an AutoML search on a CSV plus target field, or points at a timestamped generated folder from a previous search.\n\n## What this skill covers\n\n- Starting a bounded `automl_gs` \u002F `automl_grid_search(...)` run.\n- Choosing between the supported search frameworks: TensorFlow or XGBoost.\n- Inspecting the generated `model.py`, `pipeline.py`, encoders, metadata, and prediction outputs.\n- Troubleshooting package import problems, backend mismatches, and generated-folder runtime issues.\n\n## Route to a sub-skill\n\n- Use [grid-search](sub-skills\u002Fgrid-search\u002FSKILL.md) for a new search from `CSV + target`.\n- Use [generated-artifacts](sub-skills\u002Fgenerated-artifacts\u002FSKILL.md) for a completed timestamped folder and its `train` \u002F `predict` commands.\n\n## Read these references when needed\n\n- [workflow-overview](references\u002Fworkflow-overview.md) for the quick package map, supported outputs, and when to choose each route.\n- [troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport issues, backend mismatches, and other cross-cutting failures.\n- [repo-provenance](references\u002Frepo-provenance.md) when checking whether this skill matches the current repository revision or before refreshing it.\n\n## Install and smoke check\n\nInstall the package in the active environment, then add the backend you actually plan to use:\n\n```bash\npip install -e .\npython -m pip install xgboost\n```\n\nUse TensorFlow only when you need to exercise the legacy TensorFlow-generated path.\n\nFor a quick sanity check, run the bundled helper. Pass the backend you actually installed when you want a backend import check:\n\n```bash\npython scripts\u002Fcheck_install.py --backend xgboost\n```\n\n## Fast routing hints\n\n- If the user says “run automl-gs on this CSV”, “search hyperparameters”, or “pick a framework”, route to **grid-search**.\n- If the user says “train the generated model”, “predict from the exported folder”, or mentions `model.py` \u002F `pipeline.py`, route to **generated-artifacts**.\n- If import fails, `automl_gs -h` fails, or a subprocess launches the wrong Python, read **troubleshooting** first.\n\n## Public surface in one line\n\n`automl_gs` turns a CSV and target field into a generated model folder plus `automl_results.csv`; the exported folder then owns training, prediction, and encoder loading.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs",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 automl-gs",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill automl-gs",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill automl-gs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-provenance.md","REFERENCE","参考文档",983,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002Freferences\u002Frepo-provenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-routing-metadata.json",378,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002Freferences\u002Frepo-routing-metadata.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflow-overview.md",1904,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002Freferences\u002Fworkflow-overview.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_install.py","SCRIPT","脚本",2539,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoml-gs\u002Fscripts\u002Fcheck_install.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]