[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799AD415W48NWZ1BHFPCRHR":3,"skill-same:01M799AD415W48NWZ1BHFPCRHR":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},"01M799AD415W48NWZ1BHFPCRHR","model_adapter_interface",null,"Use this skill when you need to wrap a model backend behind loglikelihood, rolling loglikelihood, and generation request methods.","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\u002Fstay-on-topic-with-classifier-free-guidance\u002Fskill\u002Flm_evaluation_harness\u002Fmodel_adapter_interface\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model_adapter_interface\ndescription: Use this skill when you need to wrap a model backend behind loglikelihood, rolling loglikelihood, and generation request methods.\n---\n\n# model_adapter_interface\n\n## When to use\nUse this skill for paper-style language model evaluation harness work where reproducibility depends on explicit task contracts, model-request interfaces, response post-processing, metric aggregation, or an end-to-end auditable run. Do not use it to claim real leaderboard performance without a real model and dataset.\n\n## Inputs\n- Small JSON-like task, request, response, or metric records depending on the module.\n- Optional deterministic fake model\u002Fdata fixtures for bounded validation.\n- A recovery attempt directory when producing experiment evidence.\n\n## Outputs\n- Validated Python dictionaries or JSON artifacts with deterministic fields.\n- Clear traces that keep raw responses separate from filtered predictions and scores.\n\n## Workflow\n1. Read the task\u002Fmodule contract before executing code.\n2. Validate required fields and fail loudly on incompatible output types or missing metrics.\n3. Preserve raw inputs and produce explicit trace records for downstream modules.\n4. Keep this skill self-contained and avoid reading the original lm-evaluation-harness repository during recovery.\n5. Run the validation command below after edits.\n\n## Validation\nRun `python \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cskill_dir> --run-tests`.\n\n## Limitations\nThese utilities are compact faithful proxies for the harness mechanisms. They are not a replacement for the full upstream package when full-scale benchmark evaluation is required.\n","# model_adapter_interface\n\n## When to use\nUse this skill for paper-style language model evaluation harness work where reproducibility depends on explicit task contracts, model-request interfaces, response post-processing, metric aggregation, or an end-to-end auditable run. Do not use it to claim real leaderboard performance without a real model and dataset.\n\n## Inputs\n- Small JSON-like task, request, response, or metric records depending on the module.\n- Optional deterministic fake model\u002Fdata fixtures for bounded validation.\n- A recovery attempt directory when producing experiment evidence.\n\n## Outputs\n- Validated Python dictionaries or JSON artifacts with deterministic fields.\n- Clear traces that keep raw responses separate from filtered predictions and scores.\n\n## Workflow\n1. Read the task\u002Fmodule contract before executing code.\n2. Validate required fields and fail loudly on incompatible output types or missing metrics.\n3. Preserve raw inputs and produce explicit trace records for downstream modules.\n4. Keep this skill self-contained and avoid reading the original lm-evaluation-harness repository during recovery.\n5. Run the validation command below after edits.\n\n## Validation\nRun `python \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cskill_dir> --run-tests`.\n\n## Limitations\nThese utilities are compact faithful proxies for the harness mechanisms. They are not a replacement for the full upstream package when full-scale benchmark evaluation is required.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fstay-on-topic-with-classifier-free-guidance\u002Fskill\u002Flm_evaluation_harness\u002Fmodel_adapter_interface",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 model_adapter_interface",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model_adapter_interface",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model_adapter_interface","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fstay-on-topic-with-classifier-free-guidance\u002Fskill\u002Flm_evaluation_harness\u002Fmodel_adapter_interface\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fadapter.py","SCRIPT","脚本",1220,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fstay-on-topic-with-classifier-free-guidance\u002Fskill\u002Flm_evaluation_harness\u002Fmodel_adapter_interface\u002Fscripts\u002Fadapter.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_adapter.py",599,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fstay-on-topic-with-classifier-free-guidance\u002Fskill\u002Flm_evaluation_harness\u002Fmodel_adapter_interface\u002Ftests\u002Ftest_adapter.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",[],[]]