[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792GNGNMCYBPRBNTMFGGHBJ":3,"skill-same:01M792GNGNMCYBPRBNTMFGGHBJ":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},"01M792GNGNMCYBPRBNTMFGGHBJ","environment-utils",null,"Use PARL environment wrappers, replay buffers, schedulers, CSV logging, and summary helpers safely across Gym, continuous-control, Atari, MuJoCo, multi-agent, and vector-env workflows.","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\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: environment-utils\ndescription: \"Use PARL environment wrappers, replay buffers, schedulers, CSV\n  logging, and summary helpers safely across Gym, continuous-control, Atari,\n  MuJoCo, multi-agent, and vector-env workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PARL environment utilities\n\nUse this sub-skill when a task involves PARL's environment wrappers or small utilities around an RL loop: Gym API compatibility, continuous action remapping, Atari\u002FMuJoCo\u002Fmulti-agent\u002Fvector environment wrappers, `ReplayMemory`, schedulers, `CSVLogger`, `logger`, `summary`, `tensorboard`, or `visualdl` helpers.\n\nDo not use this sub-skill to choose a full algorithm, implement a `parl.Model`\u002F`parl.Agent`, or manage xparl workers. Route adjacent tasks to sibling operating skills:\n\n- `..\u002Fcore-framework\u002FSKILL.md` for backend selection, `Model`\u002F`Algorithm`\u002F`Agent`, save\u002Frestore, inference export, and weight synchronization.\n- `..\u002Falgorithm-recipes\u002FSKILL.md` for DQN\u002FDDPG\u002FTD3\u002FSAC\u002FPPO\u002FQMIX\u002FMADDPG\u002FA2C\u002FIMPALA\u002FCQL\u002FOAC recipes and training-loop structure.\n- `..\u002Fxparl-distributed\u002FSKILL.md` for `@parl.remote_class`, `parl.connect`, `xparl start`, remote environments, ports, and cluster security.\n\n## Operating workflow\n\n1. **Normalize the environment API first.** For ordinary Gym environments, wrap with `CompatWrapper` before calling code that expects the old four-return `step` API. Then add workflow-specific wrappers such as `ActionMappingWrapper`, `wrap_deepmind`, `wrap_rms`, `MAenv`, or `VectorEnv`.\n2. **Choose wrappers by action\u002Fobservation surface.** Use `ActionMappingWrapper` only when the environment action space is a continuous `Box`; use Atari wrappers only for Atari-like image\u002Faction-meaning environments; use MuJoCo RMS wrappers for continuous-control normalization; use multi-agent wrappers only when the PettingZoo or legacy multiagent dependency stack is intentionally installed.\n3. **Check data utility shapes before training.** Configure `ReplayMemory(max_size, obs_dim, act_dim)` from the actual observation and action dimensions. For discrete actions pass `act_dim=0`; for continuous actions pass a positive integer action dimension.\n4. **Keep logging output explicit.** Set a deliberate `logger.set_dir(...)` before writing summaries, or create `CSVLogger` with an explicit file path in a scratch\u002Foutput directory. Avoid accidental deletion from logger helpers when a directory already exists.\n5. **Smoke-test utilities safely.** Run the bundled checker before adapting examples:\n\n   ```bash\n   python scripts\u002Fcheck_env_utils.py --json\n   ```\n\n   Add `--optional-wrappers` to classify optional Atari, MuJoCo, and multi-agent imports without creating real environments.\n6. **Escalate by symptom.** For wrapper\u002Fdata-flow behavior, read `references\u002Fwrappers-and-data.md`; for logging and schedulers, read `references\u002Flogging-and-schedulers.md`; for failures, read `references\u002Ftroubleshooting.md`.\n\n## Verification status\n\nThe utility signatures for `CompatWrapper`, `ActionMappingWrapper`, `VectorEnv`, `ReplayMemory`, `PiecewiseScheduler`, `LinearDecayScheduler`, and `CSVLogger` were checked against an installed PARL 2.2.1 package. Small scheduler, replay-memory, CSV, vector-env, and action-mapping behaviors are covered by the bundled checker. Atari, MuJoCo, PettingZoo multi-agent, TensorBoard, and VisualDL flows are optional dependency surfaces and should be rechecked in the user's target environment before use.\n\n## Reference map\n\n- `references\u002Fwrappers-and-data.md` — Gym compatibility, action mapping, vector envs, Atari\u002FMuJoCo\u002Fmulti-agent wrappers, replay-memory contracts, and small NumPy RL helpers.\n- `references\u002Flogging-and-schedulers.md` — schedulers, CSV output, PARL logger directories, summary\u002FTensorBoard\u002FVisualDL behavior, and file-write safety.\n- `references\u002Ftroubleshooting.md` — common fixes for Gym API mismatches, optional dependencies, action\u002Freplay shapes, logger deletion, CSV key mismatches, and summary backends.\n- `scripts\u002Fcheck_env_utils.py` — deterministic local checker for safe imports, signatures, and tiny pure-Python utility exercises.