[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799HDH0K5F1P208SASZDJD2":3,"skill-same:01M799HDH0K5F1P208SASZDJD2":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M799HDH0K5F1P208SASZDJD2","test_time_protocol",null,"Validate fully test-time adaptation experiments so unlabeled target inputs are the only data used for adaptation updates.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Ftest_time_protocol\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: test_time_protocol\ndescription: Validate fully test-time adaptation experiments so unlabeled target inputs are the only data used for adaptation updates.\n---\n\n# Fully Test-Time Adaptation Protocol\n\nUse this skill when designing or auditing Tent-style adaptation experiments. It is appropriate for corruption robustness, domain adaptation, or proxy recovery runs where a source-trained model adapts during testing. Do not use it to justify domain adaptation that trains jointly on source and target data or any run that uses target labels in the adaptation loss.\n\n## Inputs\n\n- A JSON experiment metadata object with `adaptation_inputs`, `loss_inputs`, `evaluation_inputs`, and `mode` fields.\n- Optional `notes` explaining whether the run is online, offline target-only, continual, or episodic.\n\n## Outputs\n\n- A JSON validation report with `ok`, `violations`, and `allowed_adaptation_inputs`.\n- A concise protocol summary for recovery source manifests or experiment plans.\n\n## Workflow\n\n1. List all data consumed before and during optimizer steps.\n2. Allow target inputs and pretrained model parameters in the adaptation loop.\n3. Forbid source examples, source labels, target labels, and evaluation labels in the adaptation loss.\n4. Permit labels only in evaluation fields after adaptation.\n5. Record whether target batches are online, offline target-only, continual, or episodic.\n6. Treat any forbidden adaptation input as a blocking protocol violation.\n\n## Validation\n\nRun `python scripts\u002Fprotocol_check.py --self-test` or execute the tests with the Distiller skill validator. The self-test covers a valid target-only entropy run and invalid metadata that leaks labels into adaptation.\n\n## Limitations\n\nThis skill checks experiment metadata rather than inspecting arbitrary training code. Pair it with command logs, source manifests, and recovery traces for final acceptance.\n\n\n## Refinement Cycle 2\nA label-leakage ablation returned a nonzero status as expected; keep target labels evaluation-only in all recovery metadata.\n","# Fully Test-Time Adaptation Protocol\n\nUse this skill when designing or auditing Tent-style adaptation experiments. It is appropriate for corruption robustness, domain adaptation, or proxy recovery runs where a source-trained model adapts during testing. Do not use it to justify domain adaptation that trains jointly on source and target data or any run that uses target labels in the adaptation loss.\n\n## Inputs\n\n- A JSON experiment metadata object with `adaptation_inputs`, `loss_inputs`, `evaluation_inputs`, and `mode` fields.\n- Optional `notes` explaining whether the run is online, offline target-only, continual, or episodic.\n\n## Outputs\n\n- A JSON validation report with `ok`, `violations`, and `allowed_adaptation_inputs`.\n- A concise protocol summary for recovery source manifests or experiment plans.\n\n## Workflow\n\n1. List all data consumed before and during optimizer steps.\n2. Allow target inputs and pretrained model parameters in the adaptation loop.\n3. Forbid source examples, source labels, target labels, and evaluation labels in the adaptation loss.\n4. Permit labels only in evaluation fields after adaptation.\n5. Record whether target batches are online, offline target-only, continual, or episodic.\n6. Treat any forbidden adaptation input as a blocking protocol violation.\n\n## Validation\n\nRun `python scripts\u002Fprotocol_check.py --self-test` or execute the tests with the Distiller skill validator. The self-test covers a valid target-only entropy run and invalid metadata that leaks labels into adaptation.\n\n## Limitations\n\nThis skill checks experiment metadata rather than inspecting arbitrary training code. Pair it with command logs, source manifests, and recovery traces for final acceptance.\n\n\n## Refinement Cycle 2\nA label-leakage ablation returned a nonzero status as expected; keep target labels evaluation-only in all recovery metadata.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Ftest_time_protocol",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill test_time_protocol",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill test_time_protocol",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill test_time_protocol","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Ftest_time_protocol\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fprotocol_check.py","SCRIPT","脚本",2371,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Ftest_time_protocol\u002Fscripts\u002Fprotocol_check.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_protocol_check.py",545,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Ftest_time_protocol\u002Ftests\u002Ftest_protocol_check.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":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},"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":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},"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":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},"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":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},"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",[],[]]