[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7973DA8N2Y2NS6G4DZX7MAB":3,"skill-same:01M7973DA8N2Y2NS6G4DZX7MAB":67},{"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},"01M7973DA8N2Y2NS6G4DZX7MAB","training-and-configs",null,"Assemble verl PPO, GRPO, SFT, and on-policy distillation training commands, Hydra overrides, backend strategy switches, and config troubleshooting guidance.","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\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training-and-configs\ndescription: \"Assemble verl PPO, GRPO, SFT, and on-policy distillation training\n  commands, Hydra overrides, backend strategy switches, and config\n  troubleshooting guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# training-and-configs\n\nUse this sub-skill when a coding agent needs to build or debug verl training commands and Hydra config overrides for PPO-like RL, GRPO, SFT, or on-policy distillation.\n\n## Route by Task\n\n- **PPO \u002F critic training**: Use `references\u002Ftraining-workflows.md` for the `python -m verl.trainer.main_ppo` command shape, required actor\u002Fcritic\u002Fmodel\u002Fdata\u002Flogger overrides, and FSDP or Megatron examples.\n- **GRPO \u002F critic-less RL**: Use `references\u002Ftraining-workflows.md` for `algorithm.adv_estimator=grpo`, grouped rollout `n`, KL-loss settings, and no-critic command patterns.\n- **SFT**: Use `references\u002Ftraining-workflows.md` for `torchrun -m verl.trainer.sft_trainer`, `engine=fsdp`, dataset message keys, LoRA\u002FPEFT, and sequence-parallel switches.\n- **On-policy distillation**: Use `references\u002Ftraining-workflows.md` for `distillation.enabled=True`, teacher resource sizing, teacher model overrides, and distillation loss modes.\n- **Hydra and backend switches**: Use `references\u002Fconfiguration.md` before changing `model_engine`, FSDP\u002FFSDP2, Megatron, VeOmni, TorchTitan, rollout backend, batch, checkpoint, logger, or generated-reference config fields.\n- **Failures and validation errors**: Use `references\u002Ftroubleshooting.md` for overlong prompts, OOM, Hydra override syntax, config-doc CI, rollout backend mismatch, Ray\u002FGPU resource, and distillation teacher sizing problems.\n\n## Bundled Tool\n\n- `scripts\u002Fbuild_ppo_command.py` assembles a dry-run `python -m verl.trainer.main_ppo` command from common data, model, rollout, backend, batch, and logger options. It prints only; it never imports verl, starts Ray, downloads models, or runs training.\n\n## Boundaries\n\n- Dataset schema details, reward\u002Ftool internals, backend installation, and checkpoint merge\u002Fexport operations belong to other verl sub-skills or repo-level references.\n- Do not point future agents at source checkout examples or scripts as runtime dependencies; adapt their patterns into commands or use the bundled script here.\n","# training-and-configs\n\nUse this sub-skill when a coding agent needs to build or debug verl training commands and Hydra config overrides for PPO-like RL, GRPO, SFT, or on-policy distillation.\n\n## Route by Task\n\n- **PPO \u002F critic training**: Use `references\u002Ftraining-workflows.md` for the `python -m verl.trainer.main_ppo` command shape, required actor\u002Fcritic\u002Fmodel\u002Fdata\u002Flogger overrides, and FSDP or Megatron examples.\n- **GRPO \u002F critic-less RL**: Use `references\u002Ftraining-workflows.md` for `algorithm.adv_estimator=grpo`, grouped rollout `n`, KL-loss settings, and no-critic command patterns.\n- **SFT**: Use `references\u002Ftraining-workflows.md` for `torchrun -m verl.trainer.sft_trainer`, `engine=fsdp`, dataset message keys, LoRA\u002FPEFT, and sequence-parallel switches.\n- **On-policy distillation**: Use `references\u002Ftraining-workflows.md` for `distillation.enabled=True`, teacher resource sizing, teacher model overrides, and distillation loss modes.\n- **Hydra and backend switches**: Use `references\u002Fconfiguration.md` before changing `model_engine`, FSDP\u002FFSDP2, Megatron, VeOmni, TorchTitan, rollout backend, batch, checkpoint, logger, or generated-reference config fields.\n- **Failures and validation errors**: Use `references\u002Ftroubleshooting.md` for overlong prompts, OOM, Hydra override syntax, config-doc CI, rollout backend mismatch, Ray\u002FGPU resource, and distillation teacher sizing problems.\n\n## Bundled Tool\n\n- `scripts\u002Fbuild_ppo_command.py` assembles a dry-run `python -m verl.trainer.main_ppo` command from common data, model, rollout, backend, batch, and logger options. It prints only; it never imports verl, starts Ray, downloads models, or runs training.\n\n## Boundaries\n\n- Dataset schema details, reward\u002Ftool internals, backend installation, and checkpoint merge\u002Fexport operations belong to other verl sub-skills or repo-level references.\n- Do not point future agents at source checkout examples or scripts as runtime dependencies; adapt their patterns into commands or use the bundled script here.\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\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs",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 training-and-configs",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill training-and-configs",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill training-and-configs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fconfiguration.md","REFERENCE","参考文档",6919,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Fconfiguration.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftraining-workflows.md",10003,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Ftraining-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5908,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fbuild_ppo_command.py","SCRIPT","脚本",7426,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Ftraining-and-configs\u002Fscripts\u002Fbuild_ppo_command.py",[68,75,82,89,96,103],{"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},"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":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},"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":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},"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":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},"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":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},"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]