[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78V8TAMVNME7HAQ57TYCM4A":3,"skill-same:01M78V8TAMVNME7HAQ57TYCM4A":71},{"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},"01M78V8TAMVNME7HAQ57TYCM4A","cuml",null,"cuML operating skill for GPU-accelerated classical ML, cuml.accel, Dask multi-GPU workflows, data utilities, and native source-build guidance.","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\u002Fcuml\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cuml\ndescription: \"cuML operating skill for GPU-accelerated classical ML, cuml.accel,\n  Dask multi-GPU workflows, data utilities, and native source-build guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# cuML\n\nUse this repo skill for NVIDIA cuML tasks: direct GPU-native Python estimators, zero-code-change `cuml.accel` acceleration, `cuml.dask` multi-GPU workflows, supporting data\u002Fmetrics\u002Fpreprocessing utilities, or cuML source-build and C++\u002FCUDA maintenance.\n\ncuML is a CUDA\u002FRAPIDS package. Direct `cuml` runtime proof requires a CUDA-capable installation and an NVIDIA GPU; CPU-only imports are not a substitute for estimator execution.\n\n## First checks\n\n1. Confirm the task is about cuML\u002FRAPIDS GPU machine learning, `cuml.accel`, `cuml.dask`, `libcuml`, or source-build\u002FC++ APIs.\n2. Read `references\u002Frepo-provenance.md` when deciding whether this skill is current for a checkout or when refreshing it.\n3. Read `references\u002Fpackage-overview.md` for package surfaces, install variants, required\u002Foptional dependencies, output\u002Fdevice\u002Fmemory behavior, and supported-version notes.\n4. Run the bundled probe when an installed package is expected:\n\n   ```bash\n   python scripts\u002Fcuml_environment_probe.py --checks import cuda\n   python scripts\u002Fcuml_environment_probe.py --checks import cuda health optional\n   ```\n\n5. If any check fails, read `references\u002Ftroubleshooting.md` before changing dependencies or broadening the scope.\n\n## Route by task\n\n| User task | Read |\n| --- | --- |\n| Write, convert, debug, or validate direct single-GPU `cuml` estimator code with `fit`, `predict`, `transform`, output types, or model persistence. | `sub-skills\u002Fpython-estimators\u002FSKILL.md` |\n| Keep existing scikit-learn, UMAP, or HDBSCAN code unchanged and accelerate it with `python -m cuml.accel`, notebook magics, environment variables, or programmatic activation. | `sub-skills\u002Fsklearn-accel\u002FSKILL.md` |\n| Build a `cuml.dask` workflow with Dask-CUDA, partitioned data, multi-GPU estimators, LocalCUDACluster, or distributed model collection. | `sub-skills\u002Fdistributed-dask\u002FSKILL.md` |\n| Generate synthetic data, split\u002Fencode\u002Fscale data, compute metrics, vectorize text, use explainers, or prepare time-series utility inputs. | `sub-skills\u002Fdata-pipeline-utilities\u002FSKILL.md` |\n| Build cuML from source, diagnose `libcuml`\u002FCMake\u002FCUDA toolchain issues, select native tests, or work with C++ examples\u002FAPIs. | `sub-skills\u002Fnative-build-and-cpp\u002FSKILL.md` |\n\n## Installation and backend guidance\n\n- Prefer the RAPIDS installation selector for current release\u002Fnightly commands and choose the CUDA\u002FPython\u002Fpackage-manager combination that matches the host.\n- Pip package names are CUDA-suffixed in current RAPIDS wheels, for example `cuml-cu12` or `cuml-cu13`; dependencies such as `libcuml`, `cudf`, `rmm`, `pylibraft`, and CuPy must match the same CUDA\u002FRAPIDS generation.\n- `cuml.dask` requires additional Dask RAPIDS dependencies (`rapids-dask-dependency`, `dask-cudf`, `raft-dask`) matching the cuML version; `dask-cuda`\u002F`dask-ml` are needed for many test or local-cluster workflows.\n- `cuml.accel` should be enabled before importing scikit-learn, UMAP, or HDBSCAN. Unsupported estimators, inputs, parameters, or versions fall back to CPU and should be diagnosed with logging\u002Fprofiling rather than treated as cuML estimator failures.\n- Source builds are separate from ordinary package use. They need a full CUDA\u002Ftoolchain\u002FRAPIDS development environment and should start with the non-mutating probe in `sub-skills\u002Fnative-build-and-cpp\u002Fscripts\u002Fsource_build_probe.py`.