[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79562F5BGS7CTEMGYNG5TXG":3,"skill-same:01M79562F5BGS7CTEMGYNG5TXG":78},{"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},"01M79562F5BGS7CTEMGYNG5TXG","sensors-visualization",null,"Configure SMARTS sensor observations, optional Panda3D rendering, Envision recording and replay, and safe diagnostics without conflating CPU checks with graphics services.","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\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sensors-visualization\ndescription: \"Configure SMARTS sensor observations, optional Panda3D rendering,\n  Envision recording and replay, and safe diagnostics without conflating CPU\n  checks with graphics services.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# SMARTS sensors and visualization\n\nUse this route when an agent needs additional SMARTS observations, camera\u002Fgrid\noutputs, custom shader renders, Envision state streaming or replay, or a\nread-only check of rendering and replay prerequisites. Keep the simulation\nlifecycle and environment creation in `simulation-environments`; use\n`cli-integrations` for exact `scl` command syntax. Frontend npm development,\nraw media, and long-running servers are outside this route.\n\n## Decide which boundary you are testing\n\n1. Start with a CPU\u002Fnon-rendered interface when the policy only needs state,\n   waypoints, lidar, lane positions, accelerometer, signals, or nearby actors.\n2. Treat `drivable_area_grid_map`, `occupancy_grid_map`, `top_down_rgb`, and\n   `custom_renders` as software-rendering features. They require the camera\n   extra and a usable Panda3D\u002FOpenGL offscreen or X11 display.\n3. An `occlusion_map` also requires an occupancy map with identical width and\n   height. It is a rendered output, not a CPU-only visibility calculation.\n4. Envision is a separate client\u002Fserver\u002Fbrowser path. A successful SMARTS\n   import or Panda3D import does not prove that the server is listening.\n\nRead the linked references before building an interface:\n\n- [sensor-reference.md](references\u002Fsensor-reference.md) — configuration\n  dataclasses, sensor semantics, and observation contracts.\n- [rendering-and-cameras.md](references\u002Frendering-and-cameras.md) — camera\n  extras, offscreen rendering, custom shaders, and performance boundaries.\n- [envision-and-replay.md](references\u002Fenvision-and-replay.md) — client\u002Fserver,\n  JSONL recording, replay, and Visdom limits.\n- [data-formats.md](references\u002Fdata-formats.md) — shapes, metadata, and stable\n  serialization expectations.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) — failures by install,\n  configuration, API misuse, renderer, and service workflow.\n\n## Configure the interface\n\nUse `AgentInterface` with explicit dataclass values when a non-default shape,\nrange, or lookahead matters. Boolean `True` resolves to the corresponding\nconfig dataclass; `False` disables the sensor. The interface defaults\naccelerometer and lane positions on, but leaves most expensive or optional\nsensors off. `AgentInterface.from_type(AgentType.Full, ...)` is convenient but\nalso enables rendered observations and lidar; do not use it as a cheap smoke\ninterface.\n\n```python\nfrom smarts.core.agent_interface import (\n    AgentInterface, Waypoints, NeighborhoodVehicles, RGB, OGM,\n)\n\ninterface = AgentInterface(\n    waypoint_paths=Waypoints(lookahead=32),\n    neighborhood_vehicle_states=NeighborhoodVehicles(radius=50),\n    top_down_rgb=RGB(width=128, height=128, resolution=100 \u002F 128),\n    occupancy_grid_map=OGM(width=128, height=128, resolution=100 \u002F 128),\n    action=...,  # select an action type in the environment route\n)\n```\n\nBefore stepping, inspect the environment's per-agent observation space and\nconfirm that the policy reads only enabled fields. After a step, check `None`\nfor disabled optional fields and preserve the named observation structures;\ndo not assume every observation is a flat NumPy array.\n\n## Workflow and checks\n\n- For CPU checks, import `AgentInterface`, construct low-dimensional sensor\n  configs, and run a bounded environment test through the sibling lifecycle\n  route. This does not require Panda3D.\n- For camera checks, run\n  [`scripts\u002Fcheck_rendering.py`](scripts\u002Fcheck_rendering.py), preferably under\n  `xvfb-run -a`. Use `--probe-offscreen` only for a bounded construction and\n  teardown probe; it is not a renderer behavior test.\n- For Envision records, use\n  [`scripts\u002Finspect_replay_records.py`](scripts\u002Finspect_replay_records.py) on a\n  file or directory. It never sends data, starts a server, or modifies files.\n- Keep image dimensions and resolution small while diagnosing. Image sensors\n  can dominate `step()` time and memory.\n- For recording or replay, verify the server endpoint separately and inspect\n  the generated JSONL before attempting playback. Use the CLI sibling route\n  for command spelling; this skill documents the Python client contract only.\n\n## Verified limits\n\nThe prepared SMARTS 2.0.1 environment passed package imports, live interface\nand lidar signature inspection, and a Panda3D\u002FSMARTS renderer import smoke\nunder Xvfb. That is evidence for importability only. Full renderer behavior,\nlarge image observations, Visdom, and a live Envision server remain optional\nor unverified. The bundled helpers report these limits rather than claiming a\nsuccessful renderer or visualization session.\n","# SMARTS sensors and visualization\n\nUse this route when an agent needs additional SMARTS observations, camera\u002Fgrid\noutputs, custom shader renders, Envision state streaming or replay, or a\nread-only check of rendering and replay prerequisites. Keep the simulation\nlifecycle and environment creation in `simulation-environments`; use\n`cli-integrations` for exact `scl` command syntax. Frontend npm development,\nraw media, and long-running servers are outside this route.