[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790JCRAF8VVMZ2NZ62MBDZW":3,"skill-same:01M790JCRAF8VVMZ2NZ62MBDZW":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},"01M790JCRAF8VVMZ2NZ62MBDZW","mmdetection",null,"Use this skill when working with MMDetection 3.x for object detection, instance\u002Fpanoptic segmentation, tracking-adjacent configs, model zoo configs, inference, visualization, training\u002Ftesting commands, datasets, evaluation, or extension work.","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\u002Fmmdetection\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mmdetection\ndescription: \"Use this skill when working with MMDetection 3.x for object\n  detection, instance\u002Fpanoptic segmentation, tracking-adjacent configs, model\n  zoo configs, inference, visualization, training\u002Ftesting commands, datasets,\n  evaluation, or extension work.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# MMDetection\n\nMMDetection is OpenMMLab's PyTorch-based detection toolbox. Use this root skill as a router, then open the nearest sub-skill for concrete commands, APIs, config patterns, and troubleshooting.\n\n## Quick Import and Environment Check\n\nUse the bundled checker when diagnosing an install before deeper work:\n\n```bash\npython scripts\u002Fcheck_mmdet_environment.py\n```\n\nA healthy base environment should import `mmdet`, `mmcv`, `mmengine`, and `torch`, report compatible MMDetection\u002FMMCV\u002FMMEngine versions, and expose inference APIs such as `DetInferencer`, `init_detector`, and `inference_detector`.\n\nImportant dependency facts:\n\n- MMDetection 3.3.0 requires `mmcv>=2.0.0rc4,\u003C2.2.0` and `mmengine>=0.7.1,\u003C1.0.0`.\n- Install full `mmcv` for workflows importing `mmcv.ops`; `mmcv-lite` can fail with `ModuleNotFoundError: mmcv._ext`.\n- Match `torch`, `mmcv`, CUDA\u002FCPU wheels, NumPy, and OpenCV carefully; ABI mismatches often appear during API imports.\n- CPU inspection\u002Finference is possible for many workflows, but some ops and real training\u002Fevaluation workloads are GPU- or dataset-dependent.\n\nRead `references\u002Ftroubleshooting.md` for cross-cutting install\u002Fimport\u002Fbackend failures. Read `references\u002Frepo-provenance.md` when deciding whether this skill is stale against a newer MMDetection checkout.\n\n## Route by Task\n\n| User task | Open this sub-skill | Why |\n| --- | --- | --- |\n| Choose a config, inspect `_base_`, apply `--cfg-options`, compare model zoo entries, or debug config loading | `sub-skills\u002Fconfiguration-model-zoo\u002FSKILL.md` | Owns config inheritance, model-index\u002Fmetafile navigation, model names, override validation, and config migration pointers. |\n| Run image\u002Ffolder\u002Fvideo-style inference, save prediction JSON or visualizations, use `DetInferencer`, `init_detector`, or `inference_detector` | `sub-skills\u002Finference-visualization\u002FSKILL.md` | Owns public inference APIs, output controls, device\u002Fpalette choices, headless visualization, and deployment route selection. |\n| Build training, resume, distributed, Slurm, testing, evaluation, or result-dump commands | `sub-skills\u002Ftraining-testing\u002FSKILL.md` | Owns `tools\u002Ftrain.py`, `tools\u002Ftest.py`, distributed launcher patterns, `--resume`, `--auto-scale-lr`, `work_dir`, and command validation. |\n| Prepare datasets, convert image folders\u002Fannotations, configure COCO\u002FVOC\u002FCityscapes\u002FLVIS\u002FOpenImages metrics, or debug transforms\u002Fevaluators | `sub-skills\u002Fdatasets-evaluation\u002FSKILL.md` | Owns dataset layouts, COCO-like schemas, custom dataset config, transforms, metrics, analysis tools, and tiny dataset helpers. |\n| Add custom models, heads, losses, datasets, transforms, hooks, optimizer constructors, structures, or project plugins | `sub-skills\u002Fcustomization-extension\u002FSKILL.md` | Owns registries, `custom_imports`, project templates, MMEngine integration, data structures, and migration\u002Fcustomization pitfalls. |\n\n## Common Workflow Chains\n\n### Config to Inference\n\n1. Use `configuration-model-zoo` to select a compatible config and inspect inherited settings.\n2. Use `inference-visualization` to choose `DetInferencer` or lower-level APIs.\n3. Use root `references\u002Ftroubleshooting.md` if imports fail before model construction.\n\n### Custom Dataset Training\n\n1. Use `datasets-evaluation` to validate annotation schema, class order, `metainfo`, and evaluator paths.\n2. Use `configuration-model-zoo` to update config dataloaders, heads, and overrides.\n3. Use `training-testing` to generate training\u002Fresume\u002Ftest commands.\n4. Use `customization-extension` only if a new dataset\u002Ftransform class must be registered.\n\n### New Component or Project Plugin\n\n1. Use `customization-extension` for registry ownership, `custom_imports`, module layout, and smoke checks.\n2. Use `configuration-model-zoo` to wire the new type into configs.\n3. Use `training-testing` for safe launch command generation.\n\n## Runtime Files\n\n- `references\u002Frepo-provenance.md`: source commit, version, dirty state, and evidence baseline.\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport\u002Fbackend and dependency failures.\n- `scripts\u002Fcheck_mmdet_environment.py`: safe import\u002Fversion\u002FAPI signature checker.\n\n## Boundaries\n\nThis skill is self-contained guidance for future agents. It does not bundle MMDetection itself, pretrained checkpoints, datasets, videos, Docker images, or source-checkout-only tools. When a native MMDetection checkout is available, original demos\u002Ftests\u002Ftools can be used as optional verification candidates, but runtime instructions in this skill prefer bundled helpers or package APIs.