[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797M1RNSMZB4DX2H0DBMSP6":3,"skill-same:01M797M1RNSMZB4DX2H0DBMSP6":66},{"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},"01M797M1RNSMZB4DX2H0DBMSP6","data-preparation",null,"Prepares and validates BDD100K-style YOLOP data roots, detection JSONs, drivable-area masks, lane-line masks, and label-generation workflows.","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\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-preparation\ndescription: \"Prepares and validates BDD100K-style YOLOP data roots, detection\n  JSONs, drivable-area masks, lane-line masks, and label-generation workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# YOLOP Data Preparation\n\nUse this sub-skill when the task asks how to prepare BDD100K data for YOLOP, set `DATASET.*ROOT` config fields, diagnose missing masks\u002FJSONs\u002Fimages, generate drivable-area segmentation masks, or understand the detection label conversion used by `BddDataset`.\n\nDo not use this sub-skill for model hyperparameters, checkpoint loading, ONNX export, or demo inference except where those tasks depend on data roots; route those to `training`, `export`, or `inference`.\n\n## Read first\n\n- [references\u002Fdata-layout.md](references\u002Fdata-layout.md) explains the expected BDD100K directory layout, how `BddDataset` maps mask paths to image\u002Flabel\u002Flane paths, and how detection categories are converted.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers empty datasets, missing path pairs, malformed JSONs, mask rendering failures, and common config mistakes.\n- Run [scripts\u002Fcheck_data_layout.py](scripts\u002Fcheck_data_layout.py) before training\u002Fevaluation to check that roots and split directories line up.\n- Run [scripts\u002Fgenerate_drivable_masks.py](scripts\u002Fgenerate_drivable_masks.py) when you need a safer, argument-driven version of the repo's drivable-area mask generator.\n\n## Minimal workflow\n\n1. Acquire the BDD100K images and the YOLOP-compatible detection, drivable-area, and lane-line annotations from the source project instructions or an already prepared mirror.\n2. Put the roots into one of these forms:\n   - README combined layout: `images\u002F{train,val}`, `det_annotations\u002F{train,val}`, `da_seg_annotations\u002F{train,val}`, `ll_seg_annotations\u002F{train,val}` under one dataset root.\n   - Source config layout: independent roots where each root contains `train\u002F` and `val\u002F` subdirectories.\n3. If drivable masks are not already PNG files, generate them from BDD polygon JSONs with the bundled generator.\n4. Validate the roots and filename correspondence.\n5. Update `cfg.DATASET.DATAROOT`, `LABELROOT`, `MASKROOT`, and `LANEROOT` before running training or evaluation.\n\n## Safe helpers\n\n```bash\n# Combined README-style root\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_data_layout.py \\\n  --dataset-root \u002Fpath\u002Fto\u002Fyolop-dataset --splits train val --max-samples 20\n\n# Explicit roots matching lib\u002Fconfig\u002Fdefault.py fields\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_data_layout.py \\\n  --images-root \u002Fpath\u002Fto\u002Fimages\u002F100k \\\n  --det-root \u002Fpath\u002Fto\u002Fdet_annotations \\\n  --da-root \u002Fpath\u002Fto\u002Fda_seg_annotations \\\n  --lane-root \u002Fpath\u002Fto\u002Fll_seg_annotations\n\n# Generate drivable-area masks for one split from BDD label JSONs\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fgenerate_drivable_masks.py \\\n  --labels-dir \u002Fpath\u002Fto\u002Fbdd100k\u002Flabels\u002F100k\u002Ftrain \\\n  --output-dir \u002Fpath\u002Fto\u002Fbdd_seg_gt\u002Ftrain\n```\n\nThese helpers do not import YOLOP source code. They validate\u002Fgenerate files from paths you pass explicitly and are safe to run outside the original repo checkout.\n\n## Key ownership boundary\n\nThis sub-skill owns data layout and label generation. Once the layout is valid, use [..\u002Ftraining\u002FSKILL.md](..\u002Ftraining\u002FSKILL.md) for `tools\u002Ftrain.py` and `tools\u002Ftest.py` config choices, metrics, and checkpoint behavior.\n","# YOLOP Data Preparation\n\nUse this sub-skill when the task asks how to prepare BDD100K data for YOLOP, set `DATASET.