{"owner":"carla-simulator","repo":"carla","hasSkills":true,"totalSkillsCount":4,"totalTokensCount":4127,"categories":["root-instruction","mcp-config","marketplace","plugin-manifest"],"hasMcp":true,"mcpConfig":{"mcpServers":{"carla":{"command":"npx","args":["-y","@modelcontextprotocol/server-carla"]}}},"found":["AGENTS.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json"],"skills":{"AGENTS.md":"# AGENTS.md\n\nGuidance for any coding agent working in this repository.\n\n## Skills\n\nThis repo ships a library of **62 vetted CARLA procedures** under\n[`Skills/`](Skills/). Each is a directory containing a `SKILL.md` with YAML\nfrontmatter (`name`, `description`, `compatibility`, `metadata`), the step-by-step\nprocedure, and often `scripts/` and `references/` beside it.\n\n**These skills are the source of truth** for building, packaging, cooking,\nmap/vehicle/asset import, running servers, scenarios and ROS 2, and they cover\nmost of the commands those tasks need.\n\n### How to use them\n\n1. Match the user's request against the catalogue below.\n2. Read that skill's `SKILL.md` in full before acting — each encodes the\n   failure modes that make the naive approach fail.\n3. Run its `scripts/check_env.sh` (when `metadata.prerequisites` names one)\n   before starting.\n4. Follow the procedure rather than improvising; the gotchas sections exist\n   because those mistakes have already cost someone a day.\n\nPaths (`CARLA_ROOT` and friends) are configured on first need, not up front.\nNever guess a path — several CARLA checkouts on one machine is normal and the\nwrong one fails slowly. Ask the user, then record the answer.\n\n### Optional: MCP server\n\n[`Util/AgenticTools/`](Util/AgenticTools/) serves the same skills over MCP\n(`list_skills`, `read_skill`, `check_prerequisites`, `get_config`,\n`set_config`), which adds environment detection and persistent path config.\nProject config is in [`.mcp.json`](.mcp.json); clients that read it get the\ntools automatically. Agents without MCP should read `Skills/` directly — the\nfiles are the source of truth either way.\n\n## Skill catalogue\n\n### `docs`\n\n- **`audit-carla-docs`** — Finds undocumented and rotting documentation in a CARLA checkout — unreleased features, bindings missing from the API reference, documented API that no longer exists....\n- **`document-carla-feature`** — Writes the missing CARLA documentation that the audit found, one category at a time, in CARLA's house style....\n\n### `leaderboard`\n\n- **`create-leaderboard-route`** — Creates and edits CARLA Leaderboard route files — placing waypoints and scenario trigger points interactively from the spectator camera....\n- **`package-leaderboard-agent`** — Packages an agent for CARLA Leaderboard submission — builds the docker image with make_docker.sh (plain or ROS variant), checks the four required....\n- **`read-leaderboard-results`** — Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the....\n- **`run-leaderboard-evaluation`** — Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selection, checkpoint and....\n- **`write-leaderboard-agent`** — Writes an autonomous agent for the CARLA Leaderboard — an AutonomousAgent subclass with setup/sensors/run_step/destroy, a sensor suite inside the....\n\n### `python-api`\n\n- **`bounding-boxes`** — Gets actor and level 3D bounding boxes and projects them into a camera image as 2D boxes — the dataset-annotation workflow.\n- **`control-lights`** — Controls the map's light sources through the CARLA LightManager — turn street lamps, building/facade lights, vehicle lights or all of them on/off,....\n- **`control-spectator`** — Moves the CARLA spectator camera, frames an actor, or follows one live — third-person/chase, first-person/driver, top-down, or front views,....\n- **`control-traffic`** — Tunes the CARLA Traffic Manager that drives autopilot vehicles — global and per-vehicle speed, following distance, running lights/signs,....\n- **`control-traffic-lights`** — Controls the traffic-light actors on a running CARLA server — set a light green/red/yellow/off, freeze all lights (optionally all-green), set....\n- **`control-vehicle`** — Directly drives a specific vehicle on a running CARLA server — raw VehicleControl (throttle/steer/brake/reverse/hand-brake), Ackermann speed....