[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794891RN2REA1G9FSG59QMQ":3,"skill-same:01M794891RN2REA1G9FSG59QMQ":75},{"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},"01M794891RN2REA1G9FSG59QMQ","rf-detr",null,"Use and maintain RF-DETR for real-time object detection, instance segmentation, keypoint preview, training, export, deployment, and repository development.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rf-detr\ndescription: \"Use and maintain RF-DETR for real-time object detection, instance\n  segmentation, keypoint preview, training, export, deployment, and repository\n  development.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# RF-DETR Repo Skill\n\nUse this skill when a task involves the `rfdetr` Python package or the RF-DETR repository: selecting model variants, running prediction, fine-tuning on COCO\u002FYOLO\u002Fkeypoint datasets, exporting artifacts, deploying to inference runtimes, or editing the RF-DETR source tree.\n\nRF-DETR is a PyTorch\u002FDINOv2-based real-time vision model family for object detection, instance segmentation, and keypoint preview. The public package name is `rfdetr` and the default concrete detection model for new examples is `RFDETRSmall` \u002F `\"rfdetr-small\"`.\n\n## Install and smoke-check first\n\nFor ordinary package use:\n\n```bash\npip install rfdetr\npython -c \"from rfdetr import RFDETRSmall; print(RFDETRSmall.size)\"\n```\n\nAdd extras only for the workflow you need:\n\n```bash\npip install \"rfdetr[train,cli]\"       # training and Lightning CLI\npip install \"rfdetr[augment]\"         # Albumentations \u002F Kornia augmentation backends\npip install \"rfdetr[onnx]\"            # ONNX export and ONNX Runtime inspection\npip install \"rfdetr[tensorrt]\"        # TensorRT export on NVIDIA GPU hosts\npip install \"rfdetr[tflite]\"          # experimental TFLite export\npip install \"rfdetr[executorch]\"      # experimental ExecuTorch export\npip install \"rfdetr[coreml]\"          # native CoreML export on supported macOS hosts\npip install \"rfdetr[plus]\"            # Plus detection models; separate package\u002Flicense\n```\n\nRun the bundled read-only environment check when import, optional dependency, CLI, or backend readiness is unclear:\n\n```bash\npython scripts\u002Fcheck_rfdetr_environment.py\npython scripts\u002Fcheck_rfdetr_environment.py --extras train onnx augment --check-cuda\n```\n\n## Route by task\n\n| User task | Open |\n| --- | --- |\n| Choose an RF-DETR model class\u002Falias, run image\u002Fvideo\u002Fstream prediction, load checkpoints, interpret `supervision` detections\u002Fkeypoints, fix labels\u002Fdevices\u002Fshape\u002Fdownloads | [sub-skills\u002Finference-and-models\u002FSKILL.md](sub-skills\u002Finference-and-models\u002FSKILL.md) |\n| Fine-tune\u002Fevaluate detection, segmentation, or keypoint models; validate COCO\u002FYOLO\u002Fkeypoint datasets; use `rfdetr` Lightning CLI and YAML configs; debug resume, DDP, augmentation, loggers | [sub-skills\u002Ftraining-and-cli\u002FSKILL.md](sub-skills\u002Ftraining-and-cli\u002FSKILL.md) |\n| Export to ONNX, TensorRT, TFLite, ExecuTorch, or CoreML; choose deployment artifacts; diagnose optional backend constraints and output naming | [sub-skills\u002Fexport-and-deployment\u002FSKILL.md](sub-skills\u002Fexport-and-deployment\u002FSKILL.md) |\n| Modify RF-DETR source, tests, docs, configs, package metadata, CI, or examples while following repository contribution rules | [sub-skills\u002Frepository-development\u002FSKILL.md](sub-skills\u002Frepository-development\u002FSKILL.md) |\n\n## Shared references\n\n- Read [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md) when you need the released model families, default class choices, alias rules, license boundaries, and task-to-model map.\n- Read [references\u002Foptional-dependencies-and-backends.md](references\u002Foptional-dependencies-and-backends.md) before installing extras, choosing CPU\u002FGPU\u002Fmobile export dependencies, or explaining an unavailable backend.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, data\u002Fconfig, checkpoint, CUDA, and workflow failures before drilling into a sub-skill-specific troubleshooting file.