[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T276Y4ECDZSCDEE9R99S7":3,"skill-same:01M78T276Y4ECDZSCDEE9R99S7":68},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":47},"01M78T276Y4ECDZSCDEE9R99S7","vision-multimodal",null,"Operate AutoTrain Advanced image classification, image regression, object detection, and VLM app\u002FAPI\u002Fconfig workflows.","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\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vision-multimodal\ndescription: \"Operate AutoTrain Advanced image classification, image regression,\n  object detection, and VLM app\u002FAPI\u002Fconfig workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\n  parent-skill: autotrain-advanced\nlicense: Apache 2.0\n---\n\n# AutoTrain vision and multimodal workflows\n\nUse this sub-skill for image classification, image regression\u002Fscoring, object detection, and VLM dataset\u002Ftask flows.\n\n## Supported entry points\n\n- `autotrain image-classification --help`\n- `autotrain image-regression --help`\n- `autotrain object-detection --help`\n- YAML aliases: `image-classification`, `image-regression`, `image-scoring`, `object-detection`, `image-object-detection`, `vlm:captioning`, `vlm:vqa`\n- App\u002FAPI task keys: `image-classification`, `image-regression`, `image-object-detection`, `vlm:captioning`, `vlm:vqa`\n\nImportant: there is no top-level `autotrain vlm` command in this checkout. Route VLM through the app\u002FAPI\u002Fconfig flow.\n\n## Data-layout summary\n\n| Task | Local layout |\n| --- | --- |\n| image classification | directory with at least two class subfolders; each class folder has at least five jpg\u002Fjpeg\u002Fpng files and no extra files\u002Fsubfolders |\n| image regression | directory with at least five images plus `metadata.jsonl` containing `file_name` and `target` |\n| object detection | directory with at least five images plus `metadata.jsonl` containing `file_name` and `objects` |\n| VLM | directory with at least five images plus `metadata.jsonl` containing `file_name` and all mapped text\u002Fprompt columns |\n\nUse `scripts\u002Fvalidate_vision_data.py` for bounded local layout checks.\n\n## Safe validation sequence\n\n1. Inspect relevant CLI help with the root `inspect_cli.py` helper.\n2. Validate YAML with the root `validate_config.py` helper.\n3. Validate local image folders\u002Fmetadata with `scripts\u002Fvalidate_vision_data.py`.\n4. If VLM or UI\u002FAPI parameters are involved, use `..\u002Fapp-backends\u002F` to inspect app\u002FAPI task params and backend auth.\n5. Launch only after data layout, model id, task alias, backend, and Hub credentials are explicit.\n\n## References\n\n- `references\u002Fworkflows.md` — route patterns and launch\u002Fcheck examples.\n- `references\u002Fdata-formats.md` — local folder and metadata schemas.\n- `references\u002Ftroubleshooting.md` — image file counts, metadata parsing, VLM route, and backend issues.\n","# AutoTrain vision and multimodal workflows\n\nUse this sub-skill for image classification, image regression\u002Fscoring, object detection, and VLM dataset\u002Ftask flows.\n\n## Supported entry points\n\n- `autotrain image-classification --help`\n- `autotrain image-regression --help`\n- `autotrain object-detection --help`\n- YAML aliases: `image-classification`, `image-regression`, `image-scoring`, `object-detection`, `image-object-detection`, `vlm:captioning`, `vlm:vqa`\n- App\u002FAPI task keys: `image-classification`, `image-regression`, `image-object-detection`, `vlm:captioning`, `vlm:vqa`\n\nImportant: there is no top-level `autotrain vlm` command in this checkout. Route VLM through the app\u002FAPI\u002Fconfig flow.\n\n## Data-layout summary\n\n| Task | Local layout |\n| --- | --- |\n| image classification | directory with at least two class subfolders; each class folder has at least five jpg\u002Fjpeg\u002Fpng files and no extra files\u002Fsubfolders |\n| image regression | directory with at least five images plus `metadata.jsonl` containing `file_name` and `target` |\n| object detection | directory with at least five images plus `metadata.jsonl` containing `file_name` and `objects` |\n| VLM | directory with at least five images plus `metadata.jsonl` containing `file_name` and all mapped text\u002Fprompt columns |\n\nUse `scripts\u002Fvalidate_vision_data.py` for bounded local layout checks.\n\n## Safe validation sequence\n\n1. Inspect relevant CLI help with the root `inspect_cli.py` helper.\n2. Validate YAML with the root `validate_config.py` helper.\n3. Validate local image folders\u002Fmetadata with `scripts\u002Fvalidate_vision_data.py`.\n4. If VLM or UI\u002FAPI parameters are involved, use `..\u002Fapp-backends\u002F` to inspect app\u002FAPI task params and backend auth.\n5. Launch only after data layout, model id, task alias, backend, and Hub credentials are explicit.\n\n## References\n\n- `references\u002Fworkflows.md` — route patterns and launch\u002Fcheck examples.\n- `references\u002Fdata-formats.md` — local folder and metadata schemas.\n- `references\u002Ftroubleshooting.md` — image file counts, metadata parsing, VLM route, and backend issues.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":25,"parent-skill":26},"operating","autotrain-advanced",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":27},[37,40,43],{"tool":38,"command":39},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill vision-multimodal",{"tool":41,"command":42},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill vision-multimodal",{"tool":44,"command":45},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill vision-multimodal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fdata-formats.md","REFERENCE","参考文档",2047,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002Freferences\u002Fdata-formats.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Ftroubleshooting.md",2183,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002Freferences\u002Ftroubleshooting.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fworkflows.md",2553,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002Freferences\u002Fworkflows.md",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fvalidate_vision_data.py","SCRIPT","脚本",9219,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautotrain-advanced\u002Fsub-skills\u002Fvision-multimodal\u002Fscripts\u002Fvalidate_vision_data.py",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]