[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SWXG1G74M8AKAFPNT3894":3,"skill-same:01M78SWXG1G74M8AKAFPNT3894":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},"01M78SWXG1G74M8AKAFPNT3894","masks-and-arrays",null,"Mask-safe ground truth augmentation and in-memory grouped array workflows for Augmentor.","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\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: masks-and-arrays\ndescription: \"Mask-safe ground truth augmentation and in-memory grouped array\n  workflows for Augmentor.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Masks and Arrays\n\nUse this sub-skill when the task needs Augmentor to apply identical random transforms to an original image and its mask\u002Fground-truth companions, especially segmentation or multi-mask data.\n\n## Route here for\n\n- Directory-backed `Pipeline.ground_truth(ground_truth_directory)` workflows where original images and ground-truth images must be matched before `sample()`.\n- Verifying `get_ground_truth_paths()` pairs before running a mask-safe disk pipeline.\n- In-memory `DataPipeline(images, labels=None)` workflows where each sample is a grouped list such as `[image_array, mask_array]` or `[image_array, mask1_array, mask2_array]`.\n- `DataPipeline.sample(n)` and `DataPipeline.generator(batch_size=1)` return-shape questions, with optional labels preserved alongside grouped arrays.\n\n## Route elsewhere\n\n- Generic directory scanning, output locations, `sample()`\u002F`process()` to disk, seeding, and multithreading: use the sibling `pipeline-augmentation` sub-skill.\n- Operation selection, probability semantics, and detailed parameter ranges: use the sibling `operation-reference` sub-skill.\n- Keras, PyTorch, DataFrame, and non-mask generator integrations: use the sibling `generators-and-frameworks` sub-skill.\n\n## Fast workflow\n\n1. Choose the data path:\n   - Use `Pipeline.ground_truth()` for original and mask images already stored on disk with matching filenames and, for class data, matching class subfolders.\n   - Use `DataPipeline` for arrays already in memory or for original plus one or more masks per sample.\n2. Confirm shapes before augmentation. Directory ground-truth images should match original image dimensions; `DataPipeline` groups may mix channel counts, but each array must be convertible by Pillow.\n3. Add only operations that are valid for every member of each group. Geometric transforms are the usual mask-safe choice; color-only changes may not make sense for label masks.\n4. Inspect a tiny sample before scaling up.\n\n## Bundled references and helper\n\n- [Mask workflows](references\u002Fmask-workflows.md) covers directory ground-truth pairing, class subfolders, and `get_ground_truth_paths()`.\n- [Data formats](references\u002Fdata-formats.md) covers `DataPipeline` group\u002Flist semantics, labels, `sample()`, and `generator()`.\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers common no-match, shape, label, and no-mask pitfalls.\n- [Array smoke helper](scripts\u002Faugmentor_mask_array_smoke.py) runs a synthetic in-memory original+mask check with NumPy arrays only.\n","# Masks and Arrays\n\nUse this sub-skill when the task needs Augmentor to apply identical random transforms to an original image and its mask\u002Fground-truth companions, especially segmentation or multi-mask data.\n\n## Route here for\n\n- Directory-backed `Pipeline.ground_truth(ground_truth_directory)` workflows where original images and ground-truth images must be matched before `sample()`.\n- Verifying `get_ground_truth_paths()` pairs before running a mask-safe disk pipeline.\n- In-memory `DataPipeline(images, labels=None)` workflows where each sample is a grouped list such as `[image_array, mask_array]` or `[image_array, mask1_array, mask2_array]`.\n- `DataPipeline.sample(n)` and `DataPipeline.generator(batch_size=1)` return-shape questions, with optional labels preserved alongside grouped arrays.\n\n## Route elsewhere\n\n- Generic directory scanning, output locations, `sample()`\u002F`process()` to disk, seeding, and multithreading: use the sibling `pipeline-augmentation` sub-skill.\n- Operation selection, probability semantics, and detailed parameter ranges: use the sibling `operation-reference` sub-skill.\n- Keras, PyTorch, DataFrame, and non-mask generator integrations: use the sibling `generators-and-frameworks` sub-skill.\n\n## Fast workflow\n\n1. Choose the data path:\n   - Use `Pipeline.ground_truth()` for original and mask images already stored on disk with matching filenames and, for class data, matching class subfolders.\n   - Use `DataPipeline` for arrays already in memory or for original plus one or more masks per sample.\n2. Confirm shapes before augmentation. Directory ground-truth images should match original image dimensions; `DataPipeline` groups may mix channel counts, but each array must be convertible by Pillow.\n3. Add only operations that are valid for every member of each group. Geometric transforms are the usual mask-safe choice; color-only changes may not make sense for label masks.\n4. Inspect a tiny sample before scaling up.\n\n## Bundled references and helper\n\n- [Mask workflows](references\u002Fmask-workflows.md) covers directory ground-truth pairing, class subfolders, and `get_ground_truth_paths()`.\n- [Data formats](references\u002Fdata-formats.md) covers `DataPipeline` group\u002Flist semantics, labels, `sample()`, and `generator()`.\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers common no-match, shape, label, and no-mask pitfalls.\n- [Array smoke helper](scripts\u002Faugmentor_mask_array_smoke.py) runs a synthetic in-memory original+mask check with NumPy arrays only.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays",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 masks-and-arrays",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill masks-and-arrays",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill masks-and-arrays","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-formats.md","REFERENCE","参考文档",3942,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002Freferences\u002Fdata-formats.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmask-workflows.md",3530,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002Freferences\u002Fmask-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",3687,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Faugmentor_mask_array_smoke.py","SCRIPT","脚本",2212,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faugmentor\u002Fsub-skills\u002Fmasks-and-arrays\u002Fscripts\u002Faugmentor_mask_array_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",[],[]]