[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799HAPA33SBKNFDHCD7WPE5":3,"skill-same:01M799HAPA33SBKNFDHCD7WPE5":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},"01M799HAPA33SBKNFDHCD7WPE5","recovery_evaluation",null,"Evaluate Tent recovery artifacts for numeric metrics, source-boundary compliance, and mechanism-faithful proxy evidence.","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\u002Frecovery_evaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: recovery_evaluation\ndescription: Evaluate Tent recovery artifacts for numeric metrics, source-boundary compliance, and mechanism-faithful proxy evidence.\n---\n\n# Recovery Evaluation and Mechanism Checks\n\nUse this skill after running a Tent recovery experiment. It is appropriate for full CIFAR\u002FImageNet recovery and for soft-mode reduced recovery. Do not accept a proxy solely because an accuracy value is high; the trace must show target-only entropy adaptation, changed modulation parameters, and executable evidence.\n\n## Inputs\n\n- `recovery_result.json` with paper target, metrics, commands, and mechanism checks.\n- `training_trace.json` with losses and parameter values before and after adaptation.\n- `source_manifest.json` and generated skill invocation logs.\n- `module_plan.json` fast recovery target.\n\n## Outputs\n\n- A validation report with `ok`, metric gaps, mechanism failures, and recommended decision.\n- Human-readable feedback for analysis artifacts.\n\n## Workflow\n\n1. Verify source manifests do not include original repository paths.\n2. Confirm recovery target metadata matches the module plan target.\n3. Check that at least one numeric metric is present.\n4. For proxy runs, require mechanism checks for target-only adaptation, entropy loss, normalization-affine update, and optimizer execution.\n5. Compare `loss_before` and `loss_after`, plus `params_before` and `params_after`.\n6. Recommend `accept` only when executable evidence and mechanism checks pass.\n\n## Validation\n\nRun `python scripts\u002Fevaluate_recovery.py --self-test`. The self-test checks a valid proxy trace and an invalid unchanged-parameter trace.\n\n## Limitations\n\nThis evaluator complements, but does not replace, Distiller's recovery experiment validator. Always run both in final recovery.\n\n\n## Refinement Cycle 4\nAn unchanged-parameter ablation produced a refine decision; proxy acceptance must require parameter or optimizer-state change, not metric text alone.\n","# Recovery Evaluation and Mechanism Checks\n\nUse this skill after running a Tent recovery experiment. It is appropriate for full CIFAR\u002FImageNet recovery and for soft-mode reduced recovery. Do not accept a proxy solely because an accuracy value is high; the trace must show target-only entropy adaptation, changed modulation parameters, and executable evidence.\n\n## Inputs\n\n- `recovery_result.json` with paper target, metrics, commands, and mechanism checks.\n- `training_trace.json` with losses and parameter values before and after adaptation.\n- `source_manifest.json` and generated skill invocation logs.\n- `module_plan.json` fast recovery target.\n\n## Outputs\n\n- A validation report with `ok`, metric gaps, mechanism failures, and recommended decision.\n- Human-readable feedback for analysis artifacts.\n\n## Workflow\n\n1. Verify source manifests do not include original repository paths.\n2. Confirm recovery target metadata matches the module plan target.\n3. Check that at least one numeric metric is present.\n4. For proxy runs, require mechanism checks for target-only adaptation, entropy loss, normalization-affine update, and optimizer execution.\n5. Compare `loss_before` and `loss_after`, plus `params_before` and `params_after`.\n6. Recommend `accept` only when executable evidence and mechanism checks pass.\n\n## Validation\n\nRun `python scripts\u002Fevaluate_recovery.py --self-test`. The self-test checks a valid proxy trace and an invalid unchanged-parameter trace.\n\n## Limitations\n\nThis evaluator complements, but does not replace, Distiller's recovery experiment validator. Always run both in final recovery.\n\n\n## Refinement Cycle 4\nAn unchanged-parameter ablation produced a refine decision; proxy acceptance must require parameter or optimizer-state change, not metric text alone.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Frecovery_evaluation",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 recovery_evaluation",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill recovery_evaluation",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill recovery_evaluation","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\u002Frecovery_evaluation\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fevaluate_recovery.py","SCRIPT","脚本",3166,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Frecovery_evaluation\u002Fscripts\u002Fevaluate_recovery.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_evaluate_recovery.py",902,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ftest-time-model-adaptation\u002Fskill\u002Ftent_entropy_minimization\u002Frecovery_evaluation\u002Ftests\u002Ftest_evaluate_recovery.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",[],[]]