*ROOT` config fields, diagnose missing masks\u002FJSONs\u002Fimages, generate drivable-area segmentation masks, or understand the detection label conversion used by `BddDataset`.\n\nDo not use this sub-skill for model hyperparameters, checkpoint loading, ONNX export, or demo inference except where those tasks depend on data roots; route those to `training`, `export`, or `inference`.\n\n## Read first\n\n- [references\u002Fdata-layout.md](references\u002Fdata-layout.md) explains the expected BDD100K directory layout, how `BddDataset` maps mask paths to image\u002Flabel\u002Flane paths, and how detection categories are converted.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers empty datasets, missing path pairs, malformed JSONs, mask rendering failures, and common config mistakes.\n- Run [scripts\u002Fcheck_data_layout.py](scripts\u002Fcheck_data_layout.py) before training\u002Fevaluation to check that roots and split directories line up.\n- Run [scripts\u002Fgenerate_drivable_masks.py](scripts\u002Fgenerate_drivable_masks.py) when you need a safer, argument-driven version of the repo's drivable-area mask generator.\n\n## Minimal workflow\n\n1. Acquire the BDD100K images and the YOLOP-compatible detection, drivable-area, and lane-line annotations from the source project instructions or an already prepared mirror.\n2. Put the roots into one of these forms:\n   - README combined layout: `images\u002F{train,val}`, `det_annotations\u002F{train,val}`, `da_seg_annotations\u002F{train,val}`, `ll_seg_annotations\u002F{train,val}` under one dataset root.\n   - Source config layout: independent roots where each root contains `train\u002F` and `val\u002F` subdirectories.\n3. If drivable masks are not already PNG files, generate them from BDD polygon JSONs with the bundled generator.\n4. Validate the roots and filename correspondence.\n5. Update `cfg.DATASET.DATAROOT`, `LABELROOT`, `MASKROOT`, and `LANEROOT` before running training or evaluation.\n\n## Safe helpers\n\n```bash\n# Combined README-style root\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_data_layout.py \\\n  --dataset-root \u002Fpath\u002Fto\u002Fyolop-dataset --splits train val --max-samples 20\n\n# Explicit roots matching lib\u002Fconfig\u002Fdefault.py fields\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_data_layout.py \\\n  --images-root \u002Fpath\u002Fto\u002Fimages\u002F100k \\\n  --det-root \u002Fpath\u002Fto\u002Fdet_annotations \\\n  --da-root \u002Fpath\u002Fto\u002Fda_seg_annotations \\\n  --lane-root \u002Fpath\u002Fto\u002Fll_seg_annotations\n\n# Generate drivable-area masks for one split from BDD label JSONs\npython sub-skills\u002Fdata-preparation\u002Fscripts\u002Fgenerate_drivable_masks.py \\\n  --labels-dir \u002Fpath\u002Fto\u002Fbdd100k\u002Flabels\u002F100k\u002Ftrain \\\n  --output-dir \u002Fpath\u002Fto\u002Fbdd_seg_gt\u002Ftrain\n```\n\nThese helpers do not import YOLOP source code. They validate\u002Fgenerate files from paths you pass explicitly and are safe to run outside the original repo checkout.\n\n## Key ownership boundary\n\nThis sub-skill owns data layout and label generation. Once the layout is valid, use [..\u002Ftraining\u002FSKILL.md](..\u002Ftraining\u002FSKILL.md) for `tools\u002Ftrain.py` and `tools\u002Ftest.py` config choices, metrics, and checkpoint behavior.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation",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 data-preparation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill data-preparation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill data-preparation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002FSKILL.md",[46,52,56,62],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-layout.md","REFERENCE","参考文档",4340,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002Freferences\u002Fdata-layout.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",2372,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fcheck_data_layout.py","SCRIPT","脚本",5265,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002Fscripts\u002Fcheck_data_layout.py",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fgenerate_drivable_masks.py",5355,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Fdata-preparation\u002Fscripts\u002Fgenerate_drivable_masks.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]