[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792ZAJYEB01GD59KGMA57C9":3,"skill-same:01M792ZAJYEB01GD59KGMA57C9":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},"01M792ZAJYEB01GD59KGMA57C9","evaluation",null,"Evaluate pretrained PPO checkpoints, resolve checkpoint\u002Fenvironment configuration, and diagnose load or render issues.","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\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: evaluation\ndescription: \"Evaluate pretrained PPO checkpoints, resolve\n  checkpoint\u002Fenvironment configuration, and diagnose load or render issues.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Evaluation\n\nUse this sub-skill when the user asks to test a pretrained network, evaluate a checkpoint, render a trained policy, average episode rewards, or understand why a PPO checkpoint load fails.\n\nDo not use this sub-skill for training-loop changes, PPO update debugging, reward-log plotting, or GIF composition. Route log plots and frame\u002FGIF workflows to the sibling [visualization sub-skill](..\u002Fvisualization\u002FSKILL.md). Route low-level `PPO.load`, `PPO.save`, `select_action`, and architecture questions to the root shared [API reference](..\u002F..\u002Freferences\u002Fapi-reference.md).\n\n## What this sub-skill owns\n\n- Resolving the pretrained checkpoint path convention: `PPO_preTrained\u002F\u003Cenv_name>\u002FPPO_\u003Cenv_name>_\u003Crandom_seed>_\u003Crun_num>.pth`.\n- Matching checkpoint names to environment names, action-space class, and PPO constructor dimensions.\n- Preserving continuous-policy `action_std` alignment; the repo's checkpoint files do not store `action_std`.\n- Running or adapting the `test.py` evaluation pattern: load policy, run episodes, print per-episode rewards, and report the average reward.\n- Deciding whether rendering is safe in local, notebook, remote, or headless sessions.\n- Diagnosing missing Gym\u002FRoboschool dependencies, checkpoint path mistakes, Gym\u002FGymnasium API drift, and state-dict shape mismatches.\n\n## Quick workflow\n\n1. **Resolve the intended checkpoint before running an environment.** Use the bundled helper from this sub-skill directory:\n\n   ```bash\n   python scripts\u002Fevaluation_config_helper.py --list-presets\n   python scripts\u002Fevaluation_config_helper.py \\\n     --env-name RoboschoolWalker2d-v1 \\\n     --checkpoint-root PPO_preTrained \\\n     --check-file\n   ```\n\n   The helper is path\u002Fconfiguration-only by default. It does not import `gym`, `roboschool`, or the PPO module and does not run rollouts.\n\n2. **Match the live environment to the checkpoint.** The environment used for `gym.make(env_name)` must expose the same observation dimension, action dimension, and action-space type that were used to save the state dict. A checkpoint named for `CartPole-v1` is not load-compatible with `LunarLander-v2`, and a discrete checkpoint is not compatible with a continuous `Box` policy.\n\n3. **Construct the PPO agent with evaluation-compatible arguments.** The original testing script uses `lr_actor=0.0003`, `lr_critic=0.001`, `gamma=0.99`, `eps_clip=0.2`, and `K_epochs=80`. These update hyperparameters are mostly inert during pure `select_action` evaluation, but the constructor still requires them. Continuous policies also require an `action_std` float at construction time.\n\n4. **Load the checkpoint once the dimensions are known.** The shared PPO implementation saves `policy_old.state_dict()` and `load(checkpoint_path)` loads the same state dict into both `policy_old` and `policy` using `torch.load(..., map_location=...)`. Use the root [API reference](..\u002F..\u002Freferences\u002Fapi-reference.md) for exact load\u002Fsave behavior.\n\n5. **Run episodes and average rewards.** The native evaluation loop resets the env, calls `ppo_agent.select_action(state)`, steps the env until `done` or `max_ep_len`, clears the rollout buffer after each episode, prints episode reward, and reports `average test reward` over `total_test_episodes`.\n\n6. **Render only when the display path is ready.** Numeric evaluation does not require rendering. For on-screen display, use a compatible Gym render path and a real display. For `rgb_array` frame capture and GIF assembly, switch to [visualization](..\u002Fvisualization\u002FSKILL.md).\n\n## Core references\n\n- [Evaluation workflow](references\u002Fevaluation-workflow.md) - evaluation loop adaptation, old\u002Fnew Gym API handling, and render choices.\n- [Checkpoints and environments](references\u002Fcheckpoints-and-envs.md) - file naming, built-in pretrained environment presets, and action-space matching rules.\n- [Troubleshooting](references\u002Ftroubleshooting.md) - missing dependencies, checkpoint mismatch, headless rendering, and Gym\u002FGymnasium compatibility failures.\n- [Root PPO API reference](..\u002F..\u002Freferences\u002Fapi-reference.md) - constructor, `select_action`, `save`, and `load` details shared across sub-skills.\n\n## Validation commands\n\nSafe checks for this sub-skill should avoid long rollouts unless the user explicitly has the environment packages, display, and checkpoint ready:\n\n```bash\npython scripts\u002Fevaluation_config_helper.py --help\npython scripts\u002Fevaluation_config_helper.py --env-name CartPole-v1 --checkpoint-root PPO_preTrained --check-file\npython -m py_compile scripts\u002Fevaluation_config_helper.py\n```\n\nA real episode rollout is optional and dependency-bound because the native `test.py` imports legacy `gym` and `roboschool`; do not treat a missing optional environment package as a failure of the helper or documentation.