[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WHQBFHMNC9WQ27VTAPAH6":3,"skill-same:01M78WHQBFHMNC9WQ27VTAPAH6":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},"01M78WHQBFHMNC9WQ27VTAPAH6","navigation-environment",null,"Operate and validate the GazeboEnv observation, action, reset, timing, and reward contract for the ROS\u002FGazebo Velodyne navigation environment without requiring a live simulator.","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\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: navigation-environment\ndescription: \"Operate and validate the GazeboEnv observation, action, reset,\n  timing, and reward contract for the ROS\u002FGazebo Velodyne navigation environment\n  without requiring a live simulator.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Navigation environment\n\nUse this skill when a downstream agent needs to reason about the mobile-robot\n`GazeboEnv` interface, prepare a compatible observation\u002Faction, diagnose a\nsensor or ROS integration failure, or check a synthetic transition. This skill\nis a distilled contract, not a simulator launcher and not a TD3 training guide.\n\n## Operating contract\n\n- The repository's training configuration uses `environment_dim=20` and four\n  robot features, so every observation is a flat numeric vector of length 24.\n- The first 20 values are Velodyne distance bins, initialized to 10 and\n  updated by the point-cloud callback. The final four values are, in order,\n  distance to goal, relative goal heading, linear action, and angular action.\n  `reset` returns the two action slots as 0; `step` places the action used for\n  that transition in them. There is no separate previous-action history in\n  the implementation, so do not invent one.\n- The environment-facing action is `[linear_x, angular_z]`: linear is in\n  `[0, 1]`, angular is in `[-1, 1]`. `step` publishes these values directly;\n  it does not rescale them. A TD3 actor output in `[-1, 1]` therefore needs its\n  first component mapped with `(a_linear + 1) \u002F 2` before calling `step`.\n- `done` becomes true on a laser collision or a goal hit. A goal hit is\n  reported separately as `target=True`; collision and target reward priority\n  is target first, then collision.\n- Use `scripts\u002Fvalidate_navigation_contract.py` for offline numeric checks.\n  It imports no ROS package, starts no process, and is the preferred check for\n  state length, action range, point-bin fixtures, and threshold behavior.\n\n## Safe reasoning workflow\n\n1. Confirm the caller has ROS Noetic\u002FUbuntu 20.04-compatible ROS message and\n   Gazebo dependencies, plus Python dependencies used by the environment\n   (`numpy` and `squaternion`). A live run additionally needs `roscore`,\n   `roslaunch`, Gazebo, and a built catkin workspace with the scenario and\n   Velodyne plugin packages. This host-independent skill does not install or\n   launch any of them.\n2. Treat a relative launch name as relative to the environment module's\n   `assets` directory, not the caller's current directory. The repository's\n   `multi_robot_scenario.launch` includes the empty TD3 world and spawns model\n   `r1`.\n3. Validate an observation as 20 finite sensor values followed by four finite\n   robot values. Reject 23- or 25-value vectors rather than silently padding or\n   truncating them.\n4. Validate action-space provenance. If an actor produced `[-1, 1]` for both\n   dimensions, transform only the linear component before using this\n   environment contract.\n5. For a synthetic sensor case, reduce points into the same 20 angular bins,\n   compute the minimum distance per bin, and then apply the strict collision\n   threshold. Keep simulator verification explicitly unavailable when ROS or\n   Gazebo is absent.\n6. Interpret `reset` and `step` as ROS-dependent calls. A valid offline vector\n   does not prove that odometry, PointCloud2, publishers, or physics services\n   are connected.\n\n## Scope boundaries\n\nThis skill covers constructor prerequisites and launch resolution, point-cloud\nreduction, state\u002Faction\u002Freward semantics, reset randomization, ROS interfaces,\nand predictable numeric\u002Fintegration failures. Do not use it to explain TD3\nnetwork architecture, replay-buffer behavior, optimizer settings, training\nloops, model checkpoints, or installation procedures beyond naming prerequisites.\nSee the bundled references for the detailed contract and troubleshooting.\n\n## Numeric and evidence notes\n\nThe source callback has no explicit finite-value or zero-horizontal-range\n guard. Use the validator's stricter finite-input policy for synthetic data;\nnever turn NaN or an `acos` domain error into a claimed sensor reading.\n\n## Evidence and verification status\n\nThe contract was distilled from the pinned repository's environment module,\nlaunch file, scenario xacro\u002FURDF, Velodyne description and Gazebo plugin, and\ntraining caller. The offline validator is checked with its help\u002Fparser path,\nself-test, a valid 24-value fixture, invalid 23\u002F25-value fixtures, action-range\nmismatches, a synthetic point cloud, and strict threshold cases. No ROS,\nGazebo, `roscore`, `roslaunch`, or catkin runtime is claimed or required here.