[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796JXY62BZ73FXGGMMPQNHD":3,"skill-same:01M796JXY62BZ73FXGGMMPQNHD":70},{"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},"01M796JXY62BZ73FXGGMMPQNHD","self-training",null,"Operate Transfer Learning Library semi-supervised and self-training workflows using TLLib pseudo-label, consistency, teacher, thresholding, and debiasing APIs.","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\u002Fself-training\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: self-training\ndescription: \"Operate Transfer Learning Library semi-supervised and\n  self-training workflows using TLLib pseudo-label, consistency, teacher,\n  thresholding, and debiasing APIs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Self-Training Skill\n\nUse this sub-skill when a user needs TLLib guidance for **semi-supervised learning** or **self-training** on image classification tasks: pseudo-labeling, Pi Model, Mean Teacher, UDA, FixMatch, FlexMatch, Self-Tuning, DST, DebiasMatch-style thresholding, Noisy Student, or MCC-like self-training regularizers.\n\n## Route here for\n\n- Confidence-based pseudo-label selection, consistency losses, weak\u002Fstrong augmentation training loops, EMA teacher\u002Fstudent updates, dynamic thresholding, class-balance regularization, DST worst-case estimation, and Self-Tuning queues.\n- Choosing between Pseudo Label, Pi Model, Mean Teacher, UDA, FixMatch, FlexMatch, Noisy Student, Self-Tuning, DebiasMatch-style debiasing, DST, and MCC-style regularization.\n- Safe CPU checks for `tllib.self_training` losses\u002Fhelpers without datasets, checkpoints, GPUs, or benchmark training.\n- MoCo-style checkpoint conversion planning before SSL fine-tuning.\n\n## Route elsewhere\n\n- Datasets, image-list formats, class-balanced labeled subsets, transforms, model factories, metrics, and utility loaders: [vision-data-models](..\u002Fvision-data-models\u002FSKILL.md).\n- Task adaptation \u002F fine-tuning regularizers or checkpoint use after conversion: [task-generalization](..\u002Ftask-generalization\u002FSKILL.md).\n- Domain-adaptation tasks that use MCC on target-domain predictions: [domain-adaptation](..\u002Fdomain-adaptation\u002FSKILL.md).\n\n## Operating sequence\n\n1. Confirm the task is semi-supervised\u002Fself-training: a small labeled split plus a larger unlabeled split, or a teacher\u002Fstudent self-training loop. If the user is adapting across source\u002Ftarget domains, route DA-specific pieces to [domain-adaptation](..\u002Fdomain-adaptation\u002FSKILL.md).\n2. Confirm data\u002Fmodel readiness through [vision-data-models](..\u002Fvision-data-models\u002FSKILL.md). Full SSL training needs datasets, class-balanced labeled sampling, weak\u002Fstrong augmentations, pretrained backbones or checkpoints, and usually CUDA; this sub-skill only claims CPU component-level verification.\n3. Choose the method family:\n   - Simple pseudo labels: `ConfidenceBasedSelfTrainingLoss`.\n   - Prediction consistency: `L2ConsistencyLoss` \u002F `ConsistencyLoss`.\n   - Teacher\u002Fstudent averaging: `EMATeacher` plus a consistency loss.\n   - Weak\u002Fstrong augmentation: UDA or FixMatch-style losses.\n   - Curriculum thresholding: `DynamicThresholdingModule` for FlexMatch.\n   - Self-supervised or contrastive adaptation: Self-Tuning and MoCo checkpoint conversion.\n   - Debiasing: DST heads\u002Flosses or DebiasMatch-style class-balance\u002Fthreshold checks.\n4. Use the bundled references for API signatures, workflow recipes, checkpoint conversion, and troubleshooting. Do not copy or execute repository benchmark trainers as runtime helpers.\n5. For installation\u002FAPI sanity, run `scripts\u002Ftllib_self_training_smoke.py` from any directory where `tllib` is installed.\n\n## References\n\n- [API reference](references\u002Fapi-reference.md)\n- [Self-training workflows](references\u002Fself-training-workflows.md)\n- [Checkpoint conversion](references\u002Fcheckpoint-conversion.md)\n- [Troubleshooting](references\u002Ftroubleshooting.md)\n\n## Verification status\n\nThe bundled smoke script exercises tiny CPU tensors for pseudo-label selection, consistency, EMA teacher updates, UDA weak\u002Fstrong loss, MCC, FlexMatch dynamic thresholds, class-balance loss, and DST worst-case estimation. It does **not** run benchmark training, download datasets, download pretrained checkpoints, perform MoCo conversion on external files, or verify optional `timm`\u002FCUDA training stacks.\n","# Self-Training Skill\n\nUse this sub-skill when a user needs TLLib guidance for **semi-supervised learning** or **self-training** on image classification tasks: pseudo-labeling, Pi Model, Mean Teacher, UDA, FixMatch, FlexMatch, Self-Tuning, DST, DebiasMatch-style thresholding, Noisy Student, or MCC-like self-training regularizers.