[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78S7WFPSW6V0G93B10NE5JS":3,"skill-same:01M78S7WFPSW6V0G93B10NE5JS":75},{"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},"01M78S7WFPSW6V0G93B10NE5JS","agilerl",null,"Use AgileRL for reinforcement learning workflows: classical RL training, evolutionary HPO, evolvable networks, multi-agent PettingZoo training, offline\u002Fbandit data, and LLM fine-tuning.","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\u002Fagilerl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agilerl\ndescription: \"Use AgileRL for reinforcement learning workflows: classical RL\n  training, evolutionary HPO, evolvable networks, multi-agent PettingZoo\n  training, offline\u002Fbandit data, and LLM fine-tuning.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# AgileRL\n\nUse this repo skill when a task involves AgileRL, `agilerl`, evolutionary hyperparameter optimization for RL, Gymnasium\u002FPettingZoo training with AgileRL algorithms, AgileRL evolvable modules\u002Fnetworks, offline RL datasets, contextual bandits, or AgileRL LLM post-training.\n\n## Quick Start\n\n- Install: `pip install agilerl`.\n- Optional LLM stack: `pip install \"agilerl[llm]\"` only when the task uses GRPO\u002FCISPO\u002FGSPO, DPO\u002FSFT, vLLM, PEFT, DeepSpeed, or transformer datasets.\n- Import check: `python -c \"import agilerl, importlib.metadata as md; print(md.version('agilerl'))\"`.\n- Read `references\u002Fpackage-overview.md` for the algorithm family map, `references\u002Ftroubleshooting.md` for cross-cutting dependency\u002Fbackend issues, and `references\u002Frepo-provenance.md` when checking whether this skill is stale.\n- Run `scripts\u002Fcheck_agilerl_install.py --help` for a safe local capability probe; it does not train, download models, or require the source checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Train PPO, DQN, RainbowDQN, DDPG, or TD3 on Gymnasium; wire `create_population`, `train_on_policy`, `train_off_policy`, replay\u002Frollout buffers, or distributed classical training | `sub-skills\u002Ftraining-workflows\u002FSKILL.md` |\n| Configure tournament selection, mutations, mutable RL hyperparameters, architecture mutation probabilities, or population evolution | `sub-skills\u002Fhpo-and-mutation\u002FSKILL.md` |\n| Build custom `EvolvableModule`\u002F`EvolvableNetwork` objects, `net_config`, MLP\u002FCNN\u002FLSTM\u002FMultiInput\u002FSimBa configs, actors, critics, or `DummyEvolvable` wrappers | `sub-skills\u002Fevolvable-modules\u002FSKILL.md` |\n| Use PettingZoo multi-agent training, `MADDPG`, `MATD3`, `IPPO`, `AsyncPettingZooVecEnv`, agent id grouping, or AgileRL wrappers | `sub-skills\u002Fmulti-agent-and-wrappers\u002FSKILL.md` |\n| Use offline datasets, HDF5\u002FMinari conversion, replay filling, `CQL`\u002F`ILQL`, contextual bandits, `NeuralUCB`, `NeuralTS`, or `BanditEnv` | `sub-skills\u002Foffline-bandits-data\u002FSKILL.md` |\n| Plan LLM fine-tuning\u002Fpost-training with `GRPO`, `CISPO`, `GSPO`, LLM PPO, REINFORCE, `SFT`, `DPO`, vLLM, DeepSpeed, PEFT, or AgileRL LLM envs | `sub-skills\u002Fllm-fine-tuning\u002FSKILL.md` |\n| Compare benchmark scripts or adapt performance runs safely | `references\u002Fbenchmarking.md` |\n\n## Common AgileRL Building Blocks\n\n- Algorithms: `PPO`, `DQN`, `RainbowDQN`, `DDPG`, `TD3`, `CQN`, `ILQL`, `NeuralUCB`, `NeuralTS`, `MADDPG`, `MATD3`, `IPPO`, `GRPO`, `CISPO`, `GSPO`, LLM PPO, REINFORCE, `SFT`, and `DPO`.\n- Population setup usually starts with `agilerl.utils.utils.create_population(...)` and a Gymnasium or PettingZoo observation\u002Faction space.\n- Evolution usually combines `TournamentSelection(...)` and `Mutations(...)`; use `HyperparameterConfig` and `RLParameter` for mutable algorithm attributes.\n- Network configuration usually uses `net_config` with `encoder_config`, `head_config`, and optional recurrent\u002FCNN\u002FMultiInput fields.