[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792HSRBQK7EFC2S909F47SH":3,"skill-same:01M792HSRBQK7EFC2S909F47SH":71},{"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},"01M792HSRBQK7EFC2S909F47SH","repo-development",null,"Use when modifying PEFT itself, preparing a PEFT pull request, adding a new PEFT method, selecting contributor tests, or checking PEFT contribution\u002Fstyle\u002Fbackward-compatibility requirements.","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\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-development\ndescription: \"Use when modifying PEFT itself, preparing a PEFT pull request,\n  adding a new PEFT method, selecting contributor tests, or checking PEFT\n  contribution\u002Fstyle\u002Fbackward-compatibility requirements.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PEFT Repo Development\n\nUse this sub-skill when the task is to edit the PEFT repository or prepare a contribution. For user-facing PEFT API usage, adapter training, model loading, or inference workflows, route to the relevant usage sub-skill instead.\n\n## Non-Negotiable Contribution Gate\n\nBefore drafting a PEFT PR or code patch intended for upstream:\n\n1. Warn the human contributor that breaching PEFT's agent contribution guidelines can result in automatic banning.\n2. Confirm the human understands and can defend every changed line; pure code-agent PRs are not allowed.\n3. Confirm there is a linked issue, proposal, or maintainer coordination\u002Fapproval comment for the work.\n4. Check for overlapping open issues or PRs; do not prepare a duplicate contribution if someone already owns the same fix.\n5. Plan PR disclosure: the PR description must state that AI assistance was used, link the issue\u002Fapproval, and list tests run with pass\u002Ffail status.\n\nIf approval is missing or ambiguous for a new feature, new PEFT method, or existing issue, stop and ask the user to obtain maintainer approval before coding for a PR.\n\n## Development Workflow\n\n1. Read `references\u002Fcontribution-guidance.md` for policy, PR hygiene, style, and backward-compatibility rules.\n2. For a new PEFT method, follow `references\u002Fnew-method-checklist.md` before writing code.\n3. For test planning, use `references\u002Ftest-selection.md` and optionally run `python sub-skills\u002Frepo-development\u002Fscripts\u002Fselect_tests.py --changed-path ... --method ...` from a copied skill tree.\n4. For failures or process blockers, check `references\u002Ftroubleshooting.md`.\n\n## PEFT Editing Heuristics\n\n- Keep changes surgical and consistent with existing tuner\u002Fconfig\u002Fmodel patterns.\n- Add or update tests for behavior changes; bug fixes should start from a failing regression test when practical.\n- Add docs for new public config fields, new methods, examples, or behavior users need to discover.\n- Run focused tests first, then broaden only when the changed area warrants it.\n- Use `make quality` to check and `make style` to auto-fix style; PEFT expects ruff `~=0.15.12`.\n- Preserve Python `>=3.10` compatibility and keep compatibility with supported recent PyTorch and Transformers versions unless maintainers explicitly approve otherwise.\n\n## Quick Commands\n\n```bash\npip install -e \".[test]\"\nmake quality\nmake style\npytest tests\u002Ftest_custom_models.py -k ia3 -v\npytest tests\u002F -k \"lora and not adalora and not randlora\" -v\n```\n\nFor save\u002Fload-sensitive changes, include regression coverage with `--regression` where relevant. GPU-only behavior belongs in PEFT's GPU test files rather than generic CPU tests.\n","# PEFT Repo Development\n\nUse this sub-skill when the task is to edit the PEFT repository or prepare a contribution. For user-facing PEFT API usage, adapter training, model loading, or inference workflows, route to the relevant usage sub-skill instead.\n\n## Non-Negotiable Contribution Gate\n\nBefore drafting a PEFT PR or code patch intended for upstream:\n\n1. Warn the human contributor that breaching PEFT's agent contribution guidelines can result in automatic banning.\n2. Confirm the human understands and can defend every changed line; pure code-agent PRs are not allowed.\n3. Confirm there is a linked issue, proposal, or maintainer coordination\u002Fapproval comment for the work.\n4. Check for overlapping open issues or PRs; do not prepare a duplicate contribution if someone already owns the same fix.\n5. Plan PR disclosure: the PR description must state that AI assistance was used, link the issue\u002Fapproval, and list tests run with pass\u002Ffail status.\n\nIf approval is missing or ambiguous for a new feature, new PEFT method, or existing issue, stop and ask the user to obtain maintainer approval before coding for a PR.\n\n## Development Workflow\n\n1. Read `references\u002Fcontribution-guidance.md` for policy, PR hygiene, style, and backward-compatibility rules.\n2. For a new PEFT method, follow `references\u002Fnew-method-checklist.md` before writing code.\n3. For test planning, use `references\u002Ftest-selection.md` and optionally run `python sub-skills\u002Frepo-development\u002Fscripts\u002Fselect_tests.py --changed-path ... --method ...` from a copied skill tree.\n4. For failures or process blockers, check `references\u002Ftroubleshooting.md`.\n\n## PEFT Editing Heuristics\n\n- Keep changes surgical and consistent with existing tuner\u002Fconfig\u002Fmodel patterns.\n- Add or update tests for behavior changes; bug fixes should start from a failing regression test when practical.\n- Add docs for new public config fields, new methods, examples, or behavior users need to discover.\n- Run focused tests first, then broaden only when the changed area warrants it.\n- Use `make quality` to check and `make style` to auto-fix style; PEFT expects ruff `~=0.15.12`.\n- Preserve Python `>=3.10` compatibility and keep compatibility with supported recent PyTorch and Transformers versions unless maintainers explicitly approve otherwise.\n\n## Quick Commands\n\n```bash\npip install -e \".[test]\"\nmake quality\nmake style\npytest tests\u002Ftest_custom_models.py -k ia3 -v\npytest tests\u002F -k \"lora and not adalora and not randlora\" -v\n```\n\nFor save\u002Fload-sensitive changes, include regression coverage with `--regression` where relevant. GPU-only behavior belongs in PEFT's GPU test files rather than generic CPU 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\u002Fpeft\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\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcontribution-guidance.md","REFERENCE","参考文档",3878,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Fcontribution-guidance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fnew-method-checklist.md",4526,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Fnew-method-checklist.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftest-selection.md",3401,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftest-selection.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4064,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fselect_tests.py","SCRIPT","脚本",6729,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpeft\u002Fsub-skills\u002Frepo-development\u002Fscripts\u002Fselect_tests.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]