[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795SEKPJ3MA6XMXG0Y7PRQP":3,"skill-same:01M795SEKPJ3MA6XMXG0Y7PRQP":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},"01M795SEKPJ3MA6XMXG0Y7PRQP","supervision",null,"Route Supervision computer-vision package workflows for detections, annotators, datasets, tracking, metrics, and media utilities.","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\u002Fsupervision\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: supervision\ndescription: \"Route Supervision computer-vision package workflows for\n  detections, annotators, datasets, tracking, metrics, and media utilities.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Supervision\n\nUse this repo skill when a task uses the `supervision` Python package as a\ncomputer-vision utility layer: normalized detections, visual annotation, dataset\nconversion, tracking\u002Fkeypoints, evaluation metrics, image\u002Fvideo helpers, zones,\nsinks, slicers, and optional OpenCV backend behavior.\n\n## Install and minimal check\n\n```bash\npip install supervision\npython -c \"import supervision as sv; print(sv.__version__)\"\n```\n\nAdd extras only for workflows that need them:\n\n```bash\npip install \"supervision[metrics]\"   # pandas-backed metric tables and evaluation\npip install \"supervision[geotiff]\"   # rasterio\u002Fwindowed GeoTIFF slicing\n```\n\nNative OpenCV is optional. Use Supervision's fallback backend by default; install\nexactly one OpenCV wheel only when the application needs native OpenCV behavior,\nGUI windows, webcam capture, or broader codec compatibility.\n\nRun the bundled [check_supervision_install.py](scripts\u002Fcheck_supervision_install.py)\nhelper when the environment is unknown.\n\n## Start here\n\n- Read [overview](references\u002Foverview.md) for the package map, core concepts,\n  optional extras, and deprecation summary.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting\n  install\u002Fimport\u002Fbackend\u002Fdeprecation failures.\n- Read [repo provenance](references\u002Frepo-provenance.md) before deciding whether\n  this skill matches a different checkout or package version.\n\n## Route by task\n\n| User intent or signals | Sub-skill |\n| --- | --- |\n| `Detections`, model adapters, VLM parsing, compact masks, filtering, NMS\u002FNMM, zones, tiled inference, smoothing, CSV\u002FJSON sinks | [detection-and-zones](sub-skills\u002Fdetection-and-zones\u002FSKILL.md) |\n| Drawing boxes, masks, labels, traces, heatmaps, zones, comparison panels, and other high-level `scene` + detections\u002Fkeypoints visualization | [annotators](sub-skills\u002Fannotators\u002FSKILL.md) |\n| YOLO\u002FCOCO\u002FPascal VOC\u002FLabelMe\u002FCreateML dataset loading\u002Fexport, dataset splitting\u002Fmerging, classification folder datasets | [datasets](sub-skills\u002Fdatasets\u002FSKILL.md) |\n| `KeyPoints`, keypoint adapters\u002Fannotators, keypoint-to-detection conversion, tracker IDs, ByteTrack compatibility\u002Fmigration, line crossing with identity | [tracking-keypoints](sub-skills\u002Ftracking-keypoints\u002FSKILL.md) |\n| mAP, mAR, precision, recall, F1, confusion matrices, `MetricTarget`, `AveragingMethod`, dataset-backed evaluation | [metrics](sub-skills\u002Fmetrics\u002FSKILL.md) |\n| Image\u002Fvideo\u002Ffile helpers, primitive drawing, colors, geometry, notebook display, assets, OpenCV fallback\u002Fnative backend, GUI\u002Fwindows, codecs | [media-utils](sub-skills\u002Fmedia-utils\u002FSKILL.md) |\n\n## Operating principles\n\n1. Treat `sv.Detections` as the shared object between model adapters, filters,\n   zones, trackers, annotators, datasets, sinks, slicers, and metrics.\n2. Keep aligned arrays aligned. Filter the container object, not individual\n   `xyxy`, `confidence`, `class_id`, `mask`, `tracker_id`, or `data` arrays.\n3. Import metadata keys from `supervision.config` when writing reusable code:\n   `CLASS_NAME_DATA_FIELD`, `ORIENTED_BOX_COORDINATES`, and `AREA_DATA_FIELD`.\n4. Keep heavy optional model\u002Fframework imports lazy and model-specific.\n   Supervision adapters convert already-produced results; they do not download\n   models or install external frameworks.\n5. Use `scene.copy()` before annotation when the original image or frame must be\n   preserved. Annotators draw on the provided scene and return it.\n6. Prefer current APIs: `supervision.key_points`\u002F`sv.KeyPoints`,\n   `keypoint_confidence`, `sv.VLM`, and `Detections.from_vlm`. Treat\n   `supervision.keypoint`, `KeyPoints.confidence`, `sv.ByteTrack`, `sv.LMM`, and\n   `from_lmm` as compatibility or migration topics.\n7. Do not rely on original repository docs, examples, tests, notebooks, scripts,\n   or local checkout files as runtime dependencies. The necessary operating\n   guidance is distilled into this skill tree.\n\n## Common route combinations\n\n- **Annotate model output:** use `detection-and-zones` to normalize raw results\n  into `Detections`, then `annotators` to draw on images or video frames.\n- **Evaluate a dataset:** use `datasets` to load\u002Fconvert annotations,\n  `detection-and-zones` to normalize predictions, and `metrics` to compute and\n  interpret scores.\n- **Count objects in video zones:** use `media-utils` for video frames,\n  `detection-and-zones` for `PolygonZone`\u002F`LineZone`, `tracking-keypoints` when\n  stable `tracker_id` is needed, and `annotators` for overlays.\n- **Debug backend\u002Fimage\u002Fvideo issues:** use `media-utils` first, then return to\n  the workflow sub-skill that owns the higher-level operation.