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking whether this generated skill is stale for a checkout or before refreshing it.\n\n## Core decisions to preserve\n\n1. Default new detection examples to `RFDETRSmall` \u002F `\"rfdetr-small\"`; treat `RFDETRBase` \u002F `\"rfdetr-base\"` as deprecated for new examples, docs, and tests.\n2. Use released sized segmentation classes (`RFDETRSegNano`, `RFDETRSegSmall`, `RFDETRSegMedium`, `RFDETRSegLarge`, `RFDETRSegXLarge`, `RFDETRSeg2XLarge`); do not use `RFDETRSegPreview` for new work.\n3. Use preview variants only when the capability has no released sized version. In current RF-DETR evidence, keypoints are preview-only: `RFDETRKeypointPreview` \u002F `\"rfdetr-keypoint-preview\"`.\n4. Keep optional backend claims honest. A CPU import check does not verify TensorRT, CoreML, ExecuTorch QNN, XLA, or CUDA-specific behavior.\n5. Prefer bundled scripts in this skill for inspection and preflight checks. They are designed to be safe, read-only, and runnable without downloading pretrained weights or starting training.\n\n## Common first-response patterns\n\n- For an inference question, ask for the task family (detection, segmentation, keypoint), checkpoint source if any, input type, and whether the user needs CPU, CUDA, or deployment-runtime constraints.\n- For a training question, validate dataset layout before recommending a long run, then choose model family, extras, batch\u002Feffective-batch plan, resume semantics, and evaluation split.\n- For an export question, start with ONNX unless the target runtime requires another artifact. Reject invalid static combinations early, especially `dynamic_batch=True` for ExecuTorch\u002FCoreML or QNN without `soc`.\n- For repository changes, follow RF-DETR TDD and style rules, choose focused tests by changed paths, and run full pre-commit before handoff.\n","# RF-DETR Repo Skill\n\nUse this skill when a task involves the `rfdetr` Python package or the RF-DETR repository: selecting model variants, running prediction, fine-tuning on COCO\u002FYOLO\u002Fkeypoint datasets, exporting artifacts, deploying to inference runtimes, or editing the RF-DETR source tree.\n\nRF-DETR is a PyTorch\u002FDINOv2-based real-time vision model family for object detection, instance segmentation, and keypoint preview. The public package name is `rfdetr` and the default concrete detection model for new examples is `RFDETRSmall` \u002F `\"rfdetr-small\"`.\n\n## Install and smoke-check first\n\nFor ordinary package use:\n\n```bash\npip install rfdetr\npython -c \"from rfdetr import RFDETRSmall; print(RFDETRSmall.size)\"\n```\n\nAdd extras only for the workflow you need:\n\n```bash\npip install \"rfdetr[train,cli]\"       # training and Lightning CLI\npip install \"rfdetr[augment]\"         # Albumentations \u002F Kornia augmentation backends\npip install \"rfdetr[onnx]\"            # ONNX export and ONNX Runtime inspection\npip install \"rfdetr[tensorrt]\"        # TensorRT export on NVIDIA GPU hosts\npip install \"rfdetr[tflite]\"          # experimental TFLite export\npip install \"rfdetr[executorch]\"      # experimental ExecuTorch export\npip install \"rfdetr[coreml]\"          # native CoreML export on supported macOS hosts\npip install \"rfdetr[plus]\"            # Plus detection models; separate package\u002Flicense\n```\n\nRun the bundled read-only environment check when import, optional dependency, CLI, or backend readiness is unclear:\n\n```bash\npython scripts\u002Fcheck_rfdetr_environment.py\npython scripts\u002Fcheck_rfdetr_environment.py --extras train onnx augment --check-cuda\n```\n\n## Route by task\n\n| User task | Open |\n| --- | --- |\n| Choose an RF-DETR model class\u002Falias, run image\u002Fvideo\u002Fstream prediction, load checkpoints, interpret `supervision` detections\u002Fkeypoints, fix labels\u002Fdevices\u002Fshape\u002Fdownloads | [sub-skills\u002Finference-and-models\u002FSKILL.md](sub-skills\u002Finference-and-models\u002FSKILL.md) |\n| Fine-tune\u002Fevaluate detection, segmentation, or keypoint models; validate COCO\u002FYOLO\u002Fkeypoint datasets; use `rfdetr` Lightning CLI and YAML configs; debug