[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799JCW5FE1CWYTQMC0FHT96":3,"skill-same:01M799JCW5FE1CWYTQMC0FHT96":60},{"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},"01M799JCW5FE1CWYTQMC0FHT96","rouge_l_evaluation",null,"Compute deterministic ROUGE-L style generation metrics for Natural Instructions recovery outputs and ablations.","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\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_evaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rouge_l_evaluation\ndescription: Compute deterministic ROUGE-L style generation metrics for Natural Instructions recovery outputs and ablations.\n---\n\n# Rouge L Evaluation\n\nUse this skill when reconstructing the BART0\u002FNatural Instructions cross-task generalization workflow without relying on the original paper repository. Do not use it for unrelated instruction-following papers unless the task uses a Natural-Instructions-style schema, task-level held-out evaluation, and generation metrics.\n\n## Inputs\n- Paper-derived module document and `module_plan.json`.\n- Small task records or instruction items supplied by the current recovery attempt.\n- Optional output paths for deterministic JSON artifacts.\n\n## Outputs\n- Deterministic JSON or Python return values that can be consumed by downstream recovery scripts.\n- Validation evidence from the included tests.\n\n## Workflow\n1. Read the current attempt inputs and keep source use inside the allowed recovery boundary.\n2. Apply the module contract exactly as described by the paper-derived module document.\n3. Write machine-readable artifacts when a CLI output path is provided.\n4. Cross-check downstream consumers with tests before accepting recovery evidence.\n\n## Validation\nRun `python \u003Cdistiller>\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cskill_dir> --run-tests` from any working directory. The included tests are standard-library compatible and do not require the original source repository.\n\n## Limitations\nThis skill preserves a reusable mechanism from the paper but does not by itself reproduce full BART-base training on all 61 Natural Instructions tasks. Full recovery requires a resolved dataset and model runtime; reduced recovery must remain explicitly marked as proxy evidence.\n","# Rouge L Evaluation\n\nUse this skill when reconstructing the BART0\u002FNatural Instructions cross-task generalization workflow without relying on the original paper repository. Do not use it for unrelated instruction-following papers unless the task uses a Natural-Instructions-style schema, task-level held-out evaluation, and generation metrics.\n\n## Inputs\n- Paper-derived module document and `module_plan.json`.\n- Small task records or instruction items supplied by the current recovery attempt.\n- Optional output paths for deterministic JSON artifacts.\n\n## Outputs\n- Deterministic JSON or Python return values that can be consumed by downstream recovery scripts.\n- Validation evidence from the included tests.\n\n## Workflow\n1. Read the current attempt inputs and keep source use inside the allowed recovery boundary.\n2. Apply the module contract exactly as described by the paper-derived module document.\n3. Write machine-readable artifacts when a CLI output path is provided.\n4. Cross-check downstream consumers with tests before accepting recovery evidence.\n\n## Validation\nRun `python \u003Cdistiller>\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cskill_dir> --run-tests` from any working directory. The included tests are standard-library compatible and do not require the original source repository.\n\n## Limitations\nThis skill preserves a reusable mechanism from the paper but does not by itself reproduce full BART-base training on all 61 Natural Instructions tasks. Full recovery requires a resolved dataset and model runtime; reduced recovery must remain explicitly marked as proxy evidence.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_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 rouge_l_evaluation",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rouge_l_evaluation",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rouge_l_evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_evaluation\u002FSKILL.md",true,[44,50,56],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"calibration_rules.json","REFERENCE","参考文档",104,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_evaluation\u002Fcalibration_rules.json",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"scripts\u002Frouge_l.py","SCRIPT","脚本",1290,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_evaluation\u002Fscripts\u002Frouge_l.py",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"tests\u002Ftest_rouge_l_evaluation.py",435,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fwhat-will-my-model-forget\u002Fskill\u002Fbart0_cross_task_generalization\u002Frouge_l_evaluation\u002Ftests\u002Ftest_rouge_l_evaluation.py",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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",[],[]]