[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792136DSFSPSQBXECEKW566":3,"skill-same:01M792136DSFSPSQBXECEKW566":83},{"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},"01M792136DSFSPSQBXECEKW566","openpcdet",null,"Operate OpenPCDet 3D object detection workflows across runtime setup, dataset preparation, training\u002Fevaluation, inference\u002Fcustom data, and model\u002Fconfig extension.","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\u002Fopenpcdet\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openpcdet\ndescription: \"Operate OpenPCDet 3D object detection workflows across runtime\n  setup, dataset preparation, training\u002Fevaluation, inference\u002Fcustom data, and\n  model\u002Fconfig extension.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# OpenPCDet Operating Skill\n\nUse this skill when a task involves OpenPCDet, the `pcdet` Python package, OpenPCDet YAML configs, 3D point-cloud detection datasets, or OpenPCDet training\u002Fevaluation\u002Fdemo workflows.\n\n## Route first\n\n- Need installation, CUDA extension, spconv, import, or environment diagnosis? Read `sub-skills\u002Fruntime-and-ops\u002FSKILL.md`.\n- Need dataset layout, info pickle, ground-truth database, split, or `DATA_CONFIG` help? Read `sub-skills\u002Fdata-preparation\u002FSKILL.md`.\n- Need to train, resume, evaluate, run distributed jobs, or interpret outputs\u002Fcheckpoints? Read `sub-skills\u002Ftraining-and-evaluation\u002FSKILL.md`.\n- Need demo inference, custom point-cloud files, CustomDataset, visualization, or non-visual inference adaptation? Read `sub-skills\u002Finference-and-custom-data\u002FSKILL.md`.\n- Need config\u002Fmodel registry, YAML overrides, detector family selection, BEVFusion\u002FMPPNet\u002FCaDDN\u002FVoxelNeXt\u002FDSVT notes, or new model extension points? Read `sub-skills\u002Fmodels-and-configs\u002FSKILL.md`.\n\n## Minimal public install and verification shape\n\nFor a fresh OpenPCDet checkout and a CUDA-capable Python environment, the package build shape is:\n\n```bash\npython -m pip install --no-build-isolation -e \u003COpenPCDet-checkout>\npython scripts\u002Finspect_openpcdet_runtime.py --repo \u003COpenPCDet-checkout> --require-cuda-ops\n```\n\nThe build command is public and reproducible, but the exact CUDA\u002FPyTorch\u002Fspconv variants must match the user's environment; read `sub-skills\u002Fruntime-and-ops\u002FSKILL.md` before repairing a failing build.\n\n## Use bundled helpers instead of memorizing repository scripts\n\nThe skill bundles safe helper scripts under `scripts\u002F` and sub-skill `scripts\u002F`. They do not run expensive dataset\u002Ftraining jobs unless explicitly asked.\n\n- `scripts\u002Finspect_openpcdet_runtime.py` checks imports, PyTorch CUDA, spconv\u002Fcumm, optional packages, and compiled OpenPCDet ops.\n- `scripts\u002Fsummarize_openpcdet_config.py` loads an OpenPCDet YAML config and summarizes dataset\u002Fmodel\u002Foptimization fields without building data loaders or models.\n- `scripts\u002Fplan_openpcdet_command.py` constructs train\u002Ftest\u002Fdemo\u002Fdataset-prep commands for an OpenPCDet checkout and only executes when `--execute` is supplied.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_openpcdet_dataset_layout.py` checks expected dataset folders and generated info\u002Fdatabase products.\n- `sub-skills\u002Finference-and-custom-data\u002Fscripts\u002Fcheck_point_cloud_array.py` validates `.bin`\u002F`.npy` point-cloud shapes before demo\u002Fcustom inference.\n- `sub-skills\u002Fmodels-and-configs\u002Fscripts\u002Finventory_openpcdet_configs.py` inventories config YAMLs and detector\u002Fdataset registry names.\n\n## Operating stance\n\n1. Treat OpenPCDet as GPU-first. CPU-only imports do not prove model training, evaluation, or native op correctness.\n2. Keep config, dataset root, checkpoint, and model family aligned. Most runtime failures come from mixing a config with the wrong data layout, class list, or checkpoint.\n3. Prefer static\u002Fconfig\u002Fimport probes before large jobs. Run full training\u002Fevaluation only after checking CUDA ops, spconv variant, dataset infos, ground-truth database products, and CLI command construction.\n4. For future work in another checkout, use checkout-relative paths supplied by the user or the current task. Do not rely on the source checkout used to construct this skill.\n\n## Core references\n\n- `references\u002Frepo-provenance.md` records source commit, package version, environment facts, and evidence paths.\n- `references\u002Frepo-routing-metadata.json` contains router placement metadata for repo-skill import tooling.\n- `references\u002Fopenpcdet-overview.md` summarizes architecture, registries, and workflow entry points.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport\u002Fdata\u002Fconfig\u002Fjob failures.\n- `references\u002Fsource-script-map.md` records which repository scripts were wrapped, adapted, or excluded.\n","# OpenPCDet Operating Skill\n\nUse this skill when a task involves OpenPCDet, the `pcdet` Python package, OpenPCDet YAML configs, 3D point-cloud detection datasets, or OpenPCDet training\u002Fevaluation\u002Fdemo workflows.\n\n## Route first\n\n- Need installation, CUDA extension, spconv, import, or environment diagnosis? Read `sub-skills\u002Fruntime-and-ops\u002FSKILL.md`.