[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YAJF2J6GP951VBX60XAJ7":3,"skill-same:01M78YAJF2J6GP951VBX60XAJ7":74},{"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},"01M78YAJF2J6GP951VBX60XAJ7","imgaug",null,"Use when working with imgaug image augmentation pipelines, aligned annotations, stochastic parameters, dtype\u002Fdata utilities, or multicore augmentation for computer-vision data.","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\u002Fimgaug\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: imgaug\ndescription: \"Use when working with imgaug image augmentation pipelines, aligned\n  annotations, stochastic parameters, dtype\u002Fdata utilities, or multicore\n  augmentation for computer-vision data.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# imgaug Repo Skill\n\nUse this skill when a task involves the Python package **imgaug**: building image augmentation pipelines, applying identical transforms to annotations, choosing stochastic parameters, debugging dtype\u002Fshape issues, or running background augmentation for computer-vision training data.\n\nThis is a self-contained operating guide. Do not rely on the original repository checkout being available; use the bundled references and scripts in this skill.\n\n## First checks\n\nFor a fresh environment, install a compatible runtime before using examples:\n\n```bash\npython -m pip install \"imgaug==0.4.0\" \"numpy\u003C2\" \"opencv-python-headless\u003C4.12\"\n```\n\nIf installing from a local clone of imgaug 0.4.0, modern build isolation can fail because `setup.py` imports `pkg_resources`. Use a private environment and, only when needed, install `setuptools\u003C81` before a no-build-isolation local install. Prefer the public package install above for ordinary use.\n\nRun the bundled environment check whenever installation, imports, optional dependencies, or compatibility are uncertain:\n\n```bash\npython scripts\u002Fcheck_imgaug_env.py\n```\n\nRun a short end-to-end smoke that adapts imgaug's documented examples without display, network, or large data:\n\n```bash\npython scripts\u002Fsmoke_imgaug_workflows.py\n```\n\n## Route by task\n\n| Task signal | Read next |\n| --- | --- |\n| Build `iaa.Sequential`, `SomeOf`, `OneOf`, `Sometimes`, `WithChannels`, image-only augmentation, or choose augmenter families such as affine, blur, color, contrast, dropout, weather, superpixels, or PIL-like effects | [`sub-skills\u002Faugmentation-pipelines\u002FSKILL.md`](sub-skills\u002Faugmentation-pipelines\u002FSKILL.md) |\n| Apply one transform consistently to keypoints, bounding boxes, polygons, line strings, heatmaps, segmentation maps, or mixed `Batch`\u002F`UnnormalizedBatch` objects | [`sub-skills\u002Faugmentables-and-batches\u002FSKILL.md`](sub-skills\u002Faugmentables-and-batches\u002FSKILL.md) |\n| Control random sampling, seeds, deterministic replay, stochastic parameter distributions, dtype conversion, example quokka data, image resizing, grids, or display helpers | [`sub-skills\u002Fparameters-random-and-utilities\u002FSKILL.md`](sub-skills\u002Fparameters-random-and-utilities\u002FSKILL.md) |\n| Speed up augmentation with `augment_batches(..., background=True)`, `Augmenter.pool()`, `imgaug.multicore.Pool`, `BatchLoader`, or debug multiprocessing\u002Fperformance issues | [`sub-skills\u002Fmulticore-and-diagnostics\u002FSKILL.md`](sub-skills\u002Fmulticore-and-diagnostics\u002FSKILL.md) |\n\n## Core usage pattern\n\nMost workflows start with NumPy arrays in image shape `(N, H, W, C)` or a list of `(H, W, C)` arrays. Images should usually be RGB `uint8` with values `0..255`; convert BGR images loaded by OpenCV before color augmentations.\n\n```python\nimport numpy as np\nimport imgaug.augmenters as iaa\n\nimages = np.zeros((8, 64, 64, 3), dtype=np.uint8)\nseq = iaa.Sequential([\n    iaa.Fliplr(0.5),\n    iaa.Affine(rotate=(-10, 10)),\n    iaa.GaussianBlur(sigma=(0.0, 1.0)),\n])\nimages_aug = seq(images=images)\n```\n\nWhen images have annotations, pass them in the same call so geometric parameters are sampled once and applied consistently:\n\n```python\nimages_aug, keypoints_aug = seq(images=images, keypoints=keypoints)\n```\n\nUse `to_deterministic()` when you must apply the same sampled transform in separate calls, but prefer a single call containing all aligned augmentables when possible.\n\n## Bundled references\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) gives the package map, supported workflows, dependencies, and source-artifact replacement map.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers cross-cutting install\u002Fimport, NumPy\u002FOpenCV, dtype\u002Fshape, optional dependency, display, and multiprocessing failures.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the source snapshot used to build this skill; read it before deciding whether a checkout needs `refresh-repo-skill`.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n\n## What this skill does not cover\n\n- It does not teach general computer-vision model training frameworks beyond preparing augmented arrays\u002Fbatches for them.\n- It does not run long visual\u002Fperformance checks from the source repository; bundled scripts use tiny deterministic fixtures.\n- It does not verify optional `imagecorruptions` or `numba` acceleration unless the current task explicitly requires them.