[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795STSCWKXT37JSQG4TK15G":3,"skill-same:01M795STSCWKXT37JSQG4TK15G":62},{"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},"01M795STSCWKXT37JSQG4TK15G","tracking-keypoints",null,"Operate supervision keypoint containers, keypoint annotators, tracking IDs, and migration paths.","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\u002Fsub-skills\u002Ftracking-keypoints\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tracking-keypoints\ndescription: \"Operate supervision keypoint containers, keypoint annotators,\n  tracking IDs, and migration paths.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Tracking Keypoints\n\nUse this sub-skill when a task involves `supervision` keypoint data, keypoint\nannotation, keypoint-to-detection conversion for tracking, persistent\n`tracker_id` workflows, line-crossing\u002Fcounting that depends on tracker identity,\nor migration away from deprecated keypoint\u002Ftracker APIs.\n\n## Route here for\n\n- `KeyPoints`, `keypoint_confidence`, `detection_confidence`, `visible`,\n  `KeyPoints.merge`, `KeyPoints.with_nms`, and `KeyPoints.as_detections`.\n- Keypoint adapters such as `KeyPoints.from_ultralytics`, `from_inference`,\n  `from_mediapipe`, `from_yolo_nas`, `from_detectron2`, and\n  `from_transformers`.\n- `VertexAnnotator`, `EdgeAnnotator`, `VertexLabelAnnotator`,\n  `VertexEllipseAreaAnnotator`, `VertexEllipseOutlineAnnotator`,\n  `VertexEllipseHaloAnnotator`, and the `VertexEllipseAnnotator` alias.\n- `ByteTrack`, `ByteTrackTracker`, `tracker_id`, `track_objects`, track labels,\n  `TraceAnnotator`, `DetectionsSmoother`, and `LineZone` when persistent\n  identity is central to the answer.\n- Deprecated `supervision.keypoint`, deprecated `sv.ByteTrack`, old ByteTrack\n  threshold names, and the `KeyPoints.confidence` rename.\n\n## Route away\n\n- Build, filter, save, or reason about ordinary `Detections`, masks, polygon\n  zones, line-zone geometry, sinks, or slicers when tracker continuity is not\n  central: use [detection-and-zones](..\u002Fdetection-and-zones\u002FSKILL.md).\n- Non-keypoint detection\u002Fmask\u002Flabel visualization and annotator catalog choices:\n  use [annotators](..\u002Fannotators\u002FSKILL.md).\n- Image\u002Fvideo I\u002FO, primitive drawing, OpenCV backend diagnosis, GUI\u002Fwindow\n  problems, and video codecs: use [media-utils](..\u002Fmedia-utils\u002FSKILL.md).\n- Dataset conversion or detection metric evaluation: use the corresponding\n  dataset or metrics sub-skill.\n\n## Operating checklist\n\n1. Identify the active container. Pose\u002Fkeypoint model outputs should become\n   `sv.KeyPoints`; tracking, line crossing, traces, smoothing, and most labels\n   operate on `sv.Detections` with `tracker_id`.\n2. Prefer `sv.KeyPoints` or `supervision.key_points`. Do not introduce new\n   `supervision.keypoint` imports; that path is compatibility-only and scheduled\n   for removal.\n3. Use `keypoint_confidence` for per-anchor scores and `detection_confidence`\n   for whole-skeleton scores. Treat `KeyPoints.confidence` and `confidence=` as\n   deprecated compatibility shims.\n4. Before keypoint annotation, decide whether missing\u002Fweak anchors should be\n   hidden with `key_points.visible`. When `visible` is `None`, annotators treat\n   anchors as visible except that all-zero coordinates are skipped.\n5. Before keypoint tracking, convert with `key_points.as_detections(...)`, ensure\n   the resulting detections have confidence scores and positive-area boxes, then\n   run a tracker. Prefer the external `ByteTrackTracker` package when available;\n   `sv.ByteTrack` is only a deprecated compatibility fallback in this version.\n6. Use the tracked `Detections` object for tracker labels, traces, detection\n   smoothing, and `LineZone.trigger(...)`. Missing `tracker_id` is the first\n   thing to check when these workflows do nothing or raise.\n7. Put detailed API choices and recipes in\n   [tracking-keypoints.md](references\u002Ftracking-keypoints.md), and failure repair\n   steps in [troubleshooting.md](references\u002Ftroubleshooting.md). Use the bundled\n   [draw_zones.py](scripts\u002Fdraw_zones.py) helper only for interactive polygon\n   authoring in a GUI-capable environment.\n\n## Required context to keep in answers\n\n- Target package facts: `supervision` `0.31.0.dev0`, Python `>=3.10`, base\n  install `pip install supervision`.\n- Model adapters require their own model\u002Fframework packages; they are not part\n  of the base `supervision` install.\n- `ByteTrackTracker` comes from the optional external `trackers` package.\n  `sv.ByteTrack` still exists as a lazy compatibility export in this target, but\n  it is deprecated and should not be presented as stable.\n- Native OpenCV is optional for the package. Interactive helpers require a GUI\n  display and an OpenCV-compatible drawing\u002Fvideo backend; the documented\n  fallback backend may render or decode differently from native OpenCV.\n- Do not recommend original repository docs, examples, tests, scripts, local\n  checkout paths, or generated skill import steps as runtime dependencies.\n","# Tracking Keypoints\n\nUse this sub-skill when a task involves `supervision` keypoint data, keypoint\nannotation, keypoint-to-detection conversion for tracking, persistent\n`tracker_id` workflows, line-crossing\u002Fcounting that depends on tracker identity,\nor migration away from deprecated keypoint\u002Ftracker APIs.