[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796DXE64JKDT9BYPYPY3QT8":3,"skill-same:01M796DXE64JKDT9BYPYPY3QT8":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},"01M796DXE64JKDT9BYPYPY3QT8","transforms",null,"Build TorchIO 2.0 preprocessing and augmentation pipelines with deterministic\u002Frandom transforms, composition, include\u002Fexclude routing, per-instance batches, history, inverse replay, and MONAI\u002FCornucopia adapters.","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\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: transforms\ndescription: \"Build TorchIO 2.0 preprocessing and augmentation pipelines with\n  deterministic\u002Frandom transforms, composition, include\u002Fexclude routing,\n  per-instance batches, history, inverse replay, and MONAI\u002FCornucopia adapters.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TorchIO Transforms\n\nUse this sub-skill when an agent needs to design, migrate, debug, or validate TorchIO transform pipelines. It focuses on TorchIO 2.0 APIs: transform class names are `Flip`, `Affine`, `Noise`, `Gamma`, etc. rather than older `RandomFlip`\u002F`RandomAffine` names, and random behavior is controlled by parameter ranges, `Choice`, distributions, and `p`.\n\n## Route by Task\n\n- **Build or migrate a pipeline**: start with [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for preprocessing\u002Faugmentation patterns and TorchIO 2.0 migration notes.\n- **Check constructor names and semantics**: use [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for base arguments, transform families, composition, parameter ranges, adapters, and inverse\u002Fhistory APIs.\n- **Debug transform behavior**: use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for include\u002Fexclude mistakes, no-op warnings, label interpolation, inverse limits, and optional dependency failures.\n- **Validate history\u002Finverse mechanics**: run [`scripts\u002Ftransform_history_smoke.py`](scripts\u002Ftransform_history_smoke.py) on synthetic tensors.\n- **Validate scalar\u002Flabel routing**: run [`scripts\u002Finclude_exclude_smoke.py`](scripts\u002Finclude_exclude_smoke.py) on synthetic tensors.\n\n## Core TorchIO 2.0 Rules\n\n- Construct in-memory images as `tio.ScalarImage(tensor)` and `tio.LabelMap(tensor)`, where tensors are 4D `(C, I, J, K)`.\n- Use `tio.Normalize(...)` \u002F `tio.RescaleIntensity(...)` with keyword-only range arguments such as `out_min`, `out_max`, `in_min`, and `in_max`.\n- Use one transform class for fixed and random behavior: scalar parameters are deterministic, tuples are sampled ranges, `tio.Choice([...])` samples discrete values, and `torch.distributions.Distribution` objects can supply custom sampling.\n- Apply `p` to gate a transform; in real `SubjectsBatch` inputs, transforms that support it use `per_instance=True` by default to sample\u002Fgate each element independently.\n- Use `include=[...]` and `exclude=[...]` with exact image keys from a `Subject`; intensity transforms already skip `LabelMap` images unless they are label-aware transforms.\n- Keep labels safe during spatial operations by relying on default `label_interpolation=\"nearest\"` or setting it explicitly when using `Spatial`, `Affine`, `ElasticDeformation`, `Resample`, or `Resize`.\n\n## Minimal Pipeline Pattern\n\n```python\nimport torch\nimport torchio as tio\n\nsubject = tio.Subject(\n    t1=tio.ScalarImage(torch.rand(1, 32, 32, 32)),\n    seg=tio.LabelMap(torch.randint(0, 3, (1, 32, 32, 32))),\n)\n\npipeline = tio.Compose([\n    tio.Resample(target=1.0),\n    tio.CropOrPad(target_shape=(32, 32, 32)),\n    tio.Normalize(out_min=-1, out_max=1, include=[\"t1\"]),\n    tio.Flip(axes=(0, 1, 2), flip_probability=0.5, p=0.5),\n    tio.OneOf({\n        tio.Noise(std=(0.01, 0.05)): 0.7,\n        tio.Blur(std=(0.5, 1.5)): 0.3,\n    }),\n])\n\ntransformed = pipeline(subject)\nassert transformed.t1.shape == transformed.seg.shape\nassert transformed.seg.data.dtype == subject.seg.data.dtype\nassert transformed.applied_transforms\n```\n\n## Related Sub-skills\n\n- Use the root TorchIO skill and `data-model` for `Subject`, `Image`, `ScalarImage`, `LabelMap`, `Study`, `Points`, and `BoundingBoxes` construction basics.\n- Use `patch-workflows` for `GridSampler`, `UniformSampler`, `WeightedSampler`, `LabelSampler`, `Queue`, `SubjectsLoader`, and `PatchAggregator`.\n- Use `cli-and-io` for the `torchio transform` command and file conversion workflows.