[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y33FWMZNTGS2C3TJP2AQ9":3,"skill-same:01M78Y33FWMZNTGS2C3TJP2AQ9":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},"01M78Y33FWMZNTGS2C3TJP2AQ9","onnx-and-model-io",null,"Use Hummingbird's ONNX backend, ONNX-ML source conversion, and container save\u002Fload workflows.","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\u002Fonnx-and-model-io\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: onnx-and-model-io\ndescription: \"Use Hummingbird's ONNX backend, ONNX-ML source conversion, and\n  container save\u002Fload workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# ONNX and Model I\u002FO\n\nUse this sub-skill when a task mentions ONNX output, ONNX-ML input models,\n`onnxmltools`, `skl2onnx`, `onnxruntime`, `ONNXContainer`, saving a Hummingbird\nmodel, loading a saved digest, or deciding whether `override_flag=True` is safe.\n\n## Fast route\n\n1. If the user only needs the basic `hummingbird.ml.convert(...)` or\n   `convert_batch(...)` call shape, route to\n   [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md) first and return\n   here for ONNX-specific dependency, tracing, and artifact choices.\n2. For ONNX output from a fitted sklearn-style model, pass representative\n   `test_input` and use `backend=\"onnx\"`; read\n   [`references\u002Fonnx-workflows.md`](references\u002Fonnx-workflows.md).\n3. For ONNX-ML `ModelProto` inputs produced by `onnxmltools` or `skl2onnx`,\n   check the ONNX-ML recipe and schema limits in\n   [`references\u002Fonnx-workflows.md`](references\u002Fonnx-workflows.md).\n4. For saved Hummingbird artifacts, load with the digest returned by `save()`\n   whenever possible; use `override_flag=True` only for trusted artifacts. Read\n   [`references\u002Fmodel-io.md`](references\u002Fmodel-io.md).\n5. When conversion or load fails, diagnose from\n   [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before\n   changing backends or bypassing integrity checks.\n\n## Bundled runtime helper\n\nRun [`scripts\u002Fonnx_conversion_smoke.py`](scripts\u002Fonnx_conversion_smoke.py) to\nvalidate a small ONNX backend conversion without relying on source notebooks or\ntests:\n\n```bash\npython scripts\u002Fonnx_conversion_smoke.py --json\npython scripts\u002Fonnx_conversion_smoke.py --onnxml --json\npython scripts\u002Fonnx_conversion_smoke.py --output hb_onnx_demo --json\n```\n\nThe default smoke trains a tiny deterministic sklearn classifier, converts it to\nHummingbird's ONNX backend, and asserts label\u002Fprobability parity. `--onnxml`\nadds an ONNX-ML source-model check when `onnxmltools`\u002F`skl2onnx` are importable.\n`--output` is the only mode that writes an artifact.\n\n## What this sub-skill owns\n\n- ONNX target backend requirements and `onnxruntime` container behavior.\n- ONNX-ML input model recipes and `test_input` behavior.\n- `constants.ONNX_TARGET_OPSET` and `constants.ONNX_OUTPUT_MODEL_NAME` usage.\n- `ONNXContainer`, `TorchContainer`, `TVMContainer`, and generic\n  `hummingbird.ml.load` save\u002Fload semantics.\n- Digest verification, bad-digest failures, and trusted override behavior.\n- Prediction interface routing by estimator kind: `predict`, `predict_proba`,\n  `transform`, `decision_function`, and `score_samples`.\n\n## Route elsewhere\n\n- Basic conversion syntax, backend aliases, not-fitted estimators, and\n  `convert_batch`: [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md).\n- LightGBM, XGBoost, SparkML, Prophet, and optional source package installation:\n  [`..\u002Foptional-source-models\u002FSKILL.md`](..\u002Foptional-source-models\u002FSKILL.md).\n- CUDA acceleration, TVM, batching\u002Fperformance tuning, and GPU-specific runtime\n  choices: [`..\u002Fadvanced-backends-and-performance\u002FSKILL.md`](..\u002Fadvanced-backends-and-performance\u002FSKILL.md).\n\n## Minimum safety rules\n\n- Do not treat `onnx` alone as sufficient for Hummingbird ONNX inference;\n  `onnxruntime` must be importable for `ONNXContainer` prediction and loading.\n- Do not bypass load integrity checks for untrusted artifacts. Prefer\n  `digest=save_return_value`; use `override_flag=True` only after an explicit\n  trust decision.\n- Do not promise CUDA, TVM, LightGBM, XGBoost, Prophet, or SparkML behavior from\n  this sub-skill; those paths are optional and routed to their owning sub-skills.\n","# ONNX and Model I\u002FO\n\nUse this sub-skill when a task mentions ONNX output, ONNX-ML input models,\n`onnxmltools`, `skl2onnx`, `onnxruntime`, `ONNXContainer`, saving a Hummingbird\nmodel, loading a saved digest, or deciding whether `override_flag=True` is safe.