[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796PZT3NVMN3W23T4R5GDX8":3,"skill-same:01M796PZT3NVMN3W23T4R5GDX8":61},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M796PZT3NVMN3W23T4R5GDX8","repo-development",null,"Modify the TRL repository safely as a contributor or maintainer, including trainer consistency, docs, tests, and packaged skills.","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\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-development\ndescription: \"Modify the TRL repository safely as a contributor or maintainer,\n  including trainer consistency, docs, tests, and packaged skills.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TRL Repo Development\n\nUse this sub-skill when changing the TRL codebase itself: trainer internals, configs, docs, tests, packaged skills, or contribution hygiene. Do not use it for end-user training runs; route usage questions to the training-oriented TRL skills instead.\n\n## Route By Change Type\n\n- **Trainer or config edits**: follow [contributor guidance](references\u002Fcontributor-guidance.md) before changing `trl\u002Ftrainer\u002F` or `trl\u002Fexperimental\u002F`; duplicated trainer logic must stay aligned across copies.\n- **Paper-method additions**: add the implementation, docs, targeted tests, and a `docs\u002Fsource\u002Fpaper_index.md` subsection for the method or algorithm.\n- **Docs or public API docs**: use TRL docstring style and Hugging Face paper links; keep examples small and runnable.\n- **Test planning**: choose the narrowest relevant unit, CLI, distributed, or invariant tests using [test selection](references\u002Ftest-selection.md).\n- **Packaged skill changes**: update bundled skill content and the skill install\u002Flist tests together so installed skills remain discoverable.\n- **Unexpected review failures**: diagnose common repository-policy issues with [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Safety Rules\n\n- Preserve self-contained trainers. Do not introduce shared abstractions for generation, reward computation, metric logging, or weight syncing just to remove duplication.\n- When editing duplicated logic, update every matching trainer block with the same variable names, branch order, and comments unless trainer semantics require a documented difference.\n- Keep main code stable and well-tested; keep experimental edits small and non-invasive unless the task explicitly targets experimental development.\n- Prefer direct, lean changes over registries, factories, broad fallbacks, or speculative compatibility branches.\n- Run only the tests needed for confidence first, then broaden if the change touches shared behavior or public interfaces.\n\n## Quick Checklists\n\n- **Duplicated vLLM logic**: compare online trainers that share `_generate_single_turn`, weight-sync state, and vLLM branches; propagate the same structural edit across GRPO\u002FRLOO and relevant experimental online trainers.\n- **New paper trainer**: add trainer\u002Fconfig files, expose imports\u002FCLI docs as appropriate, add targeted tests, document user-facing behavior, and update `docs\u002Fsource\u002Fpaper_index.md` with a Hugging Face paper URL.\n- **Docstring\u002FAPI change**: use backticked types, `*optional*`, `defaults to ...`, `or` unions, and Transformers reference links in the repository style.\n- **Skill packaging change**: keep `SKILL.md` frontmatter valid, preserve installable directory structure, and cover discovery\u002Finstall behavior in skill tests.\n","# TRL Repo Development\n\nUse this sub-skill when changing the TRL codebase itself: trainer internals, configs, docs, tests, packaged skills, or contribution hygiene. Do not use it for end-user training runs; route usage questions to the training-oriented TRL skills instead.\n\n## Route By Change Type\n\n- **Trainer or config edits**: follow [contributor guidance](references\u002Fcontributor-guidance.md) before changing `trl\u002Ftrainer\u002F` or `trl\u002Fexperimental\u002F`; duplicated trainer logic must stay aligned across copies.\n- **Paper-method additions**: add the implementation, docs, targeted tests, and a `docs\u002Fsource\u002Fpaper_index.md` subsection for the method or algorithm.\n- **Docs or public API docs**: use TRL docstring style and Hugging Face paper links; keep examples small and runnable.\n- **Test planning**: choose the narrowest relevant unit, CLI, distributed, or invariant tests using [test selection](references\u002Ftest-selection.md).\n- **Packaged skill changes**: update bundled skill content and the skill install\u002Flist tests together so installed skills remain discoverable.\n- **Unexpected review failures**: diagnose common repository-policy issues with [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Safety Rules\n\n- Preserve self-contained trainers. Do not introduce shared abstractions for generation, reward computation, metric logging, or weight syncing just to remove duplication.\n- When editing duplicated logic, update every matching trainer block with the same variable names, branch order, and comments unless trainer semantics require a documented difference.\n- Keep main code stable and well-tested; keep experimental edits small and non-invasive unless the task explicitly targets experimental development.\n- Prefer direct, lean changes over registries, factories, broad fallbacks, or speculative compatibility branches.\n- Run only the tests needed for confidence first, then broaden if the change touches shared behavior or public interfaces.\n\n## Quick Checklists\n\n- **Duplicated vLLM logic**: compare online trainers that share `_generate_single_turn`, weight-sync state, and vLLM branches; propagate the same structural edit across GRPO\u002FRLOO and relevant experimental online trainers.\n- **New paper trainer**: add trainer\u002Fconfig files, expose imports\u002FCLI docs as appropriate, add targeted tests, document user-facing behavior, and update `docs\u002Fsource\u002Fpaper_index.md` with a Hugging Face paper URL.\n- **Docstring\u002FAPI change**: use backticked types, `*optional*`, `defaults to ...`, `or` unions, and Transformers reference links in the repository style.\n- **Skill packaging change**: keep `SKILL.md` frontmatter valid, preserve installable directory structure, and cover discovery\u002Finstall behavior in skill tests.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill repo-development",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill repo-development",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill repo-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcontributor-guidance.md","REFERENCE","参考文档",6071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Fcontributor-guidance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftest-selection.md",4668,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftest-selection.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4712,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"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},"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":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},"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":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},"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":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},"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":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},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]