\n\n## Decide which boundary you are testing\n\n1. Start with a CPU\u002Fnon-rendered interface when the policy only needs state,\n   waypoints, lidar, lane positions, accelerometer, signals, or nearby actors.\n2. Treat `drivable_area_grid_map`, `occupancy_grid_map`, `top_down_rgb`, and\n   `custom_renders` as software-rendering features. They require the camera\n   extra and a usable Panda3D\u002FOpenGL offscreen or X11 display.\n3. An `occlusion_map` also requires an occupancy map with identical width and\n   height. It is a rendered output, not a CPU-only visibility calculation.\n4. Envision is a separate client\u002Fserver\u002Fbrowser path. A successful SMARTS\n   import or Panda3D import does not prove that the server is listening.\n\nRead the linked references before building an interface:\n\n- [sensor-reference.md](references\u002Fsensor-reference.md) — configuration\n  dataclasses, sensor semantics, and observation contracts.\n- [rendering-and-cameras.md](references\u002Frendering-and-cameras.md) — camera\n  extras, offscreen rendering, custom shaders, and performance boundaries.\n- [envision-and-replay.md](references\u002Fenvision-and-replay.md) — client\u002Fserver,\n  JSONL recording, replay, and Visdom limits.\n- [data-formats.md](references\u002Fdata-formats.md) — shapes, metadata, and stable\n  serialization expectations.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) — failures by install,\n  configuration, API misuse, renderer, and service workflow.\n\n## Configure the interface\n\nUse `AgentInterface` with explicit dataclass values when a non-default shape,\nrange, or lookahead matters. Boolean `True` resolves to the corresponding\nconfig dataclass; `False` disables the sensor. The interface defaults\naccelerometer and lane positions on, but leaves most expensive or optional\nsensors off. `AgentInterface.from_type(AgentType.Full, ...)` is convenient but\nalso enables rendered observations and lidar; do not use it as a cheap smoke\ninterface.\n\n```python\nfrom smarts.core.agent_interface import (\n    AgentInterface, Waypoints, NeighborhoodVehicles, RGB, OGM,\n)\n\ninterface = AgentInterface(\n    waypoint_paths=Waypoints(lookahead=32),\n    neighborhood_vehicle_states=NeighborhoodVehicles(radius=50),\n    top_down_rgb=RGB(width=128, height=128, resolution=100 \u002F 128),\n    occupancy_grid_map=OGM(width=128, height=128, resolution=100 \u002F 128),\n    action=...,  # select an action type in the environment route\n)\n```\n\nBefore stepping, inspect the environment's per-agent observation space and\nconfirm that the policy reads only enabled fields. After a step, check `None`\nfor disabled optional fields and preserve the named observation structures;\ndo not assume every observation is a flat NumPy array.\n\n## Workflow and checks\n\n- For CPU checks, import `AgentInterface`, construct low-dimensional sensor\n  configs, and run a bounded environment test through the sibling lifecycle\n  route. This does not require Panda3D.\n- For camera checks, run\n  [`scripts\u002Fcheck_rendering.py`](scripts\u002Fcheck_rendering.py), preferably under\n  `xvfb-run -a`. Use `--probe-offscreen` only for a bounded construction and\n  teardown probe; it is not a renderer behavior test.\n- For Envision records, use\n  [`scripts\u002Finspect_replay_records.py`](scripts\u002Finspect_replay_records.py) on a\n  file or directory. It never sends data, starts a server, or modifies files.\n- Keep image dimensions and resolution small while diagnosing. Image sensors\n  can dominate `step()` time and memory.\n- For recording or replay, verify the server endpoint separately and inspect\n  the generated JSONL before attempting playback. Use the CLI sibling route\n  for command spelling; this skill documents the Python client contract only.\n\n## Verified limits\n\nThe prepared SMARTS 2.0.1 environment passed package imports, live interface\nand lidar signature inspection, and a Panda3D\u002FSMARTS renderer import smoke\nunder Xvfb. That is evidence for importability only. Full renderer behavior,\nlarge image observations, Visdom, and a live Envision server remain optional\nor unverified. The bundled helpers report these limits rather than claiming a\nsuccessful renderer or visualization session.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization",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 sensors-visualization",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sensors-visualization",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sensors-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002FSKILL.md",[46,52,56,60,64,68,74],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-formats.md","REFERENCE","参考文档",4368,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Freferences\u002Fdata-formats.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fenvision-and-replay.md",4525,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Freferences\u002Fenvision-and-replay.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frendering-and-cameras.md",4887,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Freferences\u002Frendering-and-cameras.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsensor-reference.md",5456,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Freferences\u002Fsensor-reference.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",5415,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_rendering.py","SCRIPT","脚本",3667,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Fscripts\u002Fcheck_rendering.py",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Finspect_replay_records.py",3142,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmarts\u002Fsub-skills\u002Fsensors-visualization\u002Fscripts\u002Finspect_replay_records.py",[79,87,94,101,108,115],{"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":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]