[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794JMQNKVEDC8N5HVC5FEAY":3,"skill-same:01M794JMQNKVEDC8N5HVC5FEAY":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},"01M794JMQNKVEDC8N5HVC5FEAY","dataset-tools",null,"Guide SAHI COCO dataset creation, slicing, filtering, conversion, evaluation, error analysis, and visualization 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\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dataset-tools\ndescription: \"Guide SAHI COCO dataset creation, slicing, filtering, conversion,\n  evaluation, error analysis, and visualization workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Dataset Tools\n\nUse this sub-skill when a task is about SAHI dataset operations rather than model\nconstruction or per-image prediction. It covers COCO-style dataset creation,\nloading, slicing, filtering, merging, train\u002Fvalidation splitting, YOLO export,\nCOCO evaluation\u002Ferror analysis, and FiftyOne visualization.\n\n## Route here for\n\n- Building or loading COCO datasets with `Coco`, `CocoImage`,\n  `CocoAnnotation`, `CocoPrediction`, and category definitions.\n- Slicing a COCO dataset with `sahi.slicing.slice_coco` or `sahi coco slice`.\n- Remapping\u002Ffiltering categories, clipping boxes to image dimensions, keeping or\n  dropping negative images, subsampling\u002Fupsampling, merging datasets, and\n  train\u002Fvalidation splitting.\n- Exporting COCO datasets to YOLO\u002FUltralytics layout with `sahi coco yolo` or\n  the `Coco` export helpers.\n- Running COCO evaluation, error-analysis plots, or FiftyOne visualization when\n  optional dependencies are available.\n\n## Route away\n\n- Per-image prediction, sliced inference, model loading, or detector backend\n  setup: use the sliced-inference and model-integrations sibling sub-skills.\n- Low-level conversion between SAHI prediction\u002Fresult objects and annotation\n  objects: use the annotations-and-results sibling sub-skill.\n\n## Operating references\n\n1. Read [COCO CLI and API](references\u002Fcoco-cli-and-api.md) for SAHI dataset APIs,\n   CLI commands, required optional dependencies, and workflow recipes.\n2. Read [Data formats and output layouts](references\u002Fdata-formats.md) before\n   writing or consuming COCO JSON, sliced datasets, YOLO exports, COCO result\n   JSON, evaluation outputs, or FiftyOne inputs.\n3. Read [Troubleshooting](references\u002Ftroubleshooting.md) when loading fails,\n   categories do not match, negative samples disappear, boxes are clipped or\n   invalid, evaluation dependencies are missing, FiftyOne does not launch, or\n   YOLO symlinks fail.\n4. For a dependency-light local sanity check, run\n   `python scripts\u002Fcoco_fixture_smoke.py` from this sub-skill directory. The\n   script creates only temporary files and does not require `pycocotools`,\n   FiftyOne, network access, model weights, or training.\n\n## Minimal decision checklist\n\n- Confirm whether the task needs API usage, CLI usage, or both.\n- Confirm the image directory that `images[*].file_name` resolves against.\n- Decide whether images without annotations must be preserved\n  (`ignore_negative_samples=False`) or excluded.\n- Decide whether category IDs must be remapped before splitting or YOLO export.\n- Treat `pycocotools` and FiftyOne as optional: guard those workflows and provide\n  a fallback JSON validation path when they are unavailable.\n","# Dataset Tools\n\nUse this sub-skill when a task is about SAHI dataset operations rather than model\nconstruction or per-image prediction. It covers COCO-style dataset creation,\nloading, slicing, filtering, merging, train\u002Fvalidation splitting, YOLO export,\nCOCO evaluation\u002Ferror analysis, and FiftyOne visualization.\n\n## Route here for\n\n- Building or loading COCO datasets with `Coco`, `CocoImage`,\n  `CocoAnnotation`, `CocoPrediction`, and category definitions.\n- Slicing a COCO dataset with `sahi.slicing.slice_coco` or `sahi coco slice`.\n- Remapping\u002Ffiltering categories, clipping boxes to image dimensions, keeping or\n  dropping negative images, subsampling\u002Fupsampling, merging datasets, and\n  train\u002Fvalidation splitting.\n- Exporting COCO datasets to YOLO\u002FUltralytics layout with `sahi coco yolo` or\n  the `Coco` export helpers.\n- Running COCO evaluation, error-analysis plots, or FiftyOne visualization when\n  optional dependencies are available.\n\n## Route away\n\n- Per-image prediction, sliced inference, model loading, or detector backend\n  setup: use the sliced-inference and model-integrations sibling sub-skills.\n- Low-level conversion between SAHI prediction\u002Fresult objects and annotation\n  objects: use the annotations-and-results sibling sub-skill.\n\n## Operating references\n\n1. Read [COCO CLI and API](references\u002Fcoco-cli-and-api.md) for SAHI dataset APIs,\n   CLI commands, required optional dependencies, and workflow recipes.\n2. Read [Data formats and output layouts](references\u002Fdata-formats.md) before\n   writing or consuming COCO JSON, sliced datasets, YOLO exports, COCO result\n   JSON, evaluation outputs, or FiftyOne inputs.\n3. Read [Troubleshooting](references\u002Ftroubleshooting.md) when loading fails,\n   categories do not match, negative samples disappear, boxes are clipped or\n   invalid, evaluation dependencies are missing, FiftyOne does not launch, or\n   YOLO symlinks fail.\n4. For a dependency-light local sanity check, run\n   `python scripts\u002Fcoco_fixture_smoke.py` from this sub-skill directory. The\n   script creates only temporary files and does not require `pycocotools`,\n   FiftyOne, network access, model weights, or training.\n\n## Minimal decision checklist\n\n- Confirm whether the task needs API usage, CLI usage, or both.\n- Confirm the image directory that `images[*].file_name` resolves against.\n- Decide whether images without annotations must be preserved\n  (`ignore_negative_samples=False`) or excluded.\n- Decide whether category IDs must be remapped before splitting or YOLO export.\n- Treat `pycocotools` and FiftyOne as optional: guard those workflows and provide\n  a fallback JSON validation path when they are unavailable.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools",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 dataset-tools",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-tools",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcoco-cli-and-api.md","REFERENCE","参考文档",8836,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002Freferences\u002Fcoco-cli-and-api.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdata-formats.md",6924,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002Freferences\u002Fdata-formats.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6794,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcoco_fixture_smoke.py","SCRIPT","脚本",7750,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsahi\u002Fsub-skills\u002Fdataset-tools\u002Fscripts\u002Fcoco_fixture_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",[],[]]