[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790DBJCP4ZRKQZ2CX1BEH2R":3,"skill-same:01M790DBJCP4ZRKQZ2CX1BEH2R":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},"01M790DBJCP4ZRKQZ2CX1BEH2R","perception-terrain-randomization",null,"Configure mjlab sensors, terrain generation, flat patches, and domain randomization with CPU\u002FCUDA verification boundaries.","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\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: perception-terrain-randomization\ndescription: \"Configure mjlab sensors, terrain generation, flat patches, and\n  domain randomization with CPU\u002FCUDA verification boundaries.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Perception, Terrain, and Randomization\n\nUse this sub-skill when an mjlab task needs perception sensors, terrain,\nterrain-aware resets\u002Fcurriculum, or runtime domain randomization.\n\n## Route here for\n\n- Scene-level `BuiltinSensorCfg`, `ContactSensorCfg`, `RayCastSensorCfg`,\n  `TerrainHeightSensorCfg`, and `CameraSensorCfg` selection.\n- Sensor data semantics: contact reductions\u002Fhistory, raycast hit distances,\n  terrain height scans, RGB\u002Fdepth\u002Fsegmentation outputs, and debug visualization.\n- `TerrainEntityCfg`, `TerrainGeneratorCfg`, terrain presets, curriculum grid\n  behavior, spawn proportions, and flat patch sampling.\n- Domain-randomization event functions in `mjlab.envs.mdp.dr`, including model\n  field expansion, recomputation levels, camera\u002Frender implications, and\n  visualization limits.\n- Deciding whether a check is CPU-config-only or a CUDA\u002Ffull sensor validation.\n\n## Route elsewhere\n\n- Base entity, scene, MuJoCo spec editing, asset variants, and scene export:\n  [scene-simulation-assets](..\u002Fscene-simulation-assets\u002FSKILL.md).\n- Observation\u002Freward\u002Faction\u002Ftermination term dictionaries and observation-group\n  wiring: [environment-configuration](..\u002Fenvironment-configuration\u002FSKILL.md)\n  and [mdp-components](..\u002Fmdp-components\u002FSKILL.md).\n- Training, playback, task registry, viewer CLI, checkpoints, W&B, and export\n  commands: [training-evaluation-cli](..\u002Ftraining-evaluation-cli\u002FSKILL.md).\n\n## Operating workflow\n\n1. Identify which layer owns the request: sensor config, terrain config,\n   terrain-aware reset\u002Fcurriculum, or `dr` event term.\n2. Confirm exact installed signatures and terrain preset names with the bundled\n   [inspection script](scripts\u002Finspect_sensor_terrain.py) when the mjlab version\n   may matter. Use `--json` for machine-readable output.\n3. Read the relevant reference:\n   - [Sensors](references\u002Fsensors.md) for built-in\u002Fcontact\u002Fraycast\u002Fcamera data.\n   - [Terrain](references\u002Fterrain.md) for generator modes, presets, flat patches,\n     curriculum, and debug groups.\n   - [Domain randomization](references\u002Fdomain-randomization.md) for event modes,\n     field selection, operations\u002Fdistributions, and recompute behavior.\n   - [Troubleshooting](references\u002Ftroubleshooting.md) for common sensor, terrain,\n     rendering, and DR failures.\n4. Choose verification level explicitly:\n   - CPU\u002Fconfig checks can inspect imports, dataclass signatures, CLI\u002Fhelp text,\n     and pure terrain config construction.\n   - CUDA\u002Ffull checks are needed for raycast\u002Fcamera sensing, MuJoCo Warp render\n     context behavior, sensor-context creation, and training-scale simulation.\n\n## Fast decisions\n\n- Use `ContactSensorCfg` for structured contact data and gait air-time signals.\n- Use `RayCastSensorCfg` with a `GridPatternCfg` for terrain scans and with a\n  `PinholeCameraPatternCfg` for depth-like rays.\n- Use `TerrainHeightSensorCfg` when the policy needs per-frame vertical\n  clearance rather than raw raycast hit positions.\n- Use `CameraSensorCfg` for RGB\u002Fdepth\u002Fsegmentation images; keep all camera\n  render settings identical inside one scene.\n- Use terrain named configs for standard locomotion terrain, then customize with\n  `dataclasses.replace()` or by replacing `sub_terrains`.\n- Prefer `startup` or `reset` events for DR functions that trigger model\n  recomputation; reserve frequent interval\u002Fstep events for cheap state or\n  friction-style changes.\n","# Perception, Terrain, and Randomization\n\nUse this sub-skill when an mjlab task needs perception sensors, terrain,\nterrain-aware resets\u002Fcurriculum, or runtime domain randomization.