\n","# Navigation environment\n\nUse this skill when a downstream agent needs to reason about the mobile-robot\n`GazeboEnv` interface, prepare a compatible observation\u002Faction, diagnose a\nsensor or ROS integration failure, or check a synthetic transition. This skill\nis a distilled contract, not a simulator launcher and not a TD3 training guide.\n\n## Operating contract\n\n- The repository's training configuration uses `environment_dim=20` and four\n  robot features, so every observation is a flat numeric vector of length 24.\n- The first 20 values are Velodyne distance bins, initialized to 10 and\n  updated by the point-cloud callback. The final four values are, in order,\n  distance to goal, relative goal heading, linear action, and angular action.\n  `reset` returns the two action slots as 0; `step` places the action used for\n  that transition in them. There is no separate previous-action history in\n  the implementation, so do not invent one.\n- The environment-facing action is `[linear_x, angular_z]`: linear is in\n  `[0, 1]`, angular is in `[-1, 1]`. `step` publishes these values directly;\n  it does not rescale them. A TD3 actor output in `[-1, 1]` therefore needs its\n  first component mapped with `(a_linear + 1) \u002F 2` before calling `step`.\n- `done` becomes true on a laser collision or a goal hit. A goal hit is\n  reported separately as `target=True`; collision and target reward priority\n  is target first, then collision.\n- Use `scripts\u002Fvalidate_navigation_contract.py` for offline numeric checks.\n  It imports no ROS package, starts no process, and is the preferred check for\n  state length, action range, point-bin fixtures, and threshold behavior.\n\n## Safe reasoning workflow\n\n1. Confirm the caller has ROS Noetic\u002FUbuntu 20.04-compatible ROS message and\n   Gazebo dependencies, plus Python dependencies used by the environment\n   (`numpy` and `squaternion`). A live run additionally needs `roscore`,\n   `roslaunch`, Gazebo, and a built catkin workspace with the scenario and\n   Velodyne plugin packages. This host-independent skill does not install or\n   launch any of them.\n2. Treat a relative launch name as relative to the environment module's\n   `assets` directory, not the caller's current directory. The repository's\n   `multi_robot_scenario.launch` includes the empty TD3 world and spawns model\n   `r1`.\n3. Validate an observation as 20 finite sensor values followed by four finite\n   robot values. Reject 23- or 25-value vectors rather than silently padding or\n   truncating them.\n4. Validate action-space provenance. If an actor produced `[-1, 1]` for both\n   dimensions, transform only the linear component before using this\n   environment contract.\n5. For a synthetic sensor case, reduce points into the same 20 angular bins,\n   compute the minimum distance per bin, and then apply the strict collision\n   threshold. Keep simulator verification explicitly unavailable when ROS or\n   Gazebo is absent.\n6. Interpret `reset` and `step` as ROS-dependent calls. A valid offline vector\n   does not prove that odometry, PointCloud2, publishers, or physics services\n   are connected.\n\n## Scope boundaries\n\nThis skill covers constructor prerequisites and launch resolution, point-cloud\nreduction, state\u002Faction\u002Freward semantics, reset randomization, ROS interfaces,\nand predictable numeric\u002Fintegration failures. Do not use it to explain TD3\nnetwork architecture, replay-buffer behavior, optimizer settings, training\nloops, model checkpoints, or installation procedures beyond naming prerequisites.\nSee the bundled references for the detailed contract and troubleshooting.\n\n## Numeric and evidence notes\n\nThe source callback has no explicit finite-value or zero-horizontal-range\n guard. Use the validator's stricter finite-input policy for synthetic data;\nnever turn NaN or an `acos` domain error into a claimed sensor reading.\n\n## Evidence and verification status\n\nThe contract was distilled from the pinned repository's environment module,\nlaunch file, scenario xacro\u002FURDF, Velodyne description and Gazebo plugin, and\ntraining caller. The offline validator is checked with its help\u002Fparser path,\nself-test, a valid 24-value fixture, invalid 23\u002F25-value fixtures, action-range\nmismatches, a synthetic point cloud, and strict threshold cases. No ROS,\nGazebo, `roscore`, `roslaunch`, or catkin runtime is claimed or required here.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment",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 navigation-environment",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill navigation-environment",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill navigation-environment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\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",5419,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fstate-action-reward.md",4595,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\u002Freferences\u002Fstate-action-reward.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5020,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fvalidate_navigation_contract.py","SCRIPT","脚本",10825,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdrl-robot-navigation\u002Fsub-skills\u002Fnavigation-environment\u002Fscripts\u002Fvalidate_navigation_contract.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",[],[]]