[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796PG0TF889APX41T4FX22K":3,"skill-same:01M796PG0TF889APX41T4FX22K":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},"01M796PG0TF889APX41T4FX22K","trl",null,"Use and modify TRL, the Hugging Face Transformers Reinforcement Learning library for post-training, CLI workflows, data\u002Freward utilities, scaling backends, experimental environments, and repo development.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: trl\ndescription: \"Use and modify TRL, the Hugging Face Transformers Reinforcement\n  Learning library for post-training, CLI workflows, data\u002Freward utilities,\n  scaling backends, experimental environments, and repo development.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TRL Repo Skill\n\nUse this skill for TRL (Transformers Reinforcement Learning), a Hugging Face library for post-training foundation models with SFT, DPO, GRPO, reward modeling, RLOO, experimental RLHF methods, CLI launchers, dataset utilities, reward functions, and scaling integrations.\n\n## Start Here\n\n- Read [repo provenance](references\u002Frepo-provenance.md) before deciding whether this skill matches a current checkout or should be refreshed.\n- Read [installation and extras](references\u002Finstallation-and-extras.md) when a task involves installing TRL, optional extras, Python versions, or import checks.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, CLI, data, backend, and repo-development failures.\n- Run `scripts\u002Fcheck_trl_environment.py --help` when you need a safe local diagnostic helper; it checks imports, metadata, CLI help, and optional packages without training or downloads.\n\n## Route by Task\n\n- Use [core-training](sub-skills\u002Fcore-training\u002FSKILL.md) for stable trainer selection and API usage: `SFTTrainer`, `DPOTrainer`, `GRPOTrainer`, `RewardTrainer`, `RLOOTrainer`, and their configs.\n- Use [data-and-rewards](sub-skills\u002Fdata-and-rewards\u002FSKILL.md) for dataset schemas, chat templates, multimodal messages, packing, prompt extraction, tool-call parsing, and built-in reward functions.\n- Use [cli-and-configs](sub-skills\u002Fcli-and-configs\u002FSKILL.md) for `trl` commands, YAML configs, dataset mixtures, `trl env`, `trl skills`, and command\u002Fconfig parser troubleshooting.\n- Use [scaling-and-backends](sub-skills\u002Fscaling-and-backends\u002FSKILL.md) for Accelerate, FSDP, DeepSpeed, PEFT, quantization, Liger, Unsloth, Kernels Hub, vLLM, memory planning, and optional backend diagnostics.\n- Use [experimental-and-environments](sub-skills\u002Fexperimental-and-environments\u002FSKILL.md) for `trl.experimental`, experimental trainers, `GRPOTrainer(environment_factory=...)`, OpenEnv, OpenReward, Harbor, and tool-calling environment training.\n- Use [repo-development](sub-skills\u002Frepo-development\u002FSKILL.md) when modifying this repository: duplicated trainer logic, tests, docs, paper index updates, packaged skills, and contribution policy.\n\n## Minimal Install and Import Check\n\nInstall the public package for normal use:\n\n```bash\npip install trl\npython - \u003C\u003C'PY'\nimport trl\nfrom trl import SFTTrainer, DPOTrainer, GRPOTrainer, RewardTrainer\nprint('trl import ok')\nPY\n```\n\nFor source development, use an editable install from the checkout:\n\n```bash\npip install -e .\ntrl --help\ntrl env\n```\n\nInstall optional extras only when the selected workflow needs them. Examples include `trl[peft]` for adapter training, `trl[vllm]` for vLLM generation\u002Fserver support, `trl[deepspeed]` for DeepSpeed, `trl[vlm]` for vision-language examples, `trl[openreward]` for OpenReward integration, and `trl[harbor]` for Harbor tasks. Avoid broad dev installs unless doing repository development.\n\n## Common Workflow Routing\n\n- **\"Fine-tune a model with SFT\u002FDPO\u002FGRPO\"**: start in `core-training`, then use `data-and-rewards` for dataset shape and `cli-and-configs` if the user wants a command or YAML file.\n- **\"My dataset columns or chat template are wrong\"**: start in `data-and-rewards`; use its validator script before changing trainer code.\n- **\"Generate a `trl sft` or `trl grpo` command\"**: start in `cli-and-configs`, then cross-check trainer semantics in `core-training`.\n- **\"Use vLLM, DeepSpeed, FSDP, LoRA, quantization, or Unsloth\"**: start in `scaling-and-backends`; do not start servers or training jobs unless the user asked and prerequisites are available.\n- **\"Train with tools, OpenEnv, OpenReward, or Harbor\"**: start in `experimental-and-environments`; verify extras, services, credentials, and stability warnings.\n- **\"Edit TRL internals\"**: start in `repo-development`; maintain duplicated trainer logic consistency and update `docs\u002Fsource\u002Fpaper_index.md` for paper-backed methods.\n\n## Safety and Validation\n\n- Prefer read-only checks first: imports, `trl --help`, config rendering, dataset validation, and optional backend diagnostics.\n- Treat examples, notebooks, long training runs, vLLM servers, Docker\u002Fsandbox tasks, and distributed jobs as expensive or environment-dependent unless explicitly requested.\n- Do not assume optional dependencies are installed because the base package imports.\n- Keep trainer changes consistent across duplicated blocks when editing the repository.\n- Use focused tests for changed areas; skip invariant, distributed, service, GPU, or long-running candidates unless they match the change and the environment supports them.