\n","# MMDetection\n\nMMDetection is OpenMMLab's PyTorch-based detection toolbox. Use this root skill as a router, then open the nearest sub-skill for concrete commands, APIs, config patterns, and troubleshooting.\n\n## Quick Import and Environment Check\n\nUse the bundled checker when diagnosing an install before deeper work:\n\n```bash\npython scripts\u002Fcheck_mmdet_environment.py\n```\n\nA healthy base environment should import `mmdet`, `mmcv`, `mmengine`, and `torch`, report compatible MMDetection\u002FMMCV\u002FMMEngine versions, and expose inference APIs such as `DetInferencer`, `init_detector`, and `inference_detector`.\n\nImportant dependency facts:\n\n- MMDetection 3.3.0 requires `mmcv>=2.0.0rc4,\u003C2.2.0` and `mmengine>=0.7.1,\u003C1.0.0`.\n- Install full `mmcv` for workflows importing `mmcv.ops`; `mmcv-lite` can fail with `ModuleNotFoundError: mmcv._ext`.\n- Match `torch`, `mmcv`, CUDA\u002FCPU wheels, NumPy, and OpenCV carefully; ABI mismatches often appear during API imports.\n- CPU inspection\u002Finference is possible for many workflows, but some ops and real training\u002Fevaluation workloads are GPU- or dataset-dependent.\n\nRead `references\u002Ftroubleshooting.md` for cross-cutting install\u002Fimport\u002Fbackend failures. Read `references\u002Frepo-provenance.md` when deciding whether this skill is stale against a newer MMDetection checkout.\n\n## Route by Task\n\n| User task | Open this sub-skill | Why |\n| --- | --- | --- |\n| Choose a config, inspect `_base_`, apply `--cfg-options`, compare model zoo entries, or debug config loading | `sub-skills\u002Fconfiguration-model-zoo\u002FSKILL.md` | Owns config inheritance, model-index\u002Fmetafile navigation, model names, override validation, and config migration pointers. |\n| Run image\u002Ffolder\u002Fvideo-style inference, save prediction JSON or visualizations, use `DetInferencer`, `init_detector`, or `inference_detector` | `sub-skills\u002Finference-visualization\u002FSKILL.md` | Owns public inference APIs, output controls, device\u002Fpalette choices, headless visualization, and deployment route selection. |\n| Build training, resume, distributed, Slurm, testing, evaluation, or result-dump commands | `sub-skills\u002Ftraining-testing\u002FSKILL.md` | Owns `tools\u002Ftrain.py`, `tools\u002Ftest.py`, distributed launcher patterns, `--resume`, `--auto-scale-lr`, `work_dir`, and command validation. |\n| Prepare datasets, convert image folders\u002Fannotations, configure COCO\u002FVOC\u002FCityscapes\u002FLVIS\u002FOpenImages metrics, or debug transforms\u002Fevaluators | `sub-skills\u002Fdatasets-evaluation\u002FSKILL.md` | Owns dataset layouts, COCO-like schemas, custom dataset config, transforms, metrics, analysis tools, and tiny dataset helpers. |\n| Add custom models, heads, losses, datasets, transforms, hooks, optimizer constructors, structures, or project plugins | `sub-skills\u002Fcustomization-extension\u002FSKILL.md` | Owns registries, `custom_imports`, project templates, MMEngine integration, data structures, and migration\u002Fcustomization pitfalls. |\n\n## Common Workflow Chains\n\n### Config to Inference\n\n1. Use `configuration-model-zoo` to select a compatible config and inspect inherited settings.\n2. Use `inference-visualization` to choose `DetInferencer` or lower-level APIs.\n3. Use root `references\u002Ftroubleshooting.md` if imports fail before model construction.\n\n### Custom Dataset Training\n\n1. Use `datasets-evaluation` to validate annotation schema, class order, `metainfo`, and evaluator paths.\n2. Use `configuration-model-zoo` to update config dataloaders, heads, and overrides.\n3. Use `training-testing` to generate training\u002Fresume\u002Ftest commands.\n4. Use `customization-extension` only if a new dataset\u002Ftransform class must be registered.\n\n### New Component or Project Plugin\n\n1. Use `customization-extension` for registry ownership, `custom_imports`, module layout, and smoke checks.\n2. Use `configuration-model-zoo` to wire the new type into configs.\n3. Use `training-testing` for safe launch command generation.\n\n## Runtime Files\n\n- `references\u002Frepo-provenance.md`: source commit, version, dirty state, and evidence baseline.\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport\u002Fbackend and dependency failures.\n- `scripts\u002Fcheck_mmdet_environment.py`: safe import\u002Fversion\u002FAPI signature checker.\n\n## Boundaries\n\nThis skill is self-contained guidance for future agents. It does not bundle MMDetection itself, pretrained checkpoints, datasets, videos, Docker images, or source-checkout-only tools. When a native MMDetection checkout is available, original demos\u002Ftests\u002Ftools can be used as optional verification candidates, but runtime instructions in this skill prefer bundled helpers or package APIs.\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\u002Fmmdetection",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 mmdetection",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mmdetection",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mmdetection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmdetection\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2488,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmdetection\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",507,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmdetection\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",3934,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmdetection\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_mmdet_environment.py","SCRIPT","脚本",2341,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmdetection\u002Fscripts\u002Fcheck_mmdet_environment.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",[],[]]