\n- **`create-sensor`** — Spawns and attaches sensors on a running CARLA server — cameras (rgb/depth/semantic/instance/optical-flow/normals), lidar, radar, IMU, GNSS,....\n- **`debug-draw`** — Draws debug overlays in a running CARLA world via world.debug — points, lines, arrows, bounding boxes, and text strings, each with a colour and....\n- **`debug-navmesh`** — Visualises and validates a map's pedestrian navigation mesh by sampling walkable locations (get_random_location_from_navigation) and drawing them....\n- **`load-map`** — Loads, reloads, and reshapes the map on a running CARLA server via the Python API — get_available_maps, load_world and reload_world (with or....\n- **`map-waypoints`** — Explores a CARLA map's road network through the Map/Waypoint API — a natural-language rundown of the whole map (\"give me the topology\"), drawing....\n- **`navigate-to`** — Drives a vehicle to a destination autonomously using CARLA's navigation agents (BasicAgent/BehaviorAgent/ConstantVelocityAgent), or plans a route....\n- **`query-recording`** — Inspects a recorded CARLA .log without replaying it — show_recorder_file_info for the header/actors/frames, collision queries between actor....\n- **`read-sensor`** — Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the....\n- **`record-simulation`** — Records a running CARLA simulation to a .log file via start_recorder/stop_recorder for later deterministic replay — capturing actor spawns,....\n- **`replay-recording`** — Replays a CARLA .log recorded by the recorder — the whole run or a time window, at any speed, following a chosen actor, optionally regenerating....\n- **`set-weather`** — Reads and sets the weather on a running CARLA server via get_weather/set_weather, and turns natural-language weather requests (\"heavy rain at....\n- **`set-world-settings`** — Reads and changes a running CARLA server's WorldSettings via apply_settings — synchronous vs asynchronous mode, fixed_delta_seconds (fps), physics....\n- **`spawn-vehicles`** — Spawns vehicles on a running CARLA server and destroys them — scattered across the map's spawn points on Traffic Manager autopilot, a row queued....\n- **`spawn-walkers`** — Spawns pedestrians that wander autonomously via WalkerAIController, and destroys them in the correct order.\n- **`telemetry`** — Reads a specific actor's live telemetry from a running CARLA server — location and rotation, velocity and speed, acceleration, angular velocity,....\n- **`toggle-env-objects`** — Lists and toggles a map's static environment objects via get_environment_objects / enable_environment_objects — hide or show buildings,....\n- **`world-data`** — Queries the live CARLA world and resolves an entity description into a concrete actor id — find actors by type, role, or colour, or the single one....\n\n### `ros2`\n\n- **`add-ros-message-type`** — Adds a new ROS 2 message type to CARLA's native ROS 2 interface — the hand-written POD struct under LibCarla/source/carla/ros2/types/msg, its....\n- **`add-ros-publisher`** — Adds a new topic to CARLA's native ROS 2 interface — a publisher (BasePublisher + PublisherImpl, topic suffix, QoS, registration in....\n- **`visualize-ros-rviz`** — Inspects and visualises a ROS-2-enabled CARLA server from Docker containers, with no local ROS 2 install — list/echo/rate-check topics (the \"are....\n\n### `scenario-runner`\n\n- **`analyze-scenario-results`** — Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result....\n- **`create-scenario`** — Writes a new ScenarioRunner scenario — a Python class deriving from BasicScenario with its behaviour tree assembled from srunner atomic behaviours....\n- **`run-openscenario`** — Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs and ParameterDeclaration....\n- **`run-route-scenario`** — Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego — the same mechanism the....\n- **`run-scenario`** — Runs a single ScenarioRunner Python scenario (or a whole group) against a running CARLA server — FollowLeadingVehicle, ControlLoss,....\n\n### `scenic`\n\n- **`create-scenic-scenario`** — Writes a new Scenic scenario (.scenic) from a natural-language description — \"a car cuts in from the right lane\", \"a pedestrian crosses in front....