[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SDPXT394FFJADDPC5BRX8":3,"skill-same:01M78SDPXT394FFJADDPC5BRX8":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},"01M78SDPXT394FFJADDPC5BRX8","albumentations",null,"Build, debug, serialize, and integrate Albumentations 2.x augmentation pipelines for images, masks, bboxes, keypoints, volumes, and PyTorch-style datasets.","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\u002Falbumentations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: albumentations\ndescription: \"Build, debug, serialize, and integrate Albumentations 2.x\n  augmentation pipelines for images, masks, bboxes, keypoints, volumes, and\n  PyTorch-style datasets.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Albumentations Repo Skill\n\nUse this skill when a coding agent needs to work with Albumentations 2.x augmentation pipelines, choose transforms, validate targets, serialize\u002Freplay pipelines, or integrate augmentations into PyTorch-style data loading.\n\nAlbumentations is a NumPy\u002FOpenCV-based augmentation library for computer vision and medical-imaging workflows. This skill covers the MIT-licensed `albumentations` package at version `2.0.8`. The upstream README states that the original Albumentations repository is no longer maintained and points users to AlbumentationsX for active development; keep that maintenance status in mind when recommending new dependencies or migrations.\n\n## Quick Start\n\nFor deterministic\u002Foffline agent checks, suppress the package's import-time update check:\n\n```bash\nNO_ALBUMENTATIONS_UPDATE=1 python - \u003C\u003C'PY'\nimport albumentations as A\nprint(A.__version__)\nPY\n```\n\nMinimal image pipeline:\n\n```python\nimport albumentations as A\n\ntransform = A.Compose(\n    [\n        A.Resize(256, 256),\n        A.HorizontalFlip(p=0.5),\n        A.RandomBrightnessContrast(p=0.2),\n    ],\n    strict=True,\n    seed=137,\n)\nresult = transform(image=image_np)\naugmented = result[\"image\"]\n```\n\nInstall the base package for NumPy\u002FOpenCV augmentation:\n\n```bash\npip install albumentations\n```\n\nInstall optional integrations only when needed:\n\n```bash\npip install \"albumentations[pytorch]\"  # ToTensorV2 \u002F ToTensor3D\npip install \"albumentations[hub]\"      # Hugging Face Hub helpers\npip install \"albumentations[text]\"     # text rendering helpers\n```\n\n## Route By Task\n\n- Use `sub-skills\u002Fpipeline-composition\u002F` to build or debug `Compose`, `ReplayCompose`, `OneOf`, `SomeOf`, `RandomOrder`, `Sequential`, `OneOrOther`, `SelectiveChannelTransform`, strict validation, additional targets, seeds, and pipeline operator edits.\n- Use `sub-skills\u002Ftransform-catalog\u002F` to choose transform families and parameters for pixel\u002Fcolor\u002Fnoise\u002Fblur, crop\u002Fresize\u002Fpad\u002Fgeometric, dropout, domain adaptation, spectrogram, text, and segmentation-safe pipelines.\n- Use `sub-skills\u002Ftargets-and-formats\u002F` to handle input\u002Foutput keys, masks, bboxes, keypoints, labels, additional targets, multiple images, volumes, and 3D masks.\n- Use `sub-skills\u002Fserialization-and-reproducibility\u002F` to save\u002Fload JSON or YAML configs, replay exact random choices, inspect applied parameters, handle custom `Lambda` objects, and reason about reproducibility.\n- Use `sub-skills\u002Fframework-integration\u002F` for PyTorch-style `Dataset` integration, `ToTensorV2`, `ToTensor3D`, optional extras, tensor shapes, dtype\u002Frange expectations, and DataLoader worker seeding.\n\n## Shared References And Helpers\n\n- `references\u002Finstallation-and-maintenance.md`: package version, Python\u002Fdependency expectations, optional extras, maintenance status, and import\u002Fupdate-check behavior.\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport, OpenCV, optional dependency, offline, validation, and migration troubleshooting.\n- `references\u002Frepo-provenance.md`: source snapshot, evidence paths, and refresh baseline for staleness checks.\n- `scripts\u002Falbumentations_smoke_check.py`: tiny safe import and pipeline smoke check for installed environments.\n\n## Common Decision Points\n\n- Keep images as NumPy arrays in `H,W,C` until a final framework tensor transform; route tensor issues to `framework-integration`.\n- Use `strict=True` while developing pipelines to catch unknown keys and invalid transform arguments early; route Compose-level validation to `pipeline-composition`.\n- Declare `bbox_params` and `keypoint_params` on `Compose` whenever calls include `bboxes` or `keypoints`; route coordinate issues to `targets-and-formats`.\n- For segmentation masks, prefer nearest-neighbor mask interpolation and explicit `fill_mask`; route transform support decisions to `transform-catalog`.\n- For reproducible debugging, use `seed`, `ReplayCompose`, or `save_applied_params=True` depending on whether you need repeatable streams, exact replay, or sampled-parameter inspection.\n- Do not assume optional PyTorch, Hub, or text helpers are available from a base install; check extras and imports first.\n\n## Safety And Self-Containment\n\nThis generated skill is self-contained. Runtime instructions, references, and helper scripts live inside this skill directory and do not require opening the original repository checkout. Treat original tests and source files as provenance evidence only; use the bundled sub-skills and helpers for future work.