\n\n## Validation policy\n\n- Always validate with tiny generated data before scaling to production-sized datasets.\n- Prefer quality metrics (`accuracy_score`, `r2_score`, adjusted Rand score, trustworthiness) over exact coefficient or label equality when comparing GPU and CPU algorithms.\n- For model serialization, load only trusted pickle\u002Fjoblib artifacts. Do not unpickle data from untrusted sources.\n- For direct `cuml`, do not claim a CPU fallback. For `cuml.accel`, CPU fallback is expected for unsupported operations and should be made visible.\n- For Dask and source-build workflows, distinguish optional unverified capability from required CUDA runtime failures.\n\n## Generated helpers\n\n- `scripts\u002Fcuml_environment_probe.py`: shared import\u002FCUDA\u002Fhealth\u002Foptional dependency check for installed cuML.\n- `sub-skills\u002Fpython-estimators\u002Fscripts\u002Fsingle_gpu_estimator_smoke.py`: tiny KMeans, LinearRegression, RandomForest, and pickle checks.\n- `sub-skills\u002Fsklearn-accel\u002Fscripts\u002Fcuml_accel_smoke.py`: accelerator CLI\u002Fprogrammatic\u002Fprofiling checks.\n- `sub-skills\u002Fdistributed-dask\u002Fscripts\u002Fdask_cuml_smoke.py`: optional LocalCUDACluster + distributed KMeans smoke with missing-dependency diagnostics.\n- `sub-skills\u002Fdata-pipeline-utilities\u002Fscripts\u002Fdata_utility_smoke.py`: datasets, preprocessing, and metric checks.\n- `sub-skills\u002Fnative-build-and-cpp\u002Fscripts\u002Fsource_build_probe.py`: non-mutating source-build prerequisite probe.\n\n## Avoid using this skill when\n\n- The task is general scikit-learn usage with no GPU\u002FRAPIDS\u002FcuML surface.\n- The task is generic Dask administration rather than cuML estimators on Dask collections.\n- The task is CUDA kernel development unrelated to cuML\u002Flibcuml APIs.\n- The task requires downloading external datasets or running long benchmarks without explicit user approval.\n","# cuML\n\nUse this repo skill for NVIDIA cuML tasks: direct GPU-native Python estimators, zero-code-change `cuml.accel` acceleration, `cuml.dask` multi-GPU workflows, supporting data\u002Fmetrics\u002Fpreprocessing utilities, or cuML source-build and C++\u002FCUDA maintenance.\n\ncuML is a CUDA\u002FRAPIDS package. Direct `cuml` runtime proof requires a CUDA-capable installation and an NVIDIA GPU; CPU-only imports are not a substitute for estimator execution.\n\n## First checks\n\n1. Confirm the task is about cuML\u002FRAPIDS GPU machine learning, `cuml.accel`, `cuml.dask`, `libcuml`, or source-build\u002FC++ APIs.\n2. Read `references\u002Frepo-provenance.md` when deciding whether this skill is current for a checkout or when refreshing it.\n3. Read `references\u002Fpackage-overview.md` for package surfaces, install variants, required\u002Foptional dependencies, output\u002Fdevice\u002Fmemory behavior, and supported-version notes.\n4. Run the bundled probe when an installed package is expected:\n\n   ```bash\n   python scripts\u002Fcuml_environment_probe.py --checks import cuda\n   python scripts\u002Fcuml_environment_probe.py --checks import cuda health optional\n   ```\n\n5. If any check fails, read `references\u002Ftroubleshooting.md` before changing dependencies or broadening the scope.\n\n## Route by task\n\n| User task | Read |\n| --- | --- |\n| Write, convert, debug, or validate direct single-GPU `cuml` estimator code with `fit`, `predict`, `transform`, output types, or model persistence. | `sub-skills\u002Fpython-estimators\u002FSKILL.md` |\n| Keep existing scikit-learn, UMAP, or HDBSCAN code unchanged and accelerate it with `python -m cuml.accel`, notebook magics, environment variables, or programmatic activation. | `sub-skills\u002Fsklearn-accel\u002FSKILL.md` |\n| Build a `cuml.dask` workflow with Dask-CUDA, partitioned data, multi-GPU estimators, LocalCUDACluster, or distributed model collection. | `sub-skills\u002Fdistributed-dask\u002FSKILL.md` |\n| Generate synthetic data, split\u002Fencode\u002Fscale data, compute metrics, vectorize text, use explainers, or prepare time-series utility inputs. | `sub-skills\u002Fdata-pipeline-utilities\u002FSKILL.md` |\n| Build cuML from source, diagnose `libcuml`\u002FCMake\u002FCUDA toolchain issues, select native tests, or work with C++ examples\u002FAPIs. | `sub-skills\u002Fnative-build-and-cpp\u002FSKILL.md` |\n\n## Installation and backend guidance\n\n- Prefer the RAPIDS installation selector for current release\u002Fnightly commands and choose the CUDA\u002FPython\u002Fpackage-manager combination that matches the host.