[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790AD29NP3C2GBSW83XPF39":3,"skill-same:01M790AD29NP3C2GBSW83XPF39":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M790AD29NP3C2GBSW83XPF39","continuous-control",null,"Guides minimalRL DDPG, continuous PPO, and SAC workflows for Pendulum-style continuous-action control.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: continuous-control\ndescription: \"Guides minimalRL DDPG, continuous PPO, and SAC workflows for\n  Pendulum-style continuous-action control.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Continuous-Control Workflows\n\nUse this sub-skill when a task asks about minimalRL's continuous-action Pendulum algorithms: DDPG, PPO-Continuous, or SAC.\n\n## Route by task\n\n- **Deterministic actor-critic \u002F DDPG**: read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for `MuNet`, `QNet`, replay, OU noise, and `soft_update`; read [references\u002Fworkflows.md](references\u002Fworkflows.md) for action scaling and target updates.\n- **Continuous PPO**: use [references\u002Fworkflows.md](references\u002Fworkflows.md) for Gaussian rollout\u002Fminibatch handling and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for `mu`, `std`, and log-prob shape issues.\n- **Soft Actor-Critic**: use [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for `PolicyNet`, twin `QNet`, `calc_target`, and alpha update contracts.\n- **Pre-training shape checks**: run [scripts\u002Fsmoke_continuous_control.py](scripts\u002Fsmoke_continuous_control.py).\n\n## Do not use this sub-skill for\n\n- Discrete CartPole REINFORCE, actor-critic, PPO, PPO-LSTM, or V-trace policy\u002Fvalue routes; use [..\u002Fon-policy-discrete\u002FSKILL.md](..\u002Fon-policy-discrete\u002FSKILL.md).\n- DQN, ACER, or V-trace replay\u002Fcorrection debugging; use [..\u002Foff-policy-value\u002FSKILL.md](..\u002Foff-policy-value\u002FSKILL.md).\n- A2C\u002FA3C multiprocessing; use [..\u002Fparallel-actor-critic\u002FSKILL.md](..\u002Fparallel-actor-critic\u002FSKILL.md).\n\n## Quick operating workflow\n\n1. Confirm the environment has continuous actions. The minimalRL continuous scripts assume Pendulum-like observations of length 3 and a one-dimensional action in `[-2, 2]`.\n2. Choose the algorithm family:\n   - DDPG for deterministic actor plus critic, replay, OU exploration, and soft target updates.\n   - Continuous PPO for on-policy Gaussian policy with clipped objective.\n   - SAC for stochastic tanh-Gaussian policy, twin critics, entropy temperature update, and replay.\n3. Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) before changing tensor shapes or action scaling.\n4. Run the smoke helper:\n\n   ```bash\n   python sub-skills\u002Fcontinuous-control\u002Fscripts\u002Fsmoke_continuous_control.py --algorithm all\n   ```\n\n5. For action range, `log_prob`, state\u002Faction concatenation, replay warm-up, or target update failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Bundled runtime files\n\n- [references\u002Fapi-reference.md](references\u002Fapi-reference.md) lists source-faithful classes, functions, hyperparameters, tensor\u002Faction shapes, and data tuple contracts.\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) explains DDPG, continuous PPO, and SAC adaptation workflows.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) gives actionable fixes for continuous-control failure modes.\n- [scripts\u002Fsmoke_continuous_control.py](scripts\u002Fsmoke_continuous_control.py) validates representative continuous-control tensors without importing the original repository or running training.\n","# Continuous-Control Workflows\n\nUse this sub-skill when a task asks about minimalRL's continuous-action Pendulum algorithms: DDPG, PPO-Continuous, or SAC.\n\n## Route by task\n\n- **Deterministic actor-critic \u002F DDPG**: read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for `MuNet`, `QNet`, replay, OU noise, and `soft_update`; read [references\u002Fworkflows.md](references\u002Fworkflows.md) for action scaling and target updates.\n- **Continuous PPO**: use [references\u002Fworkflows.md](references\u002Fworkflows.md) for Gaussian rollout\u002Fminibatch handling and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for `mu`, `std`, and log-prob shape issues.\n- **Soft Actor-Critic**: use [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for `PolicyNet`, twin `QNet`, `calc_target`, and alpha update contracts.\n- **Pre-training shape checks**: run [scripts\u002Fsmoke_continuous_control.py](scripts\u002Fsmoke_continuous_control.py).\n\n## Do not use this sub-skill for\n\n- Discrete CartPole REINFORCE, actor-critic, PPO, PPO-LSTM, or V-trace policy\u002Fvalue routes; use [..\u002Fon-policy-discrete\u002FSKILL.md](..\u002Fon-policy-discrete\u002FSKILL.md).\n- DQN, ACER, or V-trace replay\u002Fcorrection debugging; use [..\u002Foff-policy-value\u002FSKILL.md](..\u002Foff-policy-value\u002FSKILL.md).\n- A2C\u002FA3C multiprocessing; use [..\u002Fparallel-actor-critic\u002FSKILL.md](..\u002Fparallel-actor-critic\u002FSKILL.md).\n\n## Quick operating workflow\n\n1. Confirm the environment has continuous actions. The minimalRL continuous scripts assume Pendulum-like observations of length 3 and a one-dimensional action in `[-2, 2]`.\n2. Choose the algorithm family:\n   - DDPG for deterministic actor plus critic, replay, OU exploration, and soft target updates.\n   - Continuous PPO for on-policy Gaussian policy with clipped objective.\n   - SAC for stochastic tanh-Gaussian policy, twin critics, entropy temperature update, and replay.\n3. Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) before changing tensor shapes or action scaling.\n4. Run the smoke helper:\n\n   ```bash\n   python sub-skills\u002Fcontinuous-control\u002Fscripts\u002Fsmoke_continuous_control.py --algorithm all\n   ```\n\n5. For action range, `log_prob`, state\u002Faction concatenation, replay warm-up, or target update failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Bundled runtime files\n\n- [references\u002Fapi-reference.md](references\u002Fapi-reference.md) lists source-faithful classes, functions, hyperparameters, tensor\u002Faction shapes, and data tuple contracts.\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) explains DDPG, continuous PPO, and SAC adaptation workflows.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) gives actionable fixes for continuous-control failure modes.\n- [scripts\u002Fsmoke_continuous_control.py](scripts\u002Fsmoke_continuous_control.py) validates representative continuous-control tensors without importing the original repository or running training.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill continuous-control",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill continuous-control",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill continuous-control","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3608,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",2723,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",3184,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsmoke_continuous_control.py","SCRIPT","脚本",5670,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fminimal-rl\u002Fsub-skills\u002Fcontinuous-control\u002Fscripts\u002Fsmoke_continuous_control.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]