\n","# Albumentations Repo Skill\n\nUse this skill when a coding agent needs to work with Albumentations 2.x augmentation pipelines, choose transforms, validate targets, serialize\u002Freplay pipelines, or integrate augmentations into PyTorch-style data loading.\n\nAlbumentations is a NumPy\u002FOpenCV-based augmentation library for computer vision and medical-imaging workflows. This skill covers the MIT-licensed `albumentations` package at version `2.0.8`. The upstream README states that the original Albumentations repository is no longer maintained and points users to AlbumentationsX for active development; keep that maintenance status in mind when recommending new dependencies or migrations.\n\n## Quick Start\n\nFor deterministic\u002Foffline agent checks, suppress the package's import-time update check:\n\n```bash\nNO_ALBUMENTATIONS_UPDATE=1 python - \u003C\u003C'PY'\nimport albumentations as A\nprint(A.__version__)\nPY\n```\n\nMinimal image pipeline:\n\n```python\nimport albumentations as A\n\ntransform = A.Compose(\n    [\n        A.Resize(256, 256),\n        A.HorizontalFlip(p=0.5),\n        A.RandomBrightnessContrast(p=0.2),\n    ],\n    strict=True,\n    seed=137,\n)\nresult = transform(image=image_np)\naugmented = result[\"image\"]\n```\n\nInstall the base package for NumPy\u002FOpenCV augmentation:\n\n```bash\npip install albumentations\n```\n\nInstall optional integrations only when needed:\n\n```bash\npip install \"albumentations[pytorch]\"  # ToTensorV2 \u002F ToTensor3D\npip install \"albumentations[hub]\"      # Hugging Face Hub helpers\npip install \"albumentations[text]\"     # text rendering helpers\n```\n\n## Route By Task\n\n- Use `sub-skills\u002Fpipeline-composition\u002F` to build or debug `Compose`, `ReplayCompose`, `OneOf`, `SomeOf`, `RandomOrder`, `Sequential`, `OneOrOther`, `SelectiveChannelTransform`, strict validation, additional targets, seeds, and pipeline operator edits.\n- Use `sub-skills\u002Ftransform-catalog\u002F` to choose transform families and parameters for pixel\u002Fcolor\u002Fnoise\u002Fblur, crop\u002Fresize\u002Fpad\u002Fgeometric, dropout, domain adaptation, spectrogram, text, and segmentation-safe pipelines.\n- Use `sub-skills\u002Ftargets-and-formats\u002F` to handle input\u002Foutput keys, masks, bboxes, keypoints, labels, additional targets, multiple images, volumes, and 3D masks.\n- Use `sub-skills\u002Fserialization-and-reproducibility\u002F` to save\u002Fload JSON or YAML configs, replay exact random choices, inspect applied parameters, handle custom `Lambda` objects, and reason about reproducibility.\n- Use `sub-skills\u002Fframework-integration\u002F` for PyTorch-style `Dataset` integration, `ToTensorV2`, `ToTensor3D`, optional extras, tensor shapes, dtype\u002Frange expectations, and DataLoader worker seeding.\n\n## Shared References And Helpers\n\n- `references\u002Finstallation-and-maintenance.md`: package version, Python\u002Fdependency expectations, optional extras, maintenance status, and import\u002Fupdate-check behavior.\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport, OpenCV, optional dependency, offline, validation, and migration troubleshooting.\n- `references\u002Frepo-provenance.md`: source snapshot, evidence paths, and refresh baseline for staleness checks.\n- `scripts\u002Falbumentations_smoke_check.py`: tiny safe import and pipeline smoke check for installed environments.\n\n## Common Decision Points\n\n- Keep images as NumPy arrays in `H,W,C` until a final framework tensor transform; route tensor issues to `framework-integration`.\n- Use `strict=True` while developing pipelines to catch unknown keys and invalid transform arguments early; route Compose-level validation to `pipeline-composition`.\n- Declare `bbox_params` and `keypoint_params` on `Compose` whenever calls include `bboxes` or `keypoints`; route coordinate issues to `targets-and-formats`.\n- For segmentation masks, prefer nearest-neighbor mask interpolation and explicit `fill_mask`; route transform support decisions to `transform-catalog`.\n- For reproducible debugging, use `seed`, `ReplayCompose`, or `save_applied_params=True` depending on whether you need repeatable streams, exact replay, or sampled-parameter inspection.\n- Do not assume optional PyTorch, Hub, or text helpers are available from a base install; check extras and imports first.\n\n## Safety And Self-Containment\n\nThis generated skill is self-contained. Runtime instructions, references, and helper scripts live inside this skill directory and do not require opening the original repository checkout. Treat original tests and source files as provenance evidence only; use the bundled sub-skills and helpers for future work.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Falbumentations",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 albumentations",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill albumentations",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill albumentations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-maintenance.md","REFERENCE","参考文档",2180,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002Freferences\u002Finstallation-and-maintenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1284,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",340,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",2565,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Falbumentations_smoke_check.py","SCRIPT","脚本",1444,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falbumentations\u002Fscripts\u002Falbumentations_smoke_check.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",[],[]]