\n- Pip package names are CUDA-suffixed in current RAPIDS wheels, for example `cuml-cu12` or `cuml-cu13`; dependencies such as `libcuml`, `cudf`, `rmm`, `pylibraft`, and CuPy must match the same CUDA\u002FRAPIDS generation.\n- `cuml.dask` requires additional Dask RAPIDS dependencies (`rapids-dask-dependency`, `dask-cudf`, `raft-dask`) matching the cuML version; `dask-cuda`\u002F`dask-ml` are needed for many test or local-cluster workflows.\n- `cuml.accel` should be enabled before importing scikit-learn, UMAP, or HDBSCAN. Unsupported estimators, inputs, parameters, or versions fall back to CPU and should be diagnosed with logging\u002Fprofiling rather than treated as cuML estimator failures.\n- Source builds are separate from ordinary package use. They need a full CUDA\u002Ftoolchain\u002FRAPIDS development environment and should start with the non-mutating probe in `sub-skills\u002Fnative-build-and-cpp\u002Fscripts\u002Fsource_build_probe.py`.\n\n## Validation policy\n\n- Always validate with tiny generated data before scaling to production-sized datasets.\n- Prefer quality metrics (`accuracy_score`, `r2_score`, adjusted Rand score, trustworthiness) over exact coefficient or label equality when comparing GPU and CPU algorithms.\n- For model serialization, load only trusted pickle\u002Fjoblib artifacts. Do not unpickle data from untrusted sources.\n- For direct `cuml`, do not claim a CPU fallback. For `cuml.accel`, CPU fallback is expected for unsupported operations and should be made visible.\n- For Dask and source-build workflows, distinguish optional unverified capability from required CUDA runtime failures.\n\n## Generated helpers\n\n- `scripts\u002Fcuml_environment_probe.py`: shared import\u002FCUDA\u002Fhealth\u002Foptional dependency check for installed cuML.\n- `sub-skills\u002Fpython-estimators\u002Fscripts\u002Fsingle_gpu_estimator_smoke.py`: tiny KMeans, LinearRegression, RandomForest, and pickle checks.\n- `sub-skills\u002Fsklearn-accel\u002Fscripts\u002Fcuml_accel_smoke.py`: accelerator CLI\u002Fprogrammatic\u002Fprofiling checks.\n- `sub-skills\u002Fdistributed-dask\u002Fscripts\u002Fdask_cuml_smoke.py`: optional LocalCUDACluster + distributed KMeans smoke with missing-dependency diagnostics.\n- `sub-skills\u002Fdata-pipeline-utilities\u002Fscripts\u002Fdata_utility_smoke.py`: datasets, preprocessing, and metric checks.\n- `sub-skills\u002Fnative-build-and-cpp\u002Fscripts\u002Fsource_build_probe.py`: non-mutating source-build prerequisite probe.\n\n## Avoid using this skill when\n\n- The task is general scikit-learn usage with no GPU\u002FRAPIDS\u002FcuML surface.\n- The task is generic Dask administration rather than cuML estimators on Dask collections.\n- The task is CUDA kernel development unrelated to cuML\u002Flibcuml APIs.\n- The task requires downloading external datasets or running long benchmarks without explicit user approval.\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\u002Fcuml",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 cuml",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill cuml",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill cuml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fpackage-overview.md","REFERENCE","参考文档",4033,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002Freferences\u002Fpackage-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2736,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",471,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5985,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcuml_environment_probe.py","SCRIPT","脚本",5517,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcuml\u002Fscripts\u002Fcuml_environment_probe.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]