\n- Need dataset layout, info pickle, ground-truth database, split, or `DATA_CONFIG` help? Read `sub-skills\u002Fdata-preparation\u002FSKILL.md`.\n- Need to train, resume, evaluate, run distributed jobs, or interpret outputs\u002Fcheckpoints? Read `sub-skills\u002Ftraining-and-evaluation\u002FSKILL.md`.\n- Need demo inference, custom point-cloud files, CustomDataset, visualization, or non-visual inference adaptation? Read `sub-skills\u002Finference-and-custom-data\u002FSKILL.md`.\n- Need config\u002Fmodel registry, YAML overrides, detector family selection, BEVFusion\u002FMPPNet\u002FCaDDN\u002FVoxelNeXt\u002FDSVT notes, or new model extension points? Read `sub-skills\u002Fmodels-and-configs\u002FSKILL.md`.\n\n## Minimal public install and verification shape\n\nFor a fresh OpenPCDet checkout and a CUDA-capable Python environment, the package build shape is:\n\n```bash\npython -m pip install --no-build-isolation -e \u003COpenPCDet-checkout>\npython scripts\u002Finspect_openpcdet_runtime.py --repo \u003COpenPCDet-checkout> --require-cuda-ops\n```\n\nThe build command is public and reproducible, but the exact CUDA\u002FPyTorch\u002Fspconv variants must match the user's environment; read `sub-skills\u002Fruntime-and-ops\u002FSKILL.md` before repairing a failing build.\n\n## Use bundled helpers instead of memorizing repository scripts\n\nThe skill bundles safe helper scripts under `scripts\u002F` and sub-skill `scripts\u002F`. They do not run expensive dataset\u002Ftraining jobs unless explicitly asked.\n\n- `scripts\u002Finspect_openpcdet_runtime.py` checks imports, PyTorch CUDA, spconv\u002Fcumm, optional packages, and compiled OpenPCDet ops.\n- `scripts\u002Fsummarize_openpcdet_config.py` loads an OpenPCDet YAML config and summarizes dataset\u002Fmodel\u002Foptimization fields without building data loaders or models.\n- `scripts\u002Fplan_openpcdet_command.py` constructs train\u002Ftest\u002Fdemo\u002Fdataset-prep commands for an OpenPCDet checkout and only executes when `--execute` is supplied.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_openpcdet_dataset_layout.py` checks expected dataset folders and generated info\u002Fdatabase products.\n- `sub-skills\u002Finference-and-custom-data\u002Fscripts\u002Fcheck_point_cloud_array.py` validates `.bin`\u002F`.npy` point-cloud shapes before demo\u002Fcustom inference.\n- `sub-skills\u002Fmodels-and-configs\u002Fscripts\u002Finventory_openpcdet_configs.py` inventories config YAMLs and detector\u002Fdataset registry names.\n\n## Operating stance\n\n1. Treat OpenPCDet as GPU-first. CPU-only imports do not prove model training, evaluation, or native op correctness.\n2. Keep config, dataset root, checkpoint, and model family aligned. Most runtime failures come from mixing a config with the wrong data layout, class list, or checkpoint.\n3. Prefer static\u002Fconfig\u002Fimport probes before large jobs. Run full training\u002Fevaluation only after checking CUDA ops, spconv variant, dataset infos, ground-truth database products, and CLI command construction.\n4. For future work in another checkout, use checkout-relative paths supplied by the user or the current task. Do not rely on the source checkout used to construct this skill.\n\n## Core references\n\n- `references\u002Frepo-provenance.md` records source commit, package version, environment facts, and evidence paths.\n- `references\u002Frepo-routing-metadata.json` contains router placement metadata for repo-skill import tooling.\n- `references\u002Fopenpcdet-overview.md` summarizes architecture, registries, and workflow entry points.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport\u002Fdata\u002Fconfig\u002Fjob failures.\n- `references\u002Fsource-script-map.md` records which repository scripts were wrapped, adapted, or excluded.\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\u002Fopenpcdet",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 openpcdet",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill openpcdet",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill openpcdet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002FSKILL.md",[47,53,57,61,65,69,75,79],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fopenpcdet-overview.md","REFERENCE","参考文档",3384,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Freferences\u002Fopenpcdet-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2634,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",503,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fsource-script-map.md",2775,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Freferences\u002Fsource-script-map.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3699,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Finspect_openpcdet_runtime.py","SCRIPT","脚本",5178,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Fscripts\u002Finspect_openpcdet_runtime.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fplan_openpcdet_command.py",6335,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Fscripts\u002Fplan_openpcdet_command.py",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fsummarize_openpcdet_config.py",4616,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenpcdet\u002Fscripts\u002Fsummarize_openpcdet_config.py",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]