[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y39VE3AVJ297V7CQZA65Q":3,"skill-same:01M78Y39VE3AVJ297V7CQZA65Q":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},"01M78Y39VE3AVJ297V7CQZA65Q","sklearn-pipelines-and-operators",null,"Decide supported sklearn operator, pipeline, data-layout, and tree-strategy conversion tasks.","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\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sklearn-pipelines-and-operators\ndescription: \"Decide supported sklearn operator, pipeline, data-layout, and\n  tree-strategy conversion tasks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Sklearn pipelines and operators\n\nUse this sub-skill when the task is to decide whether a scikit-learn estimator, transformer, or composite pipeline can be converted by Hummingbird, how to keep its input layout valid, or how to choose a tree conversion strategy.\n\nNatural triggers include: supported sklearn operators, `MissingConverter` for a sklearn model, `Pipeline`, `ColumnTransformer`, `FeatureUnion`, pandas DataFrames, multiple inputs, `OneHotEncoder` strings, `tree_implementation`, `tree_op_precision_dtype`, and pipeline conversion parity.\n\n## Route first\n\n- Basic `hummingbird.ml.convert(...)` \u002F `convert_batch(...)` call construction and ordinary CPU parity checks: [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md).\n- LightGBM, XGBoost, SparkML, Prophet, or optional source-package dependency questions: [`..\u002Foptional-source-models\u002FSKILL.md`](..\u002Foptional-source-models\u002FSKILL.md).\n- TorchScript\u002FONNX\u002FTVM\u002FCUDA backend choice, threading, batching performance, and benchmark work: [`..\u002Fadvanced-backends-and-performance\u002FSKILL.md`](..\u002Fadvanced-backends-and-performance\u002FSKILL.md).\n\n## Use this sub-skill for\n\n1. Checking whether every sklearn operator in a model or pipeline is in a supported family.\n2. Understanding parser-level composite wrappers such as `Pipeline`, `ColumnTransformer`, `FeatureUnion`, model-selection wrappers, multi-output wrappers, bagging, and stacking.\n3. Choosing the output method family to validate after conversion: `transform`, `predict`, `predict_proba`, `decision_function`, or `score_samples`.\n4. Keeping pandas, tuple\u002Fmultiple-input, column-name, and string-feature layouts aligned between conversion and inference.\n5. Selecting and validating tree strategies: `\"gemm\"`, `\"perf_tree_trav\"`, or `\"tree_trav\"`, plus `\"float32\"`\u002F`\"float64\"` tree precision.\n\n## Operating path\n\n1. Identify the concrete fitted sklearn classes and any wrappers around them.\n2. Check [operator coverage](references\u002Foperator-coverage.md). If a wrapper is supported but a child operator is not, the whole pipeline is not convertible without changing that child.\n3. For `Pipeline`, `ColumnTransformer`, `FeatureUnion`, pandas, tuple inputs, or strings, use [pipeline and data formats](references\u002Fpipeline-data-formats.md) before writing conversion code.\n4. For tree models, decide whether to rely on Hummingbird's depth heuristic or set `extra_config` explicitly, then validate the selected inference method on representative data.\n5. If conversion or parity fails, use [troubleshooting](references\u002Ftroubleshooting.md) and route backend-only issues to the sibling backend sub-skills.\n\n## Bundled references\n\n- [Operator coverage](references\u002Foperator-coverage.md) lists supported sklearn families, parser-level wrappers, output method families, and tree strategy knobs.\n- [Pipeline and data formats](references\u002Fpipeline-data-formats.md) covers ColumnTransformer\u002FFeatureUnion behavior, pandas and tuple inputs, names, and string handling.\n- [Troubleshooting](references\u002Ftroubleshooting.md) maps common sklearn operator, pipeline, string, and tree-strategy failures to corrective actions.\n\nNo sub-skill-specific scripts are bundled for this area; use the references above and route generic conversion smokes to the core conversion sub-skill.\n","# Sklearn pipelines and operators\n\nUse this sub-skill when the task is to decide whether a scikit-learn estimator, transformer, or composite pipeline can be converted by Hummingbird, how to keep its input layout valid, or how to choose a tree conversion strategy.