\n","# PARL environment utilities\n\nUse this sub-skill when a task involves PARL's environment wrappers or small utilities around an RL loop: Gym API compatibility, continuous action remapping, Atari\u002FMuJoCo\u002Fmulti-agent\u002Fvector environment wrappers, `ReplayMemory`, schedulers, `CSVLogger`, `logger`, `summary`, `tensorboard`, or `visualdl` helpers.\n\nDo not use this sub-skill to choose a full algorithm, implement a `parl.Model`\u002F`parl.Agent`, or manage xparl workers. Route adjacent tasks to sibling operating skills:\n\n- `..\u002Fcore-framework\u002FSKILL.md` for backend selection, `Model`\u002F`Algorithm`\u002F`Agent`, save\u002Frestore, inference export, and weight synchronization.\n- `..\u002Falgorithm-recipes\u002FSKILL.md` for DQN\u002FDDPG\u002FTD3\u002FSAC\u002FPPO\u002FQMIX\u002FMADDPG\u002FA2C\u002FIMPALA\u002FCQL\u002FOAC recipes and training-loop structure.\n- `..\u002Fxparl-distributed\u002FSKILL.md` for `@parl.remote_class`, `parl.connect`, `xparl start`, remote environments, ports, and cluster security.\n\n## Operating workflow\n\n1. **Normalize the environment API first.** For ordinary Gym environments, wrap with `CompatWrapper` before calling code that expects the old four-return `step` API. Then add workflow-specific wrappers such as `ActionMappingWrapper`, `wrap_deepmind`, `wrap_rms`, `MAenv`, or `VectorEnv`.\n2. **Choose wrappers by action\u002Fobservation surface.** Use `ActionMappingWrapper` only when the environment action space is a continuous `Box`; use Atari wrappers only for Atari-like image\u002Faction-meaning environments; use MuJoCo RMS wrappers for continuous-control normalization; use multi-agent wrappers only when the PettingZoo or legacy multiagent dependency stack is intentionally installed.\n3. **Check data utility shapes before training.** Configure `ReplayMemory(max_size, obs_dim, act_dim)` from the actual observation and action dimensions. For discrete actions pass `act_dim=0`; for continuous actions pass a positive integer action dimension.\n4. **Keep logging output explicit.** Set a deliberate `logger.set_dir(...)` before writing summaries, or create `CSVLogger` with an explicit file path in a scratch\u002Foutput directory. Avoid accidental deletion from logger helpers when a directory already exists.\n5. **Smoke-test utilities safely.** Run the bundled checker before adapting examples:\n\n   ```bash\n   python scripts\u002Fcheck_env_utils.py --json\n   ```\n\n   Add `--optional-wrappers` to classify optional Atari, MuJoCo, and multi-agent imports without creating real environments.\n6. **Escalate by symptom.** For wrapper\u002Fdata-flow behavior, read `references\u002Fwrappers-and-data.md`; for logging and schedulers, read `references\u002Flogging-and-schedulers.md`; for failures, read `references\u002Ftroubleshooting.md`.\n\n## Verification status\n\nThe utility signatures for `CompatWrapper`, `ActionMappingWrapper`, `VectorEnv`, `ReplayMemory`, `PiecewiseScheduler`, `LinearDecayScheduler`, and `CSVLogger` were checked against an installed PARL 2.2.1 package. Small scheduler, replay-memory, CSV, vector-env, and action-mapping behaviors are covered by the bundled checker. Atari, MuJoCo, PettingZoo multi-agent, TensorBoard, and VisualDL flows are optional dependency surfaces and should be rechecked in the user's target environment before use.\n\n## Reference map\n\n- `references\u002Fwrappers-and-data.md` — Gym compatibility, action mapping, vector envs, Atari\u002FMuJoCo\u002Fmulti-agent wrappers, replay-memory contracts, and small NumPy RL helpers.\n- `references\u002Flogging-and-schedulers.md` — schedulers, CSV output, PARL logger directories, summary\u002FTensorBoard\u002FVisualDL behavior, and file-write safety.\n- `references\u002Ftroubleshooting.md` — common fixes for Gym API mismatches, optional dependencies, action\u002Freplay shapes, logger deletion, CSV key mismatches, and summary backends.\n- `scripts\u002Fcheck_env_utils.py` — deterministic local checker for safe imports, signatures, and tiny pure-Python utility exercises.\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\u002Fparl\u002Fsub-skills\u002Fenvironment-utils",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 environment-utils",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill environment-utils",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill environment-utils","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Flogging-and-schedulers.md","REFERENCE","参考文档",6854,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002Freferences\u002Flogging-and-schedulers.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",8343,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fwrappers-and-data.md",10570,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002Freferences\u002Fwrappers-and-data.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_env_utils.py","SCRIPT","脚本",5026,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fparl\u002Fsub-skills\u002Fenvironment-utils\u002Fscripts\u002Fcheck_env_utils.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",[],[]]