\n- **`run-scenic-scenario`** — Runs Scenic probabilistic scenarios against a running CARLA server with the `scenic FILE --simulate --2d` CLI — the carlaChallenge1-10 traffic....\n\n### `setup`\n\n- **`check-feature-support`** — Answers \"can CARLA do X here, and is there a vetted procedure for it\" before you promise anything, and detects client/server/tree version skew — a....\n- **`download-carla`** — Downloads CARLA so nothing has to be fetched by hand — an official release package for any published version (resolved live from the GitHub....\n- **`install-leaderboard`** — Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact....\n- **`install-python-api`** — Installs the CARLA Python client (the `carla` package) into a chosen interpreter so the other python-api skills work — from a wheel bundled with....\n- **`install-scenario-runner`** — Installs CARLA's ScenarioRunner (the official scenario engine) and picks the branch that matches the CARLA in use — master for 0.9.14-0.9.16....\n- **`install-scenic`** — Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds....\n\n### `ue4`\n\n- **`build-carla-ue4`** — Builds CARLA (branch ue4-dev, Unreal Engine 4.26) from source on Linux end-to-end — UE4 fork, the Carla server (editor C++ modules), the LibCarla....\n- **`import-carla-map`** — Imports a custom RoadRunner map (FBX geometry + XODR OpenDRIVE) into a CARLA source build as a drivable map — reads the map from the directory the....\n- **`import-carla-prop`** — Imports FBX meshes into a CARLA source build as spawnable static.prop.* blueprints — pass a directory whose subdirectories name the semantic tags,....\n- **`import-carla-vehicle`** — Imports an FBX vehicle into a CARLA source build as a spawnable vehicle.<make>.<model> — checks the FBX carries CARLA's 4-wheel bone rig, imports....\n- **`import-carla-walker`** — Imports an FBX pedestrian into a CARLA source build as a spawnable walker.pedestrian.NNNN — checks the FBX is skinned to CARLA's GEN3 rig, imports....\n- **`package-carla-ue4`** — Cooks and packages CarlaUE4 into distributable tarballs under Dist/ — either the full simulator or a standalone asset package of selected maps and....\n- **`run-carla-server`** — Launches a CARLA RPC server a carla.Client can connect to, working out for itself what you pointed it at — a downloaded/extracted release, a....\n\n### `ue5`\n\n- **`check-ue5-limitations`** — Tells you what CARLA on UE 5.5 (branch ue5-dev) cannot do that UE 5.8 (ue58-dev) can, so you do not attempt an unsupported workflow there — no....\n\n### `ue58`\n\n- **`build-carla-ue58`** — Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal /....\n- **`carla-vehicle-authoring`** — Create, migrate, improve, or debug detailed vehicle assets for CARLA using Blender and Unreal, including reference-based geometry, materials,....\n- **`import-carla-ue58-map`** — Gets a custom map into CARLA on UE 5.8 — the four distinct routes and which one to pick — via Util/Tools/Import.py for FBX+OpenDRIVE assets into a....\n- **`import-carla-ue58-prop`** — Imports FBX meshes into CARLA on UE 5.8 as spawnable props — drives the editor headlessly to import the mesh, derives the prop size from its....\n- **`import-carla-ue58-walker`** — Imports a pedestrian into CARLA on UE 5.8 as a spawnable, animating walker — imports the skinned FBX bound to CARLA's shared pedestrian skeleton,....\n- **`package-carla-ue58`** — Cooks and packages a shippable CARLA server from a UE 5.8 ue58-dev checkout via the CMake `package` targets (shipping/development/debug/test),....\n- **`run-autoware-ue58`** — Runs the Autoware autonomous-driving stack against CARLA on UE 5.8 over CARLA's native ROS 2 interface — no bridge process.\n- **`run-carla-ue58-server`** — Starts a CARLA UE 5.8 server from a ue58-dev tree — the editor binary in -game mode (the working headless server), the packaged shipping build, or....\n\n## Repository conventions\n\n- `LibCarla/` — the C++ client/server library. `PythonAPI/` — bindings, docs\n  (`PythonAPI/docs/*.yml`) and examples.\n- `Docs/python_api.md` is **generated** from `PythonAPI/docs/*.yml` by\n  `PythonAPI/docs/doc_gen.py`. Never edit it directly; edit the YAML and\n  regenerate.