\n\nNatural triggers include: supported sklearn operators, `MissingConverter` for a sklearn model, `Pipeline`, `ColumnTransformer`, `FeatureUnion`, pandas DataFrames, multiple inputs, `OneHotEncoder` strings, `tree_implementation`, `tree_op_precision_dtype`, and pipeline conversion parity.\n\n## Route first\n\n- Basic `hummingbird.ml.convert(...)` \u002F `convert_batch(...)` call construction and ordinary CPU parity checks: [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md).\n- LightGBM, XGBoost, SparkML, Prophet, or optional source-package dependency questions: [`..\u002Foptional-source-models\u002FSKILL.md`](..\u002Foptional-source-models\u002FSKILL.md).\n- TorchScript\u002FONNX\u002FTVM\u002FCUDA backend choice, threading, batching performance, and benchmark work: [`..\u002Fadvanced-backends-and-performance\u002FSKILL.md`](..\u002Fadvanced-backends-and-performance\u002FSKILL.md).\n\n## Use this sub-skill for\n\n1. Checking whether every sklearn operator in a model or pipeline is in a supported family.\n2. Understanding parser-level composite wrappers such as `Pipeline`, `ColumnTransformer`, `FeatureUnion`, model-selection wrappers, multi-output wrappers, bagging, and stacking.\n3. Choosing the output method family to validate after conversion: `transform`, `predict`, `predict_proba`, `decision_function`, or `score_samples`.\n4. Keeping pandas, tuple\u002Fmultiple-input, column-name, and string-feature layouts aligned between conversion and inference.\n5. Selecting and validating tree strategies: `\"gemm\"`, `\"perf_tree_trav\"`, or `\"tree_trav\"`, plus `\"float32\"`\u002F`\"float64\"` tree precision.\n\n## Operating path\n\n1. Identify the concrete fitted sklearn classes and any wrappers around them.\n2. Check [operator coverage](references\u002Foperator-coverage.md). If a wrapper is supported but a child operator is not, the whole pipeline is not convertible without changing that child.\n3. For `Pipeline`, `ColumnTransformer`, `FeatureUnion`, pandas, tuple inputs, or strings, use [pipeline and data formats](references\u002Fpipeline-data-formats.md) before writing conversion code.\n4. For tree models, decide whether to rely on Hummingbird's depth heuristic or set `extra_config` explicitly, then validate the selected inference method on representative data.\n5. If conversion or parity fails, use [troubleshooting](references\u002Ftroubleshooting.md) and route backend-only issues to the sibling backend sub-skills.\n\n## Bundled references\n\n- [Operator coverage](references\u002Foperator-coverage.md) lists supported sklearn families, parser-level wrappers, output method families, and tree strategy knobs.\n- [Pipeline and data formats](references\u002Fpipeline-data-formats.md) covers ColumnTransformer\u002FFeatureUnion behavior, pandas and tuple inputs, names, and string handling.\n- [Troubleshooting](references\u002Ftroubleshooting.md) maps common sklearn operator, pipeline, string, and tree-strategy failures to corrective actions.\n\nNo sub-skill-specific scripts are bundled for this area; use the references above and route generic conversion smokes to the core conversion sub-skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators",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 sklearn-pipelines-and-operators",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sklearn-pipelines-and-operators",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sklearn-pipelines-and-operators","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Foperator-coverage.md","REFERENCE","参考文档",9149,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators\u002Freferences\u002Foperator-coverage.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpipeline-data-formats.md",7484,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators\u002Freferences\u002Fpipeline-data-formats.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",8726,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fsklearn-pipelines-and-operators\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",[],[]]