\n\n## Route here for\n\n- Confidence-based pseudo-label selection, consistency losses, weak\u002Fstrong augmentation training loops, EMA teacher\u002Fstudent updates, dynamic thresholding, class-balance regularization, DST worst-case estimation, and Self-Tuning queues.\n- Choosing between Pseudo Label, Pi Model, Mean Teacher, UDA, FixMatch, FlexMatch, Noisy Student, Self-Tuning, DebiasMatch-style debiasing, DST, and MCC-style regularization.\n- Safe CPU checks for `tllib.self_training` losses\u002Fhelpers without datasets, checkpoints, GPUs, or benchmark training.\n- MoCo-style checkpoint conversion planning before SSL fine-tuning.\n\n## Route elsewhere\n\n- Datasets, image-list formats, class-balanced labeled subsets, transforms, model factories, metrics, and utility loaders: [vision-data-models](..\u002Fvision-data-models\u002FSKILL.md).\n- Task adaptation \u002F fine-tuning regularizers or checkpoint use after conversion: [task-generalization](..\u002Ftask-generalization\u002FSKILL.md).\n- Domain-adaptation tasks that use MCC on target-domain predictions: [domain-adaptation](..\u002Fdomain-adaptation\u002FSKILL.md).\n\n## Operating sequence\n\n1. Confirm the task is semi-supervised\u002Fself-training: a small labeled split plus a larger unlabeled split, or a teacher\u002Fstudent self-training loop. If the user is adapting across source\u002Ftarget domains, route DA-specific pieces to [domain-adaptation](..\u002Fdomain-adaptation\u002FSKILL.md).\n2. Confirm data\u002Fmodel readiness through [vision-data-models](..\u002Fvision-data-models\u002FSKILL.md). Full SSL training needs datasets, class-balanced labeled sampling, weak\u002Fstrong augmentations, pretrained backbones or checkpoints, and usually CUDA; this sub-skill only claims CPU component-level verification.\n3. Choose the method family:\n   - Simple pseudo labels: `ConfidenceBasedSelfTrainingLoss`.\n   - Prediction consistency: `L2ConsistencyLoss` \u002F `ConsistencyLoss`.\n   - Teacher\u002Fstudent averaging: `EMATeacher` plus a consistency loss.\n   - Weak\u002Fstrong augmentation: UDA or FixMatch-style losses.\n   - Curriculum thresholding: `DynamicThresholdingModule` for FlexMatch.\n   - Self-supervised or contrastive adaptation: Self-Tuning and MoCo checkpoint conversion.\n   - Debiasing: DST heads\u002Flosses or DebiasMatch-style class-balance\u002Fthreshold checks.\n4. Use the bundled references for API signatures, workflow recipes, checkpoint conversion, and troubleshooting. Do not copy or execute repository benchmark trainers as runtime helpers.\n5. For installation\u002FAPI sanity, run `scripts\u002Ftllib_self_training_smoke.py` from any directory where `tllib` is installed.\n\n## References\n\n- [API reference](references\u002Fapi-reference.md)\n- [Self-training workflows](references\u002Fself-training-workflows.md)\n- [Checkpoint conversion](references\u002Fcheckpoint-conversion.md)\n- [Troubleshooting](references\u002Ftroubleshooting.md)\n\n## Verification status\n\nThe bundled smoke script exercises tiny CPU tensors for pseudo-label selection, consistency, EMA teacher updates, UDA weak\u002Fstrong loss, MCC, FlexMatch dynamic thresholds, class-balance loss, and DST worst-case estimation. It does **not** run benchmark training, download datasets, download pretrained checkpoints, perform MoCo conversion on external files, or verify optional `timm`\u002FCUDA training stacks.\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\u002Fself-training",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 self-training",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill self-training",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill self-training","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\u002Fself-training\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",11274,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fself-training\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcheckpoint-conversion.md",5751,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fself-training\u002Freferences\u002Fcheckpoint-conversion.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fself-training-workflows.md",12627,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fself-training\u002Freferences\u002Fself-training-workflows.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",9029,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fself-training\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Ftllib_self_training_smoke.py","SCRIPT","脚本",10340,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftransfer-learning-library\u002Fsub-skills\u002Fself-training\u002Fscripts\u002Ftllib_self_training_smoke.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]