\n- Smoke tests live in `PythonAPI/test/smoke/` and need a running server on\n  port 3654.\n- Add a `CHANGELOG.md` entry under `## LATEST Changes` for user-visible changes.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/plugin.json)"},"files":{"AGENTS.md":"# AGENTS.md\n\nGuidance for any coding agent working in this repository.\n\n## Skills\n\nThis repo ships a library of **62 vetted CARLA procedures** under\n[`Skills/`](Skills/). Each is a directory containing a `SKILL.md` with YAML\nfrontmatter (`name`, `description`, `compatibility`, `metadata`), the step-by-step\nprocedure, and often `scripts/` and `references/` beside it.\n\n**These skills are the source of truth** for building, packaging, cooking,\nmap/vehicle/asset import, running servers, scenarios and ROS 2, and they cover\nmost of the commands those tasks need.\n\n### How to use them\n\n1. Match the user's request against the catalogue below.\n2. Read that skill's `SKILL.md` in full before acting — each encodes the\n   failure modes that make the naive approach fail.\n3. Run its `scripts/check_env.sh` (when `metadata.prerequisites` names one)\n   before starting.\n4. Follow the procedure rather than improvising; the gotchas sections exist\n   because those mistakes have already cost someone a day.\n\nPaths (`CARLA_ROOT` and friends) are configured on first need, not up front.\nNever guess a path — several CARLA checkouts on one machine is normal and the\nwrong one fails slowly. Ask the user, then record the answer.\n\n### Optional: MCP server\n\n[`Util/AgenticTools/`](Util/AgenticTools/) serves the same skills over MCP\n(`list_skills`, `read_skill`, `check_prerequisites`, `get_config`,\n`set_config`), which adds environment detection and persistent path config.\nProject config is in [`.mcp.json`](.mcp.json); clients that read it get the\ntools automatically. Agents without MCP should read `Skills/` directly — the\nfiles are the source of truth either way.\n\n## Skill catalogue\n\n### `docs`\n\n- **`audit-carla-docs`** — Finds undocumented and rotting documentation in a CARLA checkout — unreleased features, bindings missing from the API reference, documented API that no longer exists....\n- **`document-carla-feature`** — Writes the missing CARLA documentation that the audit found, one category at a time, in CARLA's house style....\n\n### `leaderboard`\n\n- **`create-leaderboard-route`** — Creates and edits CARLA Leaderboard route files — placing waypoints and scenario trigger points interactively from the spectator camera....\n- **`package-leaderboard-agent`** — Packages an agent for CARLA Leaderboard submission — builds the docker image with make_docker.sh (plain or ROS variant), checks the four required....\n- **`read-leaderboard-results`** — Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the....\n- **`run-leaderboard-evaluation`** — Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selection, checkpoint and....\n- **`write-leaderboard-agent`** — Writes an autonomous agent for the CARLA Leaderboard — an AutonomousAgent subclass with setup/sensors/run_step/destroy, a sensor suite inside the....\n\n### `python-api`\n\n- **`bounding-boxes`** — Gets actor and level 3D bounding boxes and projects them into a camera image as 2D boxes — the dataset-annotation workflow.\n- **`control-lights`** — Controls the map's light sources through the CARLA LightManager — turn street lamps, building/facade lights, vehicle lights or all of them on/off,....\n- **`control-spectator`** — Moves the CARLA spectator camera, frames an actor, or follows one live — third-person/chase, first-person/driver, top-down, or front views,....\n- **`control-traffic`** — Tunes the CARLA Traffic Manager that drives autopilot vehicles — global and per-vehicle speed, following distance, running lights/signs,....\n- **`control-traffic-lights`** — Controls the traffic-light actors on a running CARLA server — set a light green/red/yellow/off, freeze all lights (optionally all-green), set....\n- **`control-vehicle`** — Directly drives a specific vehicle on a running CARLA server — raw VehicleControl (throttle/steer/brake/reverse/hand-brake), Ackermann speed....