\n\n## Fast route\n\n1. If the user only needs the basic `hummingbird.ml.convert(...)` or\n   `convert_batch(...)` call shape, route to\n   [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md) first and return\n   here for ONNX-specific dependency, tracing, and artifact choices.\n2. For ONNX output from a fitted sklearn-style model, pass representative\n   `test_input` and use `backend=\"onnx\"`; read\n   [`references\u002Fonnx-workflows.md`](references\u002Fonnx-workflows.md).\n3. For ONNX-ML `ModelProto` inputs produced by `onnxmltools` or `skl2onnx`,\n   check the ONNX-ML recipe and schema limits in\n   [`references\u002Fonnx-workflows.md`](references\u002Fonnx-workflows.md).\n4. For saved Hummingbird artifacts, load with the digest returned by `save()`\n   whenever possible; use `override_flag=True` only for trusted artifacts. Read\n   [`references\u002Fmodel-io.md`](references\u002Fmodel-io.md).\n5. When conversion or load fails, diagnose from\n   [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before\n   changing backends or bypassing integrity checks.\n\n## Bundled runtime helper\n\nRun [`scripts\u002Fonnx_conversion_smoke.py`](scripts\u002Fonnx_conversion_smoke.py) to\nvalidate a small ONNX backend conversion without relying on source notebooks or\ntests:\n\n```bash\npython scripts\u002Fonnx_conversion_smoke.py --json\npython scripts\u002Fonnx_conversion_smoke.py --onnxml --json\npython scripts\u002Fonnx_conversion_smoke.py --output hb_onnx_demo --json\n```\n\nThe default smoke trains a tiny deterministic sklearn classifier, converts it to\nHummingbird's ONNX backend, and asserts label\u002Fprobability parity. `--onnxml`\nadds an ONNX-ML source-model check when `onnxmltools`\u002F`skl2onnx` are importable.\n`--output` is the only mode that writes an artifact.\n\n## What this sub-skill owns\n\n- ONNX target backend requirements and `onnxruntime` container behavior.\n- ONNX-ML input model recipes and `test_input` behavior.\n- `constants.ONNX_TARGET_OPSET` and `constants.ONNX_OUTPUT_MODEL_NAME` usage.\n- `ONNXContainer`, `TorchContainer`, `TVMContainer`, and generic\n  `hummingbird.ml.load` save\u002Fload semantics.\n- Digest verification, bad-digest failures, and trusted override behavior.\n- Prediction interface routing by estimator kind: `predict`, `predict_proba`,\n  `transform`, `decision_function`, and `score_samples`.\n\n## Route elsewhere\n\n- Basic conversion syntax, backend aliases, not-fitted estimators, and\n  `convert_batch`: [`..\u002Fcore-conversion\u002FSKILL.md`](..\u002Fcore-conversion\u002FSKILL.md).\n- LightGBM, XGBoost, SparkML, Prophet, and optional source package installation:\n  [`..\u002Foptional-source-models\u002FSKILL.md`](..\u002Foptional-source-models\u002FSKILL.md).\n- CUDA acceleration, TVM, batching\u002Fperformance tuning, and GPU-specific runtime\n  choices: [`..\u002Fadvanced-backends-and-performance\u002FSKILL.md`](..\u002Fadvanced-backends-and-performance\u002FSKILL.md).\n\n## Minimum safety rules\n\n- Do not treat `onnx` alone as sufficient for Hummingbird ONNX inference;\n  `onnxruntime` must be importable for `ONNXContainer` prediction and loading.\n- Do not bypass load integrity checks for untrusted artifacts. Prefer\n  `digest=save_return_value`; use `override_flag=True` only after an explicit\n  trust decision.\n- Do not promise CUDA, TVM, LightGBM, XGBoost, Prophet, or SparkML behavior from\n  this sub-skill; those paths are optional and routed to their owning sub-skills.\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\u002Fonnx-and-model-io",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 onnx-and-model-io",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill onnx-and-model-io",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill onnx-and-model-io","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fonnx-and-model-io\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmodel-io.md","REFERENCE","参考文档",5716,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fonnx-and-model-io\u002Freferences\u002Fmodel-io.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fonnx-workflows.md",7072,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fonnx-and-model-io\u002Freferences\u002Fonnx-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",7587,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fonnx-and-model-io\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fonnx_conversion_smoke.py","SCRIPT","脚本",11272,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhummingbird\u002Fsub-skills\u002Fonnx-and-model-io\u002Fscripts\u002Fonnx_conversion_smoke.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",[],[]]