\n\n## Route here for\n\n- Scene-level `BuiltinSensorCfg`, `ContactSensorCfg`, `RayCastSensorCfg`,\n  `TerrainHeightSensorCfg`, and `CameraSensorCfg` selection.\n- Sensor data semantics: contact reductions\u002Fhistory, raycast hit distances,\n  terrain height scans, RGB\u002Fdepth\u002Fsegmentation outputs, and debug visualization.\n- `TerrainEntityCfg`, `TerrainGeneratorCfg`, terrain presets, curriculum grid\n  behavior, spawn proportions, and flat patch sampling.\n- Domain-randomization event functions in `mjlab.envs.mdp.dr`, including model\n  field expansion, recomputation levels, camera\u002Frender implications, and\n  visualization limits.\n- Deciding whether a check is CPU-config-only or a CUDA\u002Ffull sensor validation.\n\n## Route elsewhere\n\n- Base entity, scene, MuJoCo spec editing, asset variants, and scene export:\n  [scene-simulation-assets](..\u002Fscene-simulation-assets\u002FSKILL.md).\n- Observation\u002Freward\u002Faction\u002Ftermination term dictionaries and observation-group\n  wiring: [environment-configuration](..\u002Fenvironment-configuration\u002FSKILL.md)\n  and [mdp-components](..\u002Fmdp-components\u002FSKILL.md).\n- Training, playback, task registry, viewer CLI, checkpoints, W&B, and export\n  commands: [training-evaluation-cli](..\u002Ftraining-evaluation-cli\u002FSKILL.md).\n\n## Operating workflow\n\n1. Identify which layer owns the request: sensor config, terrain config,\n   terrain-aware reset\u002Fcurriculum, or `dr` event term.\n2. Confirm exact installed signatures and terrain preset names with the bundled\n   [inspection script](scripts\u002Finspect_sensor_terrain.py) when the mjlab version\n   may matter. Use `--json` for machine-readable output.\n3. Read the relevant reference:\n   - [Sensors](references\u002Fsensors.md) for built-in\u002Fcontact\u002Fraycast\u002Fcamera data.\n   - [Terrain](references\u002Fterrain.md) for generator modes, presets, flat patches,\n     curriculum, and debug groups.\n   - [Domain randomization](references\u002Fdomain-randomization.md) for event modes,\n     field selection, operations\u002Fdistributions, and recompute behavior.\n   - [Troubleshooting](references\u002Ftroubleshooting.md) for common sensor, terrain,\n     rendering, and DR failures.\n4. Choose verification level explicitly:\n   - CPU\u002Fconfig checks can inspect imports, dataclass signatures, CLI\u002Fhelp text,\n     and pure terrain config construction.\n   - CUDA\u002Ffull checks are needed for raycast\u002Fcamera sensing, MuJoCo Warp render\n     context behavior, sensor-context creation, and training-scale simulation.\n\n## Fast decisions\n\n- Use `ContactSensorCfg` for structured contact data and gait air-time signals.\n- Use `RayCastSensorCfg` with a `GridPatternCfg` for terrain scans and with a\n  `PinholeCameraPatternCfg` for depth-like rays.\n- Use `TerrainHeightSensorCfg` when the policy needs per-frame vertical\n  clearance rather than raw raycast hit positions.\n- Use `CameraSensorCfg` for RGB\u002Fdepth\u002Fsegmentation images; keep all camera\n  render settings identical inside one scene.\n- Use terrain named configs for standard locomotion terrain, then customize with\n  `dataclasses.replace()` or by replacing `sub_terrains`.\n- Prefer `startup` or `reset` events for DR functions that trigger model\n  recomputation; reserve frequent interval\u002Fstep events for cheap state or\n  friction-style changes.\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\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization",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 perception-terrain-randomization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill perception-terrain-randomization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill perception-terrain-randomization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdomain-randomization.md","REFERENCE","参考文档",10628,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002Freferences\u002Fdomain-randomization.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fsensors.md",11045,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002Freferences\u002Fsensors.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fterrain.md",9962,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002Freferences\u002Fterrain.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",2526,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_sensor_terrain.py","SCRIPT","脚本",2654,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmjlab\u002Fsub-skills\u002Fperception-terrain-randomization\u002Fscripts\u002Finspect_sensor_terrain.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",[],[]]