\n- **`create-sensor`** — Spawns and attaches sensors on a running CARLA server — cameras (rgb/depth/semantic/instance/optical-flow/normals), lidar, radar, IMU, GNSS,....\n- **`debug-draw`** — Draws debug overlays in a running CARLA world via world.debug — points, lines, arrows, bounding boxes, and text strings, each with a colour and....\n- **`debug-navmesh`** — Visualises and validates a map's pedestrian navigation mesh by sampling walkable locations (get_random_location_from_navigation) and drawing them....\n- **`load-map`** — Loads, reloads, and reshapes the map on a running CARLA server via the Python API — get_available_maps, load_world and reload_world (with or....\n- **`map-waypoints`** — Explores a CARLA map's road network through the Map/Waypoint API — a natural-language rundown of the whole map (\"give me the topology\"), drawing....\n- **`navigate-to`** — Drives a vehicle to a destination autonomously using CARLA's navigation agents (BasicAgent/BehaviorAgent/ConstantVelocityAgent), or plans a route....\n- **`query-recording`** — Inspects a recorded CARLA .log without replaying it — show_recorder_file_info for the header/actors/frames, collision queries between actor....\n- **`read-sensor`** — Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the....\n- **`record-simulation`** — Records a running CARLA simulation to a .log file via start_recorder/stop_recorder for later deterministic replay — capturing actor spawns,....\n- **`replay-recording`** — Replays a CARLA .log recorded by the recorder — the whole run or a time window, at any speed, following a chosen actor, optionally regenerating....\n- **`set-weather`** — Reads and sets the weather on a running CARLA server via get_weather/set_weather, and turns natural-language weather requests (\"heavy rain at....\n- **`set-world-settings`** — Reads and changes a running CARLA server's WorldSettings via apply_settings — synchronous vs asynchronous mode, fixed_delta_seconds (fps), physics....\n- **`spawn-vehicles`** — Spawns vehicles on a running CARLA server and destroys them — scattered across the map's spawn points on Traffic Manager autopilot, a row queued....\n- **`spawn-walkers`** — Spawns pedestrians that wander autonomously via WalkerAIController, and destroys them in the correct order.\n- **`telemetry`** — Reads a specific actor's live telemetry from a running CARLA server — location and rotation, velocity and speed, acceleration, angular velocity,....\n- **`toggle-env-objects`** — Lists and toggles a map's static environment objects via get_environment_objects / enable_environment_objects — hide or show buildings,....\n- **`world-data`** — Queries the live CARLA world and resolves an entity description into a concrete actor id — find actors by type, role, or colour, or the single one....\n\n### `ros2`\n\n- **`add-ros-message-type`** — Adds a new ROS 2 message type to CARLA's native ROS 2 interface — the hand-written POD struct under LibCarla/source/carla/ros2/types/msg, its....\n- **`add-ros-publisher`** — Adds a new topic to CARLA's native ROS 2 interface — a publisher (BasePublisher + PublisherImpl, topic suffix, QoS, registration in....\n- **`visualize-ros-rviz`** — Inspects and visualises a ROS-2-enabled CARLA server from Docker containers, with no local ROS 2 install — list/echo/rate-check topics (the \"are....\n\n### `scenario-runner`\n\n- **`analyze-scenario-results`** — Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result....\n- **`create-scenario`** — Writes a new ScenarioRunner scenario — a Python class deriving from BasicScenario with its behaviour tree assembled from srunner atomic behaviours....\n- **`run-openscenario`** — Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs and ParameterDeclaration....\n- **`run-route-scenario`** — Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego — the same mechanism the....\n- **`run-scenario`** — Runs a single ScenarioRunner Python scenario (or a whole group) against a running CARLA server — FollowLeadingVehicle, ControlLoss,....\n\n### `scenic`\n\n- **`create-scenic-scenario`** — Writes a new Scenic scenario (.scenic) from a natural-language description — \"a car cuts in from the right lane\", \"a pedestrian crosses in front....