\n","# Supervision\n\nUse this repo skill when a task uses the `supervision` Python package as a\ncomputer-vision utility layer: normalized detections, visual annotation, dataset\nconversion, tracking\u002Fkeypoints, evaluation metrics, image\u002Fvideo helpers, zones,\nsinks, slicers, and optional OpenCV backend behavior.\n\n## Install and minimal check\n\n```bash\npip install supervision\npython -c \"import supervision as sv; print(sv.__version__)\"\n```\n\nAdd extras only for workflows that need them:\n\n```bash\npip install \"supervision[metrics]\"   # pandas-backed metric tables and evaluation\npip install \"supervision[geotiff]\"   # rasterio\u002Fwindowed GeoTIFF slicing\n```\n\nNative OpenCV is optional. Use Supervision's fallback backend by default; install\nexactly one OpenCV wheel only when the application needs native OpenCV behavior,\nGUI windows, webcam capture, or broader codec compatibility.\n\nRun the bundled [check_supervision_install.py](scripts\u002Fcheck_supervision_install.py)\nhelper when the environment is unknown.\n\n## Start here\n\n- Read [overview](references\u002Foverview.md) for the package map, core concepts,\n  optional extras, and deprecation summary.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting\n  install\u002Fimport\u002Fbackend\u002Fdeprecation failures.\n- Read [repo provenance](references\u002Frepo-provenance.md) before deciding whether\n  this skill matches a different checkout or package version.\n\n## Route by task\n\n| User intent or signals | Sub-skill |\n| --- | --- |\n| `Detections`, model adapters, VLM parsing, compact masks, filtering, NMS\u002FNMM, zones, tiled inference, smoothing, CSV\u002FJSON sinks | [detection-and-zones](sub-skills\u002Fdetection-and-zones\u002FSKILL.md) |\n| Drawing boxes, masks, labels, traces, heatmaps, zones, comparison panels, and other high-level `scene` + detections\u002Fkeypoints visualization | [annotators](sub-skills\u002Fannotators\u002FSKILL.md) |\n| YOLO\u002FCOCO\u002FPascal VOC\u002FLabelMe\u002FCreateML dataset loading\u002Fexport, dataset splitting\u002Fmerging, classification folder datasets | [datasets](sub-skills\u002Fdatasets\u002FSKILL.md) |\n| `KeyPoints`, keypoint adapters\u002Fannotators, keypoint-to-detection conversion, tracker IDs, ByteTrack compatibility\u002Fmigration, line crossing with identity | [tracking-keypoints](sub-skills\u002Ftracking-keypoints\u002FSKILL.md) |\n| mAP, mAR, precision, recall, F1, confusion matrices, `MetricTarget`, `AveragingMethod`, dataset-backed evaluation | [metrics](sub-skills\u002Fmetrics\u002FSKILL.md) |\n| Image\u002Fvideo\u002Ffile helpers, primitive drawing, colors, geometry, notebook display, assets, OpenCV fallback\u002Fnative backend, GUI\u002Fwindows, codecs | [media-utils](sub-skills\u002Fmedia-utils\u002FSKILL.md) |\n\n## Operating principles\n\n1. Treat `sv.Detections` as the shared object between model adapters, filters,\n   zones, trackers, annotators, datasets, sinks, slicers, and metrics.\n2. Keep aligned arrays aligned. Filter the container object, not individual\n   `xyxy`, `confidence`, `class_id`, `mask`, `tracker_id`, or `data` arrays.\n3. Import metadata keys from `supervision.config` when writing reusable code:\n   `CLASS_NAME_DATA_FIELD`, `ORIENTED_BOX_COORDINATES`, and `AREA_DATA_FIELD`.\n4. Keep heavy optional model\u002Fframework imports lazy and model-specific.\n   Supervision adapters convert already-produced results; they do not download\n   models or install external frameworks.\n5. Use `scene.copy()` before annotation when the original image or frame must be\n   preserved. Annotators draw on the provided scene and return it.\n6. Prefer current APIs: `supervision.key_points`\u002F`sv.KeyPoints`,\n   `keypoint_confidence`, `sv.VLM`, and `Detections.from_vlm`. Treat\n   `supervision.keypoint`, `KeyPoints.confidence`, `sv.ByteTrack`, `sv.LMM`, and\n   `from_lmm` as compatibility or migration topics.\n7. Do not rely on original repository docs, examples, tests, notebooks, scripts,\n   or local checkout files as runtime dependencies. The necessary operating\n   guidance is distilled into this skill tree.\n\n## Common route combinations\n\n- **Annotate model output:** use `detection-and-zones` to normalize raw results\n  into `Detections`, then `annotators` to draw on images or video frames.\n- **Evaluate a dataset:** use `datasets` to load\u002Fconvert annotations,\n  `detection-and-zones` to normalize predictions, and `metrics` to compute and\n  interpret scores.\n- **Count objects in video zones:** use `media-utils` for video frames,\n  `detection-and-zones` for `PolygonZone`\u002F`LineZone`, `tracking-keypoints` when\n  stable `tracker_id` is needed, and `annotators` for overlays.\n- **Debug backend\u002Fimage\u002Fvideo issues:** use `media-utils` first, then return to\n  the workflow sub-skill that owns the higher-level operation.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsupervision",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 supervision",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill supervision",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill supervision","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Foverview.md","REFERENCE","参考文档",5779,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Freferences\u002Foverview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2515,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",487,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5762,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_supervision_install.py","SCRIPT","脚本",7072,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fscripts\u002Fcheck_supervision_install.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",[],[]]