[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795SN2PZ1PJR7B31GQP4B0V":3,"skill-same:01M795SN2PZ1PJR7B31GQP4B0V":60},{"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},"01M795SN2PZ1PJR7B31GQP4B0V","detection-and-zones",null,"Use supervision Detections, model adapters, compact masks, filtering, zones, slicing, smoothing, and CSV\u002FJSON sinks.","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\u002Fdetection-and-zones\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: detection-and-zones\ndescription: \"Use supervision Detections, model adapters, compact masks,\n  filtering, zones, slicing, smoothing, and CSV\u002FJSON sinks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Detection And Zones\n\nUse this sub-skill when the task centers on detection data, model-result normalization, segmentation mask containers, filtering, overlap suppression\u002Fmerging, zones, tiled inference, smoothing, or saving detections.\n\n## Natural triggers\n\nRoute here for prompts mentioning:\n\n- `sv.Detections`, `Detections.empty`, indexing\u002Ffiltering, `data`, `metadata`, `tracker_id`, `class_name`.\n- `from_ultralytics`, `from_inference`, `from_transformers`, `from_vlm`, `from_lmm`, `from_sam`, `from_sam3`, `from_tensorflow`, `from_mmdetection`, `from_detectron2`, `from_yolov5`, `from_yolo_nas`, `from_easyocr`, `from_ncnn`, or other `Detections.from_*` adapters.\n- `CompactMask`, `compact_masks=True`, dense vs compact masks, mask\u002Fbox\u002FOBB geometry, `ORIENTED_BOX_COORDINATES`.\n- `with_nms`, `with_soft_nms`, `with_nmm`, `OverlapFilter`, `OverlapMetric`, IoU\u002FIoS, duplicate detections.\n- `PolygonZone`, `LineZone`, count in zone, line crossing, zone trigger masks, `Position` anchors.\n- `InferenceSlicer`, small object detection, tiled inference, overlap windows, GeoTIFF\u002Fwindowed raster slicing.\n- `DetectionsSmoother`, `CSVSink`, `JSONSink`, save detections, custom detection data serialization.\n\n## First response routing\n\n1. Identify the raw input type: already a `Detections`, a framework result object, a VLM response, manual NumPy arrays, or persisted rows.\n2. Open [API reference](references\u002Fapi-reference.md) for exact container fields, adapter signatures, constants, and tool parameters.\n3. Open [workflows](references\u002Fworkflows.md) for common recipes: normalization, filtering, zones, slicing, compact masks, smoothing, and CSV\u002FJSON export.\n4. Open [troubleshooting](references\u002Ftroubleshooting.md) before changing code when shapes, optional dependencies, missing metadata, tracker IDs, masks, zones, or slicer behavior are unclear.\n\n## Boundaries\n\nHandle:\n\n- Detection containers and aligned per-detection arrays.\n- Adapter normalization from model\u002Fframework\u002FVLM outputs into `sv.Detections`.\n- Detection utility functions that transform boxes, masks, polygons, overlaps, or VLM label matching.\n- Zone trigger logic and counts, including tracker-dependent line crossing.\n- Slicer, smoother, CSV sink, and JSON sink behaviors.\n\nRoute elsewhere:\n\n- Pure drawing, color styling, label layout, and annotator composition belong to the annotators sub-skill.\n- Tracking identity persistence, tracker configuration, keypoint containers, and keypoint deprecations belong to the tracking-keypoints sub-skill; return here once `tracker_id` is present for `LineZone` or smoothing.\n- Image\u002Fvideo I\u002FO, OpenCV backend selection, media helpers, assets, and low-level geometry primitives belong to the media-utils sub-skill unless they directly affect detection boxes\u002Fmasks\u002Fzones.\n- Dataset format conversion and dataset splitting\u002Fmerging belong to the datasets sub-skill.\n- mAP\u002FMAR\u002Fprecision\u002Frecall\u002FF1\u002Fconfusion-matrix evaluation belongs to the metrics sub-skill.\n\n## Operating defaults\n\n- Target package facts: `supervision` 0.31.0.dev0, Python >=3.10, base install via `pip install supervision`.\n- Optional model frameworks are caller-managed; Supervision adapters normalize results but do not install or download model packages.\n- Optional GeoTIFF\u002Fwindowed raster support needs the geotiff extra or `rasterio`.\n- OpenCV native wheels are optional for the package; do not assume native OpenCV is installed when writing detection-only code.\n- Prefer constants from `supervision.config` (`CLASS_NAME_DATA_FIELD`, `ORIENTED_BOX_COORDINATES`) over string literals in code that writes `detections.data`.\n- Treat all detection-level fields as aligned length-`N` data; filtering must preserve alignment by indexing the `Detections` object, not by slicing only one array.