\n- **`run-scenic-scenario`** — Runs Scenic probabilistic scenarios against a running CARLA server with the `scenic FILE --simulate --2d` CLI — the carlaChallenge1-10 traffic....\n\n### `setup`\n\n- **`check-feature-support`** — Answers \"can CARLA do X here, and is there a vetted procedure for it\" before you promise anything, and detects client/server/tree version skew — a....\n- **`download-carla`** — Downloads CARLA so nothing has to be fetched by hand — an official release package for any published version (resolved live from the GitHub....\n- **`install-leaderboard`** — Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact....\n- **`install-python-api`** — Installs the CARLA Python client (the `carla` package) into a chosen interpreter so the other python-api skills work — from a wheel bundled with....\n- **`install-scenario-runner`** — Installs CARLA's ScenarioRunner (the official scenario engine) and picks the branch that matches the CARLA in use — master for 0.9.14-0.9.16....\n- **`install-scenic`** — Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds....\n\n### `ue4`\n\n- **`build-carla-ue4`** — Builds CARLA (branch ue4-dev, Unreal Engine 4.26) from source on Linux end-to-end — UE4 fork, the Carla server (editor C++ modules), the LibCarla....\n- **`import-carla-map`** — Imports a custom RoadRunner map (FBX geometry + XODR OpenDRIVE) into a CARLA source build as a drivable map — reads the map from the directory the....\n- **`import-carla-prop`** — Imports FBX meshes into a CARLA source build as spawnable static.prop.* blueprints — pass a directory whose subdirectories name the semantic tags,....\n- **`import-carla-vehicle`** — Imports an FBX vehicle into a CARLA source build as a spawnable vehicle.<make>.<model> — checks the FBX carries CARLA's 4-wheel bone rig, imports....\n- **`import-carla-walker`** — Imports an FBX pedestrian into a CARLA source build as a spawnable walker.pedestrian.NNNN — checks the FBX is skinned to CARLA's GEN3 rig, imports....\n- **`package-carla-ue4`** — Cooks and packages CarlaUE4 into distributable tarballs under Dist/ — either the full simulator or a standalone asset package of selected maps and....\n- **`run-carla-server`** — Launches a CARLA RPC server a carla.Client can connect to, working out for itself what you pointed it at — a downloaded/extracted release, a....\n\n### `ue5`\n\n- **`check-ue5-limitations`** — Tells you what CARLA on UE 5.5 (branch ue5-dev) cannot do that UE 5.8 (ue58-dev) can, so you do not attempt an unsupported workflow there — no....\n\n### `ue58`\n\n- **`build-carla-ue58`** — Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal /....\n- **`carla-vehicle-authoring`** — Create, migrate, improve, or debug detailed vehicle assets for CARLA using Blender and Unreal, including reference-based geometry, materials,....\n- **`import-carla-ue58-map`** — Gets a custom map into CARLA on UE 5.8 — the four distinct routes and which one to pick — via Util/Tools/Import.py for FBX+OpenDRIVE assets into a....\n- **`import-carla-ue58-prop`** — Imports FBX meshes into CARLA on UE 5.8 as spawnable props — drives the editor headlessly to import the mesh, derives the prop size from its....\n- **`import-carla-ue58-walker`** — Imports a pedestrian into CARLA on UE 5.8 as a spawnable, animating walker — imports the skinned FBX bound to CARLA's shared pedestrian skeleton,....\n- **`package-carla-ue58`** — Cooks and packages a shippable CARLA server from a UE 5.8 ue58-dev checkout via the CMake `package` targets (shipping/development/debug/test),....\n- **`run-autoware-ue58`** — Runs the Autoware autonomous-driving stack against CARLA on UE 5.8 over CARLA's native ROS 2 interface — no bridge process.\n- **`run-carla-ue58-server`** — Starts a CARLA UE 5.8 server from a ue58-dev tree — the editor binary in -game mode (the working headless server), the packaged shipping build, or....\n\n## Repository conventions\n\n- `LibCarla/` — the C++ client/server library. `PythonAPI/` — bindings, docs\n  (`PythonAPI/docs/*.yml`) and examples.\n- `Docs/python_api.md` is **generated** from `PythonAPI/docs/*.yml` by\n  `PythonAPI/docs/doc_gen.py`. Never edit it directly; edit the YAML and\n  regenerate.