\n- Training helpers return trained populations and fitness metrics; full training can be long, so prefer import\u002Fconfig\u002Fsmoke checks before launching runs.\n\n## Safe Validation Pattern\n\n1. Check installation and optional dependency availability with `scripts\u002Fcheck_agilerl_install.py`.\n2. Validate spaces, algorithm names, `INIT_HP`, `net_config`, and HPO configs with the nearest sub-skill helper script.\n3. Run tiny constructor\u002Fimport checks before full training.\n4. Treat demos, tutorials, benchmark launchers, and original repo tests as evidence only; do not depend on the AgileRL source checkout from this generated skill.\n5. For long training, LLM, GPU, vLLM, DeepSpeed, Minari remote, UCI, or benchmark tasks, document required hardware\u002Fdata\u002Fnetwork first and ask before expensive execution.\n\n## Troubleshooting First Reads\n\n- Install\u002Fimport, Python version, missing optional extras, Torch\u002FGymnasium\u002FPettingZoo\u002FJAX\u002FW&B issues: `references\u002Ftroubleshooting.md`.\n- Training shape\u002Fconfig errors: `sub-skills\u002Ftraining-workflows\u002Freferences\u002Ftroubleshooting.md`.\n- Mutation\u002FHPO mistakes: `sub-skills\u002Fhpo-and-mutation\u002Freferences\u002Ftroubleshooting.md`.\n- Network architecture\u002Fconfig mistakes: `sub-skills\u002Fevolvable-modules\u002Freferences\u002Ftroubleshooting.md`.\n- Multi-agent env\u002Fwrapper mistakes: `sub-skills\u002Fmulti-agent-and-wrappers\u002Freferences\u002Ftroubleshooting.md`.\n- Offline\u002Fbandit data schema mistakes: `sub-skills\u002Foffline-bandits-data\u002Freferences\u002Ftroubleshooting.md`.\n- LLM optional dependency and backend mistakes: `sub-skills\u002Fllm-fine-tuning\u002Freferences\u002Ftroubleshooting.md`.\n","# AgileRL\n\nUse this repo skill when a task involves AgileRL, `agilerl`, evolutionary hyperparameter optimization for RL, Gymnasium\u002FPettingZoo training with AgileRL algorithms, AgileRL evolvable modules\u002Fnetworks, offline RL datasets, contextual bandits, or AgileRL LLM post-training.\n\n## Quick Start\n\n- Install: `pip install agilerl`.\n- Optional LLM stack: `pip install \"agilerl[llm]\"` only when the task uses GRPO\u002FCISPO\u002FGSPO, DPO\u002FSFT, vLLM, PEFT, DeepSpeed, or transformer datasets.\n- Import check: `python -c \"import agilerl, importlib.metadata as md; print(md.version('agilerl'))\"`.\n- Read `references\u002Fpackage-overview.md` for the algorithm family map, `references\u002Ftroubleshooting.md` for cross-cutting dependency\u002Fbackend issues, and `references\u002Frepo-provenance.md` when checking whether this skill is stale.\n- Run `scripts\u002Fcheck_agilerl_install.py --help` for a safe local capability probe; it does not train, download models, or require the source checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Train PPO, DQN, RainbowDQN, DDPG, or TD3 on Gymnasium; wire `create_population`, `train_on_policy`, `train_off_policy`, replay\u002Frollout buffers, or distributed classical training | `sub-skills\u002Ftraining-workflows\u002FSKILL.md` |\n| Configure tournament selection, mutations, mutable RL hyperparameters, architecture mutation probabilities, or population evolution | `sub-skills\u002Fhpo-and-mutation\u002FSKILL.md` |\n| Build custom `EvolvableModule`\u002F`EvolvableNetwork` objects, `net_config`, MLP\u002FCNN\u002FLSTM\u002FMultiInput\u002FSimBa configs, actors, critics, or `DummyEvolvable` wrappers | `sub-skills\u002Fevolvable-modules\u002FSKILL.md` |\n| Use PettingZoo multi-agent training, `MADDPG`, `MATD3`, `IPPO`, `AsyncPettingZooVecEnv`, agent id grouping, or AgileRL wrappers | `sub-skills\u002Fmulti-agent-and-wrappers\u002FSKILL.md` |\n| Use offline datasets, HDF5\u002FMinari conversion, replay filling, `CQL`\u002F`ILQL`, contextual bandits, `NeuralUCB`, `NeuralTS`, or `BanditEnv` | `sub-skills\u002Foffline-bandits-data\u002FSKILL.md` |\n| Plan LLM fine-tuning\u002Fpost-training with `GRPO`, `CISPO`, `GSPO`, LLM PPO, REINFORCE, `SFT`, `DPO`, vLLM, DeepSpeed, PEFT, or AgileRL LLM envs | `sub-skills\u002Fllm-fine-tuning\u002FSKILL.md` |\n| Compare benchmark scripts or adapt performance runs safely | `references\u002Fbenchmarking.md` |\n\n## Common AgileRL Building Blocks\n\n- Algorithms: `PPO`, `DQN`, `RainbowDQN`, `DDPG`, `TD3`, `CQN`, `ILQL`, `NeuralUCB`, `NeuralTS`, `MADDPG`, `MATD3`, `IPPO`, `GRPO`, `CISPO`, `GSPO`, LLM PPO, REINFORCE, `SFT`, and `DPO`.