\n\n## Route here for\n\n- `KeyPoints`, `keypoint_confidence`, `detection_confidence`, `visible`,\n  `KeyPoints.merge`, `KeyPoints.with_nms`, and `KeyPoints.as_detections`.\n- Keypoint adapters such as `KeyPoints.from_ultralytics`, `from_inference`,\n  `from_mediapipe`, `from_yolo_nas`, `from_detectron2`, and\n  `from_transformers`.\n- `VertexAnnotator`, `EdgeAnnotator`, `VertexLabelAnnotator`,\n  `VertexEllipseAreaAnnotator`, `VertexEllipseOutlineAnnotator`,\n  `VertexEllipseHaloAnnotator`, and the `VertexEllipseAnnotator` alias.\n- `ByteTrack`, `ByteTrackTracker`, `tracker_id`, `track_objects`, track labels,\n  `TraceAnnotator`, `DetectionsSmoother`, and `LineZone` when persistent\n  identity is central to the answer.\n- Deprecated `supervision.keypoint`, deprecated `sv.ByteTrack`, old ByteTrack\n  threshold names, and the `KeyPoints.confidence` rename.\n\n## Route away\n\n- Build, filter, save, or reason about ordinary `Detections`, masks, polygon\n  zones, line-zone geometry, sinks, or slicers when tracker continuity is not\n  central: use [detection-and-zones](..\u002Fdetection-and-zones\u002FSKILL.md).\n- Non-keypoint detection\u002Fmask\u002Flabel visualization and annotator catalog choices:\n  use [annotators](..\u002Fannotators\u002FSKILL.md).\n- Image\u002Fvideo I\u002FO, primitive drawing, OpenCV backend diagnosis, GUI\u002Fwindow\n  problems, and video codecs: use [media-utils](..\u002Fmedia-utils\u002FSKILL.md).\n- Dataset conversion or detection metric evaluation: use the corresponding\n  dataset or metrics sub-skill.\n\n## Operating checklist\n\n1. Identify the active container. Pose\u002Fkeypoint model outputs should become\n   `sv.KeyPoints`; tracking, line crossing, traces, smoothing, and most labels\n   operate on `sv.Detections` with `tracker_id`.\n2. Prefer `sv.KeyPoints` or `supervision.key_points`. Do not introduce new\n   `supervision.keypoint` imports; that path is compatibility-only and scheduled\n   for removal.\n3. Use `keypoint_confidence` for per-anchor scores and `detection_confidence`\n   for whole-skeleton scores. Treat `KeyPoints.confidence` and `confidence=` as\n   deprecated compatibility shims.\n4. Before keypoint annotation, decide whether missing\u002Fweak anchors should be\n   hidden with `key_points.visible`. When `visible` is `None`, annotators treat\n   anchors as visible except that all-zero coordinates are skipped.\n5. Before keypoint tracking, convert with `key_points.as_detections(...)`, ensure\n   the resulting detections have confidence scores and positive-area boxes, then\n   run a tracker. Prefer the external `ByteTrackTracker` package when available;\n   `sv.ByteTrack` is only a deprecated compatibility fallback in this version.\n6. Use the tracked `Detections` object for tracker labels, traces, detection\n   smoothing, and `LineZone.trigger(...)`. Missing `tracker_id` is the first\n   thing to check when these workflows do nothing or raise.\n7. Put detailed API choices and recipes in\n   [tracking-keypoints.md](references\u002Ftracking-keypoints.md), and failure repair\n   steps in [troubleshooting.md](references\u002Ftroubleshooting.md). Use the bundled\n   [draw_zones.py](scripts\u002Fdraw_zones.py) helper only for interactive polygon\n   authoring in a GUI-capable environment.\n\n## Required context to keep in answers\n\n- Target package facts: `supervision` `0.31.0.dev0`, Python `>=3.10`, base\n  install `pip install supervision`.\n- Model adapters require their own model\u002Fframework packages; they are not part\n  of the base `supervision` install.\n- `ByteTrackTracker` comes from the optional external `trackers` package.\n  `sv.ByteTrack` still exists as a lazy compatibility export in this target, but\n  it is deprecated and should not be presented as stable.\n- Native OpenCV is optional for the package. Interactive helpers require a GUI\n  display and an OpenCV-compatible drawing\u002Fvideo backend; the documented\n  fallback backend may render or decode differently from native OpenCV.\n- Do not recommend original repository docs, examples, tests, scripts, local\n  checkout paths, or generated skill import steps as runtime dependencies.\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\u002Fsub-skills\u002Ftracking-keypoints",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 tracking-keypoints",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill tracking-keypoints",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill tracking-keypoints","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Ftracking-keypoints\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Ftracking-keypoints.md","REFERENCE","参考文档",13519,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Ftracking-keypoints\u002Freferences\u002Ftracking-keypoints.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",10130,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Ftracking-keypoints\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fdraw_zones.py","SCRIPT","脚本",10230,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Ftracking-keypoints\u002Fscripts\u002Fdraw_zones.py",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]