\n- Smoke tests live in `PythonAPI/test/smoke/` and need a running server on\n  port 3654.\n- Add a `CHANGELOG.md` entry under `## LATEST Changes` for user-visible changes.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/plugin.json)"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/carla-simulator/carla/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# AGENTS.md\n\nGuidance for any coding agent working in this repository.\n\n## Skills\n\nThis repo ships a library of **62 vetted CARLA procedures** under\n[`Skills/`](Skills/). Each is a directory containing a `SKILL.md` with YAML\nfrontmatter (`name`, `description`, `compatibility`, `metadata`), the step-by-step\nprocedure, and often `scripts/` and `references/` beside it.\n\n**These skills are the source of truth** for building, packaging, cooking,\nmap/vehicle/asset import, running servers, scenarios and ROS 2, and they cover\nmost of the commands those tasks need.\n\n### How to use them\n\n1. Match the user's request against the catalogue below.\n2. Read that skill's `SKILL.md` in full before acting — each encodes the\n   failure modes that make the naive approach fail.\n3. Run its `scripts/check_env.sh` (when `metadata.prerequisites` names one)\n   before starting.\n4. Follow the procedure rather than improvising; the gotchas sections exist\n   because those mistakes have already cost someone a day.\n\nPaths (`CARLA_ROOT` and friends) are configured on first need, not up front.\nNever guess a path — several CARLA checkouts on one machine is normal and the\nwrong one fails slowly. Ask the user, then record the answer.\n\n### Optional: MCP server\n\n[`Util/AgenticTools/`](Util/AgenticTools/) serves the same skills over MCP\n(`list_skills`, `read_skill`, `check_prerequisites`, `get_config`,\n`set_config`), which adds environment detection and persistent path config.\nProject config is in [`.mcp.json`](.mcp.json); clients that read it get the\ntools automatically. Agents without MCP should read `Skills/` directly — the\nfiles are the source of truth either way.\n\n## Skill catalogue\n\n### `docs`\n\n- **`audit-carla-docs`** — Finds undocumented and rotting documentation in a CARLA checkout — unreleased features, bindings missing from the API reference, documented API that no longer exists....\n- **`document-carla-feature`** — Writes the missing CARLA documentation that the audit found, one category at a time, in CARLA's house style....\n\n### `leaderboard`\n\n- **`create-leaderboard-route`** — Creates and edits CARLA Leaderboard route files — placing waypoints and scenario trigger points interactively from the spectator camera....\n- **`package-leaderboard-agent`** — Packages an agent for CARLA Leaderboard submission — builds the docker image with make_docker.sh (plain or ROS variant), checks the four required....\n- **`read-leaderboard-results`** — Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the....\n- **`run-leaderboard-evaluation`** — Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selection, checkpoint and....\n- **`write-leaderboard-agent`** — Writes an autonomous agent for the CARLA Leaderboard — an AutonomousAgent subclass with setup/sensors/run_step/destroy, a sensor suite inside the....\n\n### `python-api`\n\n- **`bounding-boxes`** — Gets actor and level 3D bounding boxes and projects them into a camera image as 2D boxes — the dataset-annotation workflow.\n- **`control-lights`** — Controls the map's light sources through the CARLA LightManager — turn street lamps, building/facade lights, vehicle lights or all of them on/off,....\n- **`control-spectator`** — Moves the CARLA spectator camera, frames an actor, or follows one live — third-person/chase, first-person/driver, top-down, or front views,....\n- **`control-traffic`** — Tunes the CARLA Traffic Manager that drives autopilot vehicles — global and per-vehicle speed, following distance, running lights/signs,....\n- **`control-traffic-lights`** — Controls the traffic-light actors on a running CARLA server — set a light green/red/yellow/off, freeze all lights (optionally all-green), set....\n- **`control-vehicle`** — Directly drives a specific vehicle on a running CARLA server — raw VehicleControl (throttle/steer/brake/reverse/hand-brake), Ackermann speed....