\n","# Detection And Zones\n\nUse this sub-skill when the task centers on detection data, model-result normalization, segmentation mask containers, filtering, overlap suppression\u002Fmerging, zones, tiled inference, smoothing, or saving detections.\n\n## Natural triggers\n\nRoute here for prompts mentioning:\n\n- `sv.Detections`, `Detections.empty`, indexing\u002Ffiltering, `data`, `metadata`, `tracker_id`, `class_name`.\n- `from_ultralytics`, `from_inference`, `from_transformers`, `from_vlm`, `from_lmm`, `from_sam`, `from_sam3`, `from_tensorflow`, `from_mmdetection`, `from_detectron2`, `from_yolov5`, `from_yolo_nas`, `from_easyocr`, `from_ncnn`, or other `Detections.from_*` adapters.\n- `CompactMask`, `compact_masks=True`, dense vs compact masks, mask\u002Fbox\u002FOBB geometry, `ORIENTED_BOX_COORDINATES`.\n- `with_nms`, `with_soft_nms`, `with_nmm`, `OverlapFilter`, `OverlapMetric`, IoU\u002FIoS, duplicate detections.\n- `PolygonZone`, `LineZone`, count in zone, line crossing, zone trigger masks, `Position` anchors.\n- `InferenceSlicer`, small object detection, tiled inference, overlap windows, GeoTIFF\u002Fwindowed raster slicing.\n- `DetectionsSmoother`, `CSVSink`, `JSONSink`, save detections, custom detection data serialization.\n\n## First response routing\n\n1. Identify the raw input type: already a `Detections`, a framework result object, a VLM response, manual NumPy arrays, or persisted rows.\n2. Open [API reference](references\u002Fapi-reference.md) for exact container fields, adapter signatures, constants, and tool parameters.\n3. Open [workflows](references\u002Fworkflows.md) for common recipes: normalization, filtering, zones, slicing, compact masks, smoothing, and CSV\u002FJSON export.\n4. Open [troubleshooting](references\u002Ftroubleshooting.md) before changing code when shapes, optional dependencies, missing metadata, tracker IDs, masks, zones, or slicer behavior are unclear.\n\n## Boundaries\n\nHandle:\n\n- Detection containers and aligned per-detection arrays.\n- Adapter normalization from model\u002Fframework\u002FVLM outputs into `sv.Detections`.\n- Detection utility functions that transform boxes, masks, polygons, overlaps, or VLM label matching.\n- Zone trigger logic and counts, including tracker-dependent line crossing.\n- Slicer, smoother, CSV sink, and JSON sink behaviors.\n\nRoute elsewhere:\n\n- Pure drawing, color styling, label layout, and annotator composition belong to the annotators sub-skill.\n- Tracking identity persistence, tracker configuration, keypoint containers, and keypoint deprecations belong to the tracking-keypoints sub-skill; return here once `tracker_id` is present for `LineZone` or smoothing.\n- Image\u002Fvideo I\u002FO, OpenCV backend selection, media helpers, assets, and low-level geometry primitives belong to the media-utils sub-skill unless they directly affect detection boxes\u002Fmasks\u002Fzones.\n- Dataset format conversion and dataset splitting\u002Fmerging belong to the datasets sub-skill.\n- mAP\u002FMAR\u002Fprecision\u002Frecall\u002FF1\u002Fconfusion-matrix evaluation belongs to the metrics sub-skill.\n\n## Operating defaults\n\n- Target package facts: `supervision` 0.31.0.dev0, Python >=3.10, base install via `pip install supervision`.\n- Optional model frameworks are caller-managed; Supervision adapters normalize results but do not install or download model packages.\n- Optional GeoTIFF\u002Fwindowed raster support needs the geotiff extra or `rasterio`.\n- OpenCV native wheels are optional for the package; do not assume native OpenCV is installed when writing detection-only code.\n- Prefer constants from `supervision.config` (`CLASS_NAME_DATA_FIELD`, `ORIENTED_BOX_COORDINATES`) over string literals in code that writes `detections.data`.\n- Treat all detection-level fields as aligned length-`N` data; filtering must preserve alignment by indexing the `Detections` object, not by slicing only one array.\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\u002Fdetection-and-zones",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 detection-and-zones",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill detection-and-zones",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill detection-and-zones","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Fdetection-and-zones\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",17211,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Fdetection-and-zones\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",12779,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Fdetection-and-zones\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",13237,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsupervision\u002Fsub-skills\u002Fdetection-and-zones\u002Freferences\u002Fworkflows.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]