[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78W0ZX4MKRB6BX2Q1C2RVB6":3,"skill-same:01M78W0ZX4MKRB6BX2Q1C2RVB6":71},{"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},"01M78W0ZX4MKRB6BX2Q1C2RVB6","data-datasets",null,"Register and validate Detectron2 datasets, metadata, COCO helpers, mappers, and data loaders.","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\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-datasets\ndescription: \"Register and validate Detectron2 datasets, metadata, COCO helpers,\n  mappers, and data loaders.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Detectron2 Data & Datasets\n\nUse this sub-skill when a task is about getting data into Detectron2: registering custom datasets, checking Detectron2-standard dataset dicts, setting metadata, using COCO helpers, designing mappers, or building train\u002Ftest data loaders.\n\n## Read First\n\n- `references\u002Fdataset-format.md` for `DatasetCatalog`, `MetadataCatalog`, standard dataset dict fields, COCO registration, metadata keys, and dataset-root conventions.\n- `references\u002Fdata-loading.md` for `DatasetMapper`, custom mapper patterns, augmentations, and `build_detection_train_loader` \u002F `build_detection_test_loader` usage.\n- `references\u002Ftroubleshooting.md` for common registration, annotation, metadata, class-count, COCO path, and mapper failures.\n\n## Common Workflows\n\n1. Register a dataset by name with `DatasetCatalog.register(name, callable)`; the callable must take no arguments and return the same ordered records on every call.\n2. Attach shared dataset facts through `MetadataCatalog.get(name).set(...)`, especially class names and evaluator\u002FCOCO metadata.\n3. Validate records with `scripts\u002Fvalidate_dataset_dicts.py` before wiring them into a loader or config.\n4. Use `register_coco_instances` or `load_coco_json` when annotations are COCO instance\u002Fkeypoint style.\n5. Pass the registered names into `cfg.DATASETS.TRAIN` \u002F `cfg.DATASETS.TEST`, and route class-count or solver changes to the config\u002Ftraining sub-skills.\n6. Customize loading through `DatasetMapper(..., augmentations=...)` or a custom mapper passed to `build_detection_train_loader(..., mapper=...)`.\n\n## Bundled Helpers\n\n- `scripts\u002Fvalidate_dataset_dicts.py`: validates a JSON list of Detectron2-standard dataset dicts and reports actionable schema\u002Fdata-shape errors.\n- `scripts\u002Fvalidate_dataset_registration.py`: smoke-checks catalog registration and metadata behavior with a synthetic dataset, and optionally validates a user JSON fixture.\n\n## Boundaries\n\n- This sub-skill owns dataset registration, metadata, dataset dict structure, COCO helpers, mapper design, loader construction, dataset roots, and annotation\u002Floader troubleshooting.\n- Use the training\u002Fevaluation sub-skill for `DefaultTrainer`, launch commands, evaluators, class-count config changes, and metrics.\n- Use the inference\u002Fvisualization sub-skill for rendering predictions or dataset visualizations.\n- Use extension-projects guidance for project-specific dataset converters or custom task heads.\n","# Detectron2 Data & Datasets\n\nUse this sub-skill when a task is about getting data into Detectron2: registering custom datasets, checking Detectron2-standard dataset dicts, setting metadata, using COCO helpers, designing mappers, or building train\u002Ftest data loaders.\n\n## Read First\n\n- `references\u002Fdataset-format.md` for `DatasetCatalog`, `MetadataCatalog`, standard dataset dict fields, COCO registration, metadata keys, and dataset-root conventions.\n- `references\u002Fdata-loading.md` for `DatasetMapper`, custom mapper patterns, augmentations, and `build_detection_train_loader` \u002F `build_detection_test_loader` usage.\n- `references\u002Ftroubleshooting.md` for common registration, annotation, metadata, class-count, COCO path, and mapper failures.\n\n## Common Workflows\n\n1. Register a dataset by name with `DatasetCatalog.register(name, callable)`; the callable must take no arguments and return the same ordered records on every call.\n2. Attach shared dataset facts through `MetadataCatalog.get(name).set(...)`, especially class names and evaluator\u002FCOCO metadata.\n3. Validate records with `scripts\u002Fvalidate_dataset_dicts.py` before wiring them into a loader or config.\n4. Use `register_coco_instances` or `load_coco_json` when annotations are COCO instance\u002Fkeypoint style.\n5. Pass the registered names into `cfg.DATASETS.TRAIN` \u002F `cfg.DATASETS.TEST`, and route class-count or solver changes to the config\u002Ftraining sub-skills.\n6. Customize loading through `DatasetMapper(..., augmentations=...)` or a custom mapper passed to `build_detection_train_loader(..., mapper=...)`.\n\n## Bundled Helpers\n\n- `scripts\u002Fvalidate_dataset_dicts.py`: validates a JSON list of Detectron2-standard dataset dicts and reports actionable schema\u002Fdata-shape errors.\n- `scripts\u002Fvalidate_dataset_registration.py`: smoke-checks catalog registration and metadata behavior with a synthetic dataset, and optionally validates a user JSON fixture.\n\n## Boundaries\n\n- This sub-skill owns dataset registration, metadata, dataset dict structure, COCO helpers, mapper design, loader construction, dataset roots, and annotation\u002Floader troubleshooting.\n- Use the training\u002Fevaluation sub-skill for `DefaultTrainer`, launch commands, evaluators, class-count config changes, and metrics.\n- Use the inference\u002Fvisualization sub-skill for rendering predictions or dataset visualizations.\n- Use extension-projects guidance for project-specific dataset converters or custom task heads.\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\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets",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 data-datasets",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill data-datasets",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill data-datasets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdata-loading.md","REFERENCE","参考文档",7711,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002Freferences\u002Fdata-loading.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdataset-format.md",8278,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002Freferences\u002Fdataset-format.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7100,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_dataset_dicts.py","SCRIPT","脚本",22615,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002Fscripts\u002Fvalidate_dataset_dicts.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fvalidate_dataset_registration.py",10062,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Fdata-datasets\u002Fscripts\u002Fvalidate_dataset_registration.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]