\n- Population setup usually starts with `agilerl.utils.utils.create_population(...)` and a Gymnasium or PettingZoo observation\u002Faction space.\n- Evolution usually combines `TournamentSelection(...)` and `Mutations(...)`; use `HyperparameterConfig` and `RLParameter` for mutable algorithm attributes.\n- Network configuration usually uses `net_config` with `encoder_config`, `head_config`, and optional recurrent\u002FCNN\u002FMultiInput fields.\n- Training helpers return trained populations and fitness metrics; full training can be long, so prefer import\u002Fconfig\u002Fsmoke checks before launching runs.\n\n## Safe Validation Pattern\n\n1. Check installation and optional dependency availability with `scripts\u002Fcheck_agilerl_install.py`.\n2. Validate spaces, algorithm names, `INIT_HP`, `net_config`, and HPO configs with the nearest sub-skill helper script.\n3. Run tiny constructor\u002Fimport checks before full training.\n4. Treat demos, tutorials, benchmark launchers, and original repo tests as evidence only; do not depend on the AgileRL source checkout from this generated skill.\n5. For long training, LLM, GPU, vLLM, DeepSpeed, Minari remote, UCI, or benchmark tasks, document required hardware\u002Fdata\u002Fnetwork first and ask before expensive execution.\n\n## Troubleshooting First Reads\n\n- Install\u002Fimport, Python version, missing optional extras, Torch\u002FGymnasium\u002FPettingZoo\u002FJAX\u002FW&B issues: `references\u002Ftroubleshooting.md`.\n- Training shape\u002Fconfig errors: `sub-skills\u002Ftraining-workflows\u002Freferences\u002Ftroubleshooting.md`.\n- Mutation\u002FHPO mistakes: `sub-skills\u002Fhpo-and-mutation\u002Freferences\u002Ftroubleshooting.md`.\n- Network architecture\u002Fconfig mistakes: `sub-skills\u002Fevolvable-modules\u002Freferences\u002Ftroubleshooting.md`.\n- Multi-agent env\u002Fwrapper mistakes: `sub-skills\u002Fmulti-agent-and-wrappers\u002Freferences\u002Ftroubleshooting.md`.\n- Offline\u002Fbandit data schema mistakes: `sub-skills\u002Foffline-bandits-data\u002Freferences\u002Ftroubleshooting.md`.\n- LLM optional dependency and backend mistakes: `sub-skills\u002Fllm-fine-tuning\u002Freferences\u002Ftroubleshooting.md`.\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\u002Fagilerl",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 agilerl",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill agilerl",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill agilerl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbenchmarking.md","REFERENCE","参考文档",1858,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Freferences\u002Fbenchmarking.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fpackage-overview.md",3020,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Freferences\u002Fpackage-overview.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",1035,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",513,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",2894,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_agilerl_install.py","SCRIPT","脚本",2898,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fscripts\u002Fcheck_agilerl_install.py",[76,83,90,97,104,111],{"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},"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":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},"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":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},"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":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},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]