\n","# imgaug Repo Skill\n\nUse this skill when a task involves the Python package **imgaug**: building image augmentation pipelines, applying identical transforms to annotations, choosing stochastic parameters, debugging dtype\u002Fshape issues, or running background augmentation for computer-vision training data.\n\nThis is a self-contained operating guide. Do not rely on the original repository checkout being available; use the bundled references and scripts in this skill.\n\n## First checks\n\nFor a fresh environment, install a compatible runtime before using examples:\n\n```bash\npython -m pip install \"imgaug==0.4.0\" \"numpy\u003C2\" \"opencv-python-headless\u003C4.12\"\n```\n\nIf installing from a local clone of imgaug 0.4.0, modern build isolation can fail because `setup.py` imports `pkg_resources`. Use a private environment and, only when needed, install `setuptools\u003C81` before a no-build-isolation local install. Prefer the public package install above for ordinary use.\n\nRun the bundled environment check whenever installation, imports, optional dependencies, or compatibility are uncertain:\n\n```bash\npython scripts\u002Fcheck_imgaug_env.py\n```\n\nRun a short end-to-end smoke that adapts imgaug's documented examples without display, network, or large data:\n\n```bash\npython scripts\u002Fsmoke_imgaug_workflows.py\n```\n\n## Route by task\n\n| Task signal | Read next |\n| --- | --- |\n| Build `iaa.Sequential`, `SomeOf`, `OneOf`, `Sometimes`, `WithChannels`, image-only augmentation, or choose augmenter families such as affine, blur, color, contrast, dropout, weather, superpixels, or PIL-like effects | [`sub-skills\u002Faugmentation-pipelines\u002FSKILL.md`](sub-skills\u002Faugmentation-pipelines\u002FSKILL.md) |\n| Apply one transform consistently to keypoints, bounding boxes, polygons, line strings, heatmaps, segmentation maps, or mixed `Batch`\u002F`UnnormalizedBatch` objects | [`sub-skills\u002Faugmentables-and-batches\u002FSKILL.md`](sub-skills\u002Faugmentables-and-batches\u002FSKILL.md) |\n| Control random sampling, seeds, deterministic replay, stochastic parameter distributions, dtype conversion, example quokka data, image resizing, grids, or display helpers | [`sub-skills\u002Fparameters-random-and-utilities\u002FSKILL.md`](sub-skills\u002Fparameters-random-and-utilities\u002FSKILL.md) |\n| Speed up augmentation with `augment_batches(..., background=True)`, `Augmenter.pool()`, `imgaug.multicore.Pool`, `BatchLoader`, or debug multiprocessing\u002Fperformance issues | [`sub-skills\u002Fmulticore-and-diagnostics\u002FSKILL.md`](sub-skills\u002Fmulticore-and-diagnostics\u002FSKILL.md) |\n\n## Core usage pattern\n\nMost workflows start with NumPy arrays in image shape `(N, H, W, C)` or a list of `(H, W, C)` arrays. Images should usually be RGB `uint8` with values `0..255`; convert BGR images loaded by OpenCV before color augmentations.\n\n```python\nimport numpy as np\nimport imgaug.augmenters as iaa\n\nimages = np.zeros((8, 64, 64, 3), dtype=np.uint8)\nseq = iaa.Sequential([\n    iaa.Fliplr(0.5),\n    iaa.Affine(rotate=(-10, 10)),\n    iaa.GaussianBlur(sigma=(0.0, 1.0)),\n])\nimages_aug = seq(images=images)\n```\n\nWhen images have annotations, pass them in the same call so geometric parameters are sampled once and applied consistently:\n\n```python\nimages_aug, keypoints_aug = seq(images=images, keypoints=keypoints)\n```\n\nUse `to_deterministic()` when you must apply the same sampled transform in separate calls, but prefer a single call containing all aligned augmentables when possible.\n\n## Bundled references\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) gives the package map, supported workflows, dependencies, and source-artifact replacement map.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers cross-cutting install\u002Fimport, NumPy\u002FOpenCV, dtype\u002Fshape, optional dependency, display, and multiprocessing failures.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the source snapshot used to build this skill; read it before deciding whether a checkout needs `refresh-repo-skill`.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n\n## What this skill does not cover\n\n- It does not teach general computer-vision model training frameworks beyond preparing augmented arrays\u002Fbatches for them.\n- It does not run long visual\u002Fperformance checks from the source repository; bundled scripts use tiny deterministic fixtures.\n- It does not verify optional `imagecorruptions` or `numba` acceleration unless the current task explicitly requires them.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fimgaug",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 imgaug",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill imgaug",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill imgaug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",3783,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1315,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",310,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5632,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_imgaug_env.py","SCRIPT","脚本",2273,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Fscripts\u002Fcheck_imgaug_env.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fsmoke_imgaug_workflows.py",2809,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimgaug\u002Fscripts\u002Fsmoke_imgaug_workflows.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]