[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7948F2WP2DFYD4RM9D2TPF5":3,"skill-same:01M7948F2WP2DFYD4RM9D2TPF5":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7948F2WP2DFYD4RM9D2TPF5","inference-and-models",null,"Use RF-DETR model variants, checkpoints, prediction outputs, video and stream inference, labels, and inference troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-and-models\ndescription: \"Use RF-DETR model variants, checkpoints, prediction outputs, video\n  and stream inference, labels, and inference troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# RF-DETR Inference and Models\n\nUse this sub-skill when the task is to run or diagnose RF-DETR prediction code, choose a detection \u002F segmentation \u002F keypoint model class, load a checkpoint, interpret `supervision` outputs, handle class names, tune inference memory, or explain Plus model boundaries.\n\nDo not use this sub-skill for fine-tuning, Lightning CLI, dataset schema work, export\u002Fdeployment formats, or source-repository contribution policy; route those tasks to sibling sub-skills when available:\n\n- `..\u002Ftraining-and-cli\u002FSKILL.md` for `train()`, `evaluate()`, datasets, configs, and CLI.\n- `..\u002Fexport-and-deployment\u002FSKILL.md` for ONNX, TensorRT, TFLite, ExecuTorch, CoreML, and Roboflow deployment bundles.\n- `..\u002Frepository-development\u002FSKILL.md` for modifying RF-DETR source, tests, docs, packaging, or CI.\n\n## Runtime map\n\n- API surface, class tables, signatures, checkpoint trust rules, output fields, and label mapping: [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- Recipes for image, batch, video, webcam, RTSP, keypoint visualization, checkpoint loading, and memory optimization: [references\u002Fworkflows.md](references\u002Fworkflows.md)\n- Failure diagnosis for imports, downloads, checkpoints, shapes, labels, keypoints, video sources, devices, and Plus models: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n- Safe installed-package inspector that does not download weights or instantiate models: [scripts\u002Finspect_rfdetr_models.py](scripts\u002Finspect_rfdetr_models.py)\n\n## Quick decision rules\n\n1. Default new detection examples to `RFDETRSmall` \u002F `\"rfdetr-small\"`; do not introduce new `RFDETRBase` or `\"rfdetr-base\"` examples.\n2. Use a sized segmentation model (`RFDETRSegNano`, `RFDETRSegSmall`, `RFDETRSegMedium`, `RFDETRSegLarge`, `RFDETRSegXLarge`, `RFDETRSeg2XLarge`); do not use `RFDETRSegPreview` for new work.\n3. Keypoints are preview-only: use `RFDETRKeypointPreview` \u002F `\"rfdetr-keypoint-preview\"` only for keypoint tasks.\n4. Prefer `detections.data[\"class_name\"]` or `key_points.data[\"class_name\"]` for labels. `COCO_CLASSES` is only for manually mapping COCO-pretrained sparse category IDs.\n5. For fine-tuned checkpoints, load with `RFDETR.from_checkpoint(path)` or `rfdetr.from_checkpoint(path)` and leave `trust_checkpoint=False` unless the checkpoint source is fully trusted.\n6. For memory-constrained prediction, consider `include_source_image=False` first; use `model.inference(compile=False, inplace=True, dtype=\"float16\")` only when the destructive, inference-only trade-off is acceptable.\n","# RF-DETR Inference and Models\n\nUse this sub-skill when the task is to run or diagnose RF-DETR prediction code, choose a detection \u002F segmentation \u002F keypoint model class, load a checkpoint, interpret `supervision` outputs, handle class names, tune inference memory, or explain Plus model boundaries.\n\nDo not use this sub-skill for fine-tuning, Lightning CLI, dataset schema work, export\u002Fdeployment formats, or source-repository contribution policy; route those tasks to sibling sub-skills when available:\n\n- `..\u002Ftraining-and-cli\u002FSKILL.md` for `train()`, `evaluate()`, datasets, configs, and CLI.\n- `..\u002Fexport-and-deployment\u002FSKILL.md` for ONNX, TensorRT, TFLite, ExecuTorch, CoreML, and Roboflow deployment bundles.\n- `..\u002Frepository-development\u002FSKILL.md` for modifying RF-DETR source, tests, docs, packaging, or CI.\n\n## Runtime map\n\n- API surface, class tables, signatures, checkpoint trust rules, output fields, and label mapping: [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- Recipes for image, batch, video, webcam, RTSP, keypoint visualization, checkpoint loading, and memory optimization: [references\u002Fworkflows.md](references\u002Fworkflows.md)\n- Failure diagnosis for imports, downloads, checkpoints, shapes, labels, keypoints, video sources, devices, and Plus models: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n- Safe installed-package inspector that does not download weights or instantiate models: [scripts\u002Finspect_rfdetr_models.py](scripts\u002Finspect_rfdetr_models.py)\n\n## Quick decision rules\n\n1. Default new detection examples to `RFDETRSmall` \u002F `\"rfdetr-small\"`; do not introduce new `RFDETRBase` or `\"rfdetr-base\"` examples.\n2. Use a sized segmentation model (`RFDETRSegNano`, `RFDETRSegSmall`, `RFDETRSegMedium`, `RFDETRSegLarge`, `RFDETRSegXLarge`, `RFDETRSeg2XLarge`); do not use `RFDETRSegPreview` for new work.\n3. Keypoints are preview-only: use `RFDETRKeypointPreview` \u002F `\"rfdetr-keypoint-preview\"` only for keypoint tasks.\n4. Prefer `detections.data[\"class_name\"]` or `key_points.data[\"class_name\"]` for labels. `COCO_CLASSES` is only for manually mapping COCO-pretrained sparse category IDs.\n5. For fine-tuned checkpoints, load with `RFDETR.from_checkpoint(path)` or `rfdetr.from_checkpoint(path)` and leave `trust_checkpoint=False` unless the checkpoint source is fully trusted.\n6. For memory-constrained prediction, consider `include_source_image=False` first; use `model.inference(compile=False, inplace=True, dtype=\"float16\")` only when the destructive, inference-only trade-off is acceptable.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-models",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-models",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",10618,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",9236,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",8013,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_rfdetr_models.py","SCRIPT","脚本",10102,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Finference-and-models\u002Fscripts\u002Finspect_rfdetr_models.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]