\n","# TRL Repo Skill\n\nUse this skill for TRL (Transformers Reinforcement Learning), a Hugging Face library for post-training foundation models with SFT, DPO, GRPO, reward modeling, RLOO, experimental RLHF methods, CLI launchers, dataset utilities, reward functions, and scaling integrations.\n\n## Start Here\n\n- Read [repo provenance](references\u002Frepo-provenance.md) before deciding whether this skill matches a current checkout or should be refreshed.\n- Read [installation and extras](references\u002Finstallation-and-extras.md) when a task involves installing TRL, optional extras, Python versions, or import checks.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, CLI, data, backend, and repo-development failures.\n- Run `scripts\u002Fcheck_trl_environment.py --help` when you need a safe local diagnostic helper; it checks imports, metadata, CLI help, and optional packages without training or downloads.\n\n## Route by Task\n\n- Use [core-training](sub-skills\u002Fcore-training\u002FSKILL.md) for stable trainer selection and API usage: `SFTTrainer`, `DPOTrainer`, `GRPOTrainer`, `RewardTrainer`, `RLOOTrainer`, and their configs.\n- Use [data-and-rewards](sub-skills\u002Fdata-and-rewards\u002FSKILL.md) for dataset schemas, chat templates, multimodal messages, packing, prompt extraction, tool-call parsing, and built-in reward functions.\n- Use [cli-and-configs](sub-skills\u002Fcli-and-configs\u002FSKILL.md) for `trl` commands, YAML configs, dataset mixtures, `trl env`, `trl skills`, and command\u002Fconfig parser troubleshooting.\n- Use [scaling-and-backends](sub-skills\u002Fscaling-and-backends\u002FSKILL.md) for Accelerate, FSDP, DeepSpeed, PEFT, quantization, Liger, Unsloth, Kernels Hub, vLLM, memory planning, and optional backend diagnostics.\n- Use [experimental-and-environments](sub-skills\u002Fexperimental-and-environments\u002FSKILL.md) for `trl.experimental`, experimental trainers, `GRPOTrainer(environment_factory=...)`, OpenEnv, OpenReward, Harbor, and tool-calling environment training.\n- Use [repo-development](sub-skills\u002Frepo-development\u002FSKILL.md) when modifying this repository: duplicated trainer logic, tests, docs, paper index updates, packaged skills, and contribution policy.\n\n## Minimal Install and Import Check\n\nInstall the public package for normal use:\n\n```bash\npip install trl\npython - \u003C\u003C'PY'\nimport trl\nfrom trl import SFTTrainer, DPOTrainer, GRPOTrainer, RewardTrainer\nprint('trl import ok')\nPY\n```\n\nFor source development, use an editable install from the checkout:\n\n```bash\npip install -e .\ntrl --help\ntrl env\n```\n\nInstall optional extras only when the selected workflow needs them. Examples include `trl[peft]` for adapter training, `trl[vllm]` for vLLM generation\u002Fserver support, `trl[deepspeed]` for DeepSpeed, `trl[vlm]` for vision-language examples, `trl[openreward]` for OpenReward integration, and `trl[harbor]` for Harbor tasks. Avoid broad dev installs unless doing repository development.\n\n## Common Workflow Routing\n\n- **\"Fine-tune a model with SFT\u002FDPO\u002FGRPO\"**: start in `core-training`, then use `data-and-rewards` for dataset shape and `cli-and-configs` if the user wants a command or YAML file.\n- **\"My dataset columns or chat template are wrong\"**: start in `data-and-rewards`; use its validator script before changing trainer code.\n- **\"Generate a `trl sft` or `trl grpo` command\"**: start in `cli-and-configs`, then cross-check trainer semantics in `core-training`.\n- **\"Use vLLM, DeepSpeed, FSDP, LoRA, quantization, or Unsloth\"**: start in `scaling-and-backends`; do not start servers or training jobs unless the user asked and prerequisites are available.\n- **\"Train with tools, OpenEnv, OpenReward, or Harbor\"**: start in `experimental-and-environments`; verify extras, services, credentials, and stability warnings.\n- **\"Edit TRL internals\"**: start in `repo-development`; maintain duplicated trainer logic consistency and update `docs\u002Fsource\u002Fpaper_index.md` for paper-backed methods.\n\n## Safety and Validation\n\n- Prefer read-only checks first: imports, `trl --help`, config rendering, dataset validation, and optional backend diagnostics.\n- Treat examples, notebooks, long training runs, vLLM servers, Docker\u002Fsandbox tasks, and distributed jobs as expensive or environment-dependent unless explicitly requested.\n- Do not assume optional dependencies are installed because the base package imports.\n- Keep trainer changes consistent across duplicated blocks when editing the repository.\n- Use focused tests for changed areas; skip invariant, distributed, service, GPU, or long-running candidates unless they match the change and the environment supports them.\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",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 trl",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill trl",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill trl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation-and-extras.md","REFERENCE","参考文档",2770,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Freferences\u002Finstallation-and-extras.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1955,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",452,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",3523,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_trl_environment.py","SCRIPT","脚本",3451,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftrl\u002Fscripts\u002Fcheck_trl_environment.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",[],[]]