\n- **`create-sensor`** — Spawns and attaches sensors on a running CARLA server — cameras (rgb/depth/semantic/instance/optical-flow/normals), lidar, radar, IMU, GNSS,....\n- **`debug-draw`** — Draws debug overlays in a running CARLA world via world.debug — points, lines, arrows, bounding boxes, and text strings, each with a colour and....\n- **`debug-navmesh`** — Visualises and validates a map's pedestrian navigation mesh by sampling walkable locations (get_random_location_from_navigation) and drawing them....\n- **`load-map`** — Loads, reloads, and reshapes the map on a running CARLA server via the Python API — get_available_maps, load_world and reload_world (with or....\n- **`map-waypoints`** — Explores a CARLA map's road network through the Map/Waypoint API — a natural-language rundown of the whole map (\"give me the topology\"), drawing....\n- **`navigate-to`** — Drives a vehicle to a destination autonomously using CARLA's navigation agents (BasicAgent/BehaviorAgent/ConstantVelocityAgent), or plans a route....\n- **`query-recording`** — Inspects a recorded CARLA .log without replaying it — show_recorder_file_info for the header/actors/frames, collision queries between actor....\n- **`read-sensor`** — Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the....\n- **`record-simulation`** — Records a running CARLA simulation to a .log file via start_recorder/stop_recorder for later deterministic replay — capturing actor spawns,....\n- **`replay-recording`** — Replays a CARLA .log recorded by the recorder — the whole run or a time window, at any speed, following a chosen actor, optionally regenerating....\n- **`set-weather`** — Reads and sets the weather on a running CARLA server via get_weather/set_weather, and turns natural-language weather requests (\"heavy rain at....\n- **`set-world-settings`** — Reads and changes a running CARLA server's WorldSettings via apply_settings — synchronous vs asynchronous mode, fixed_delta_seconds (fps), physics....\n- **`spawn-vehicles`** — Spawns vehicles on a running CARLA server and destroys them — scattered across the map's spawn points on Traffic Manager autopilot, a row queued....\n- **`spawn-walkers`** — Spawns pedestrians that wander autonomously via WalkerAIController, and destroys them in the correct order.\n- **`telemetry`** — Reads a specific actor's live telemetry from a running CARLA server — location and rotation, velocity and speed, acceleration, angular velocity,....\n- **`toggle-env-objects`** — Lists and toggles a map's static environment objects via get_environment_objects / enable_environment_objects — hide or show buildings,....\n- **`world-data`** — Queries the live CARLA world and resolves an entity description into a concrete actor id — find actors by type, role, or colour, or the single one....\n\n### `ros2`\n\n- **`add-ros-message-type`** — Adds a new ROS 2 message type to CARLA's native ROS 2 interface — the hand-written POD struct under LibCarla/source/carla/ros2/types/msg, its....\n- **`add-ros-publisher`** — Adds a new topic to CARLA's native ROS 2 interface — a publisher (BasePublisher + PublisherImpl, topic suffix, QoS, registration in....\n- **`visualize-ros-rviz`** — Inspects and visualises a ROS-2-enabled CARLA server from Docker containers, with no local ROS 2 install — list/echo/rate-check topics (the \"are....\n\n### `scenario-runner`\n\n- **`analyze-scenario-results`** — Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result....\n- **`create-scenario`** — Writes a new ScenarioRunner scenario — a Python class deriving from BasicScenario with its behaviour tree assembled from srunner atomic behaviours....\n- **`run-openscenario`** — Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs and ParameterDeclaration....\n- **`run-route-scenario`** — Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego — the same mechanism the....\n- **`run-scenario`** — Runs a single ScenarioRunner Python scenario (or a whole group) against a running CARLA server — FollowLeadingVehicle, ControlLoss,....\n\n### `scenic`\n\n- **`create-scenic-scenario`** — Writes a new Scenic scenario (.scenic) from a natural-language description — \"a car cuts in from the right lane