\n","# Evaluation\n\nUse this sub-skill when the user asks to test a pretrained network, evaluate a checkpoint, render a trained policy, average episode rewards, or understand why a PPO checkpoint load fails.\n\nDo not use this sub-skill for training-loop changes, PPO update debugging, reward-log plotting, or GIF composition. Route log plots and frame\u002FGIF workflows to the sibling [visualization sub-skill](..\u002Fvisualization\u002FSKILL.md). Route low-level `PPO.load`, `PPO.save`, `select_action`, and architecture questions to the root shared [API reference](..\u002F..\u002Freferences\u002Fapi-reference.md).\n\n## What this sub-skill owns\n\n- Resolving the pretrained checkpoint path convention: `PPO_preTrained\u002F\u003Cenv_name>\u002FPPO_\u003Cenv_name>_\u003Crandom_seed>_\u003Crun_num>.pth`.\n- Matching checkpoint names to environment names, action-space class, and PPO constructor dimensions.\n- Preserving continuous-policy `action_std` alignment; the repo's checkpoint files do not store `action_std`.\n- Running or adapting the `test.py` evaluation pattern: load policy, run episodes, print per-episode rewards, and report the average reward.\n- Deciding whether rendering is safe in local, notebook, remote, or headless sessions.\n- Diagnosing missing Gym\u002FRoboschool dependencies, checkpoint path mistakes, Gym\u002FGymnasium API drift, and state-dict shape mismatches.\n\n## Quick workflow\n\n1. **Resolve the intended checkpoint before running an environment.** Use the bundled helper from this sub-skill directory:\n\n   ```bash\n   python scripts\u002Fevaluation_config_helper.py --list-presets\n   python scripts\u002Fevaluation_config_helper.py \\\n     --env-name RoboschoolWalker2d-v1 \\\n     --checkpoint-root PPO_preTrained \\\n     --check-file\n   ```\n\n   The helper is path\u002Fconfiguration-only by default. It does not import `gym`, `roboschool`, or the PPO module and does not run rollouts.\n\n2. **Match the live environment to the checkpoint.** The environment used for `gym.make(env_name)` must expose the same observation dimension, action dimension, and action-space type that were used to save the state dict. A checkpoint named for `CartPole-v1` is not load-compatible with `LunarLander-v2`, and a discrete checkpoint is not compatible with a continuous `Box` policy.\n\n3. **Construct the PPO agent with evaluation-compatible arguments.** The original testing script uses `lr_actor=0.0003`, `lr_critic=0.001`, `gamma=0.99`, `eps_clip=0.2`, and `K_epochs=80`. These update hyperparameters are mostly inert during pure `select_action` evaluation, but the constructor still requires them. Continuous policies also require an `action_std` float at construction time.\n\n4. **Load the checkpoint once the dimensions are known.** The shared PPO implementation saves `policy_old.state_dict()` and `load(checkpoint_path)` loads the same state dict into both `policy_old` and `policy` using `torch.load(..., map_location=...)`. Use the root [API reference](..\u002F..\u002Freferences\u002Fapi-reference.md) for exact load\u002Fsave behavior.\n\n5. **Run episodes and average rewards.** The native evaluation loop resets the env, calls `ppo_agent.select_action(state)`, steps the env until `done` or `max_ep_len`, clears the rollout buffer after each episode, prints episode reward, and reports `average test reward` over `total_test_episodes`.\n\n6. **Render only when the display path is ready.** Numeric evaluation does not require rendering. For on-screen display, use a compatible Gym render path and a real display. For `rgb_array` frame capture and GIF assembly, switch to [visualization](..\u002Fvisualization\u002FSKILL.md).\n\n## Core references\n\n- [Evaluation workflow](references\u002Fevaluation-workflow.md) - evaluation loop adaptation, old\u002Fnew Gym API handling, and render choices.\n- [Checkpoints and environments](references\u002Fcheckpoints-and-envs.md) - file naming, built-in pretrained environment presets, and action-space matching rules.\n- [Troubleshooting](references\u002Ftroubleshooting.md) - missing dependencies, checkpoint mismatch, headless rendering, and Gym\u002FGymnasium compatibility failures.\n- [Root PPO API reference](..\u002F..\u002Freferences\u002Fapi-reference.md) - constructor, `select_action`, `save`, and `load` details shared across sub-skills.\n\n## Validation commands\n\nSafe checks for this sub-skill should avoid long rollouts unless the user explicitly has the environment packages, display, and checkpoint ready:\n\n```bash\npython scripts\u002Fevaluation_config_helper.py --help\npython scripts\u002Fevaluation_config_helper.py --env-name CartPole-v1 --checkpoint-root PPO_preTrained --check-file\npython -m py_compile scripts\u002Fevaluation_config_helper.py\n```\n\nA real episode rollout is optional and dependency-bound because the native `test.py` imports legacy `gym` and `roboschool`; do not treat a missing optional environment package as a failure of the helper or documentation.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation",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 evaluation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcheckpoints-and-envs.md","REFERENCE","参考文档",4844,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fcheckpoints-and-envs.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fevaluation-workflow.md",5969,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fevaluation-workflow.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5825,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fevaluation_config_helper.py","SCRIPT","脚本",12748,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fppo-pytorch\u002Fsub-skills\u002Fevaluation\u002Fscripts\u002Fevaluation_config_helper.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",[],[]]