\n","# TorchIO Transforms\n\nUse this sub-skill when an agent needs to design, migrate, debug, or validate TorchIO transform pipelines. It focuses on TorchIO 2.0 APIs: transform class names are `Flip`, `Affine`, `Noise`, `Gamma`, etc. rather than older `RandomFlip`\u002F`RandomAffine` names, and random behavior is controlled by parameter ranges, `Choice`, distributions, and `p`.\n\n## Route by Task\n\n- **Build or migrate a pipeline**: start with [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for preprocessing\u002Faugmentation patterns and TorchIO 2.0 migration notes.\n- **Check constructor names and semantics**: use [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for base arguments, transform families, composition, parameter ranges, adapters, and inverse\u002Fhistory APIs.\n- **Debug transform behavior**: use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for include\u002Fexclude mistakes, no-op warnings, label interpolation, inverse limits, and optional dependency failures.\n- **Validate history\u002Finverse mechanics**: run [`scripts\u002Ftransform_history_smoke.py`](scripts\u002Ftransform_history_smoke.py) on synthetic tensors.\n- **Validate scalar\u002Flabel routing**: run [`scripts\u002Finclude_exclude_smoke.py`](scripts\u002Finclude_exclude_smoke.py) on synthetic tensors.\n\n## Core TorchIO 2.0 Rules\n\n- Construct in-memory images as `tio.ScalarImage(tensor)` and `tio.LabelMap(tensor)`, where tensors are 4D `(C, I, J, K)`.\n- Use `tio.Normalize(...)` \u002F `tio.RescaleIntensity(...)` with keyword-only range arguments such as `out_min`, `out_max`, `in_min`, and `in_max`.\n- Use one transform class for fixed and random behavior: scalar parameters are deterministic, tuples are sampled ranges, `tio.Choice([...])` samples discrete values, and `torch.distributions.Distribution` objects can supply custom sampling.\n- Apply `p` to gate a transform; in real `SubjectsBatch` inputs, transforms that support it use `per_instance=True` by default to sample\u002Fgate each element independently.\n- Use `include=[...]` and `exclude=[...]` with exact image keys from a `Subject`; intensity transforms already skip `LabelMap` images unless they are label-aware transforms.\n- Keep labels safe during spatial operations by relying on default `label_interpolation=\"nearest\"` or setting it explicitly when using `Spatial`, `Affine`, `ElasticDeformation`, `Resample`, or `Resize`.\n\n## Minimal Pipeline Pattern\n\n```python\nimport torch\nimport torchio as tio\n\nsubject = tio.Subject(\n    t1=tio.ScalarImage(torch.rand(1, 32, 32, 32)),\n    seg=tio.LabelMap(torch.randint(0, 3, (1, 32, 32, 32))),\n)\n\npipeline = tio.Compose([\n    tio.Resample(target=1.0),\n    tio.CropOrPad(target_shape=(32, 32, 32)),\n    tio.Normalize(out_min=-1, out_max=1, include=[\"t1\"]),\n    tio.Flip(axes=(0, 1, 2), flip_probability=0.5, p=0.5),\n    tio.OneOf({\n        tio.Noise(std=(0.01, 0.05)): 0.7,\n        tio.Blur(std=(0.5, 1.5)): 0.3,\n    }),\n])\n\ntransformed = pipeline(subject)\nassert transformed.t1.shape == transformed.seg.shape\nassert transformed.seg.data.dtype == subject.seg.data.dtype\nassert transformed.applied_transforms\n```\n\n## Related Sub-skills\n\n- Use the root TorchIO skill and `data-model` for `Subject`, `Image`, `ScalarImage`, `LabelMap`, `Study`, `Points`, and `BoundingBoxes` construction basics.\n- Use `patch-workflows` for `GridSampler`, `UniformSampler`, `WeightedSampler`, `LabelSampler`, `Queue`, `SubjectsLoader`, and `PatchAggregator`.\n- Use `cli-and-io` for the `torchio transform` command and file conversion workflows.\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\u002Ftorchio\u002Fsub-skills\u002Ftransforms",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 transforms",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill transforms",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill transforms","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8950,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",6097,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",6893,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finclude_exclude_smoke.py","SCRIPT","脚本",2679,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002Fscripts\u002Finclude_exclude_smoke.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Ftransform_history_smoke.py",2759,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchio\u002Fsub-skills\u002Ftransforms\u002Fscripts\u002Ftransform_history_smoke.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",[],[]]