resume, DDP, augmentation, loggers | [sub-skills\u002Ftraining-and-cli\u002FSKILL.md](sub-skills\u002Ftraining-and-cli\u002FSKILL.md) |\n| Export to ONNX, TensorRT, TFLite, ExecuTorch, or CoreML; choose deployment artifacts; diagnose optional backend constraints and output naming | [sub-skills\u002Fexport-and-deployment\u002FSKILL.md](sub-skills\u002Fexport-and-deployment\u002FSKILL.md) |\n| Modify RF-DETR source, tests, docs, configs, package metadata, CI, or examples while following repository contribution rules | [sub-skills\u002Frepository-development\u002FSKILL.md](sub-skills\u002Frepository-development\u002FSKILL.md) |\n\n## Shared references\n\n- Read [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md) when you need the released model families, default class choices, alias rules, license boundaries, and task-to-model map.\n- Read [references\u002Foptional-dependencies-and-backends.md](references\u002Foptional-dependencies-and-backends.md) before installing extras, choosing CPU\u002FGPU\u002Fmobile export dependencies, or explaining an unavailable backend.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, data\u002Fconfig, checkpoint, CUDA, and workflow failures before drilling into a sub-skill-specific troubleshooting file.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking whether this generated skill is stale for a checkout or before refreshing it.\n\n## Core decisions to preserve\n\n1. Default new detection examples to `RFDETRSmall` \u002F `\"rfdetr-small\"`; treat `RFDETRBase` \u002F `\"rfdetr-base\"` as deprecated for new examples, docs, and tests.\n2. Use released sized segmentation classes (`RFDETRSegNano`, `RFDETRSegSmall`, `RFDETRSegMedium`, `RFDETRSegLarge`, `RFDETRSegXLarge`, `RFDETRSeg2XLarge`); do not use `RFDETRSegPreview` for new work.\n3. Use preview variants only when the capability has no released sized version. In current RF-DETR evidence, keypoints are preview-only: `RFDETRKeypointPreview` \u002F `\"rfdetr-keypoint-preview\"`.\n4. Keep optional backend claims honest. A CPU import check does not verify TensorRT, CoreML, ExecuTorch QNN, XLA, or CUDA-specific behavior.\n5. Prefer bundled scripts in this skill for inspection and preflight checks. They are designed to be safe, read-only, and runnable without downloading pretrained weights or starting training.\n\n## Common first-response patterns\n\n- For an inference question, ask for the task family (detection, segmentation, keypoint), checkpoint source if any, input type, and whether the user needs CPU, CUDA, or deployment-runtime constraints.\n- For a training question, validate dataset layout before recommending a long run, then choose model family, extras, batch\u002Feffective-batch plan, resume semantics, and evaluation split.\n- For an export question, start with ONNX unless the target runtime requires another artifact. Reject invalid static combinations early, especially `dynamic_batch=True` for ExecuTorch\u002FCoreML or QNN without `soc`.\n- For repository changes, follow RF-DETR TDD and style rules, choose focused tests by changed paths, and run full pre-commit before handoff.\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",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 rf-detr",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rf-detr",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rf-detr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmodel-overview.md","REFERENCE","参考文档",3940,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Freferences\u002Fmodel-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Foptional-dependencies-and-backends.md",5362,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Freferences\u002Foptional-dependencies-and-backends.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",2183,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",485,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",6117,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_rfdetr_environment.py","SCRIPT","脚本",8191,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fscripts\u002Fcheck_rfdetr_environment.py",[76,83,90,97,104,111],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]