[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796JT1RS4MHFDZHTFX4SWG8":3,"skill-same:01M796JT1RS4MHFDZHTFX4SWG8":74},{"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},"01M796JT1RS4MHFDZHTFX4SWG8","domain-adaptation",null,"Router for Transfer-Learning-Library domain adaptation workflows, losses, and optional benchmark stacks.","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\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: domain-adaptation\ndescription: \"Router for Transfer-Learning-Library domain adaptation workflows,\n  losses, and optional benchmark stacks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Domain Adaptation\n\nUse this sub-skill for TLLib domain-adaptation workflows, loss wiring, and benchmark recipe selection.\n\n## What it covers\n- Closed-set feature alignment: DANN, CDAN, ADDA, DAN, JAN, CORAL, BSP, MCD, MDD.\n- Partial and open-set adaptation: PADA, IWAN, OSBP, class-weight reweighting, unknown-class thresholding.\n- Special DA variants: AFN, MCC, RegDA keypoint, D-adapt object detection, and WILDS DA examples.\n\n## Route elsewhere when\n- Datasets, ImageList formats, model factories, or transforms are the main question: `..\u002Fvision-data-models\u002FSKILL.md`\n- Translation, CycleGAN, FDA, or style-transfer is the main question: `..\u002Ftranslation\u002FSKILL.md`\n- SSL, pseudo-labeling, or teacher\u002Fstudent training is the main question: `..\u002Fself-training\u002FSKILL.md`\n- DG, fine-tuning, or standalone transfer regularization is the main question: `..\u002Ftask-generalization\u002FSKILL.md`\n\n## How to use\n1. Identify the transfer setting: closed-set, partial, open-set, regression, keypoint, detection, or WILDS.\n2. Pick the matching API or workflow reference in `references\u002F`.\n3. For CPU-safe validation, use `scripts\u002Ftllib_domain_adaptation_smoke.py`.\n4. Treat object-detection and WILDS coverage as optional-stack guidance unless the user explicitly has those dependencies.\n\n## Notes\n- AFN appears here because it is used in DA workflows, but its standalone module mechanics live in the task-generalization \u002F normalization path.\n- MCC appears here because it is used in DA workflows, but its standalone semi-supervised mechanics live in the self-training path.\n- Do not point users back to the source checkout or benchmark launchers; keep them on the bundled references and smoke helper.\n- Keep benchmark-scale training, downloads, and optional dependency setup out of the smoke path.\n\n## Reference map\n- `references\u002Fapi-reference.md` - public modules, losses, shapes, and common traps.\n- `references\u002Fdomain-adaptation-workflows.md` - classifier, regression, keypoint, and WILDS workflow patterns.\n- `references\u002Fobject-detection-adaptation.md` - D-adapt, Detectron2, proposal and feedback flow, optional stack notes.\n- `references\u002Fwilds-workflows.md` - WILDS-specific CLI and dependency patterns.\n- `references\u002Ftroubleshooting.md` - shape, NumPy, TorchVision, CUDA, Detectron2, and WILDS issues.\n- `scripts\u002Ftllib_domain_adaptation_smoke.py` - tiny CPU tensor smoke using installed `tllib`.\n","# Domain Adaptation\n\nUse this sub-skill for TLLib domain-adaptation workflows, loss wiring, and benchmark recipe selection.\n\n## What it covers\n- Closed-set feature alignment: DANN, CDAN, ADDA, DAN, JAN, CORAL, BSP, MCD, MDD.\n- Partial and open-set adaptation: PADA, IWAN, OSBP, class-weight reweighting, unknown-class thresholding.\n- Special DA variants: AFN, MCC, RegDA keypoint, D-adapt object detection, and WILDS DA examples.\n\n## Route elsewhere when\n- Datasets, ImageList formats, model factories, or transforms are the main question: `..\u002Fvision-data-models\u002FSKILL.md`\n- Translation, CycleGAN, FDA, or style-transfer is the main question: `..\u002Ftranslation\u002FSKILL.md`\n- SSL, pseudo-labeling, or teacher\u002Fstudent training is the main question: `..\u002Fself-training\u002FSKILL.md`\n- DG, fine-tuning, or standalone transfer regularization is the main question: `..\u002Ftask-generalization\u002FSKILL.md`\n\n## How to use\n1. Identify the transfer setting: closed-set, partial, open-set, regression, keypoint, detection, or WILDS.\n2. Pick the matching API or workflow reference in `references\u002F`.\n3. For CPU-safe validation, use `scripts\u002Ftllib_domain_adaptation_smoke.py`.\n4. Treat object-detection and WILDS coverage as optional-stack guidance unless the user explicitly has those dependencies.\n\n## Notes\n- AFN appears here because it is used in DA workflows, but its standalone module mechanics live in the task-generalization \u002F normalization path.\n- MCC appears here because it is used in DA workflows, but its standalone semi-supervised mechanics live in the self-training path.\n- Do not point users back to the source checkout or benchmark launchers; keep them on the bundled references and smoke helper.\n- Keep benchmark-scale training, downloads, and optional dependency setup out of the smoke path.\n\n## Reference map\n- `references\u002Fapi-reference.md` - public modules, losses, shapes, and common traps.\n- `references\u002Fdomain-adaptation-workflows.md` - classifier, regression, keypoint, and WILDS workflow patterns.\n- `references\u002Fobject-detection-adaptation.md` - D-adapt, Detectron2, proposal and feedback flow, optional stack notes.\n- `references\u002Fwilds-workflows.md` - WILDS-specific CLI and dependency patterns.\n- `references\u002Ftroubleshooting.md` - shape, NumPy, TorchVision, CUDA, Detectron2, and WILDS issues.\n- `scripts\u002Ftllib_domain_adaptation_smoke.py` - tiny CPU tensor smoke using installed `tllib`.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation",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 domain-adaptation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill domain-adaptation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill domain-adaptation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",9824,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdomain-adaptation-workflows.md",8953,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Freferences\u002Fdomain-adaptation-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fobject-detection-adaptation.md",4777,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Freferences\u002Fobject-detection-adaptation.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4645,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fwilds-workflows.md",3134,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Freferences\u002Fwilds-workflows.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Ftllib_domain_adaptation_smoke.py","SCRIPT","脚本",10516,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fdomain-adaptation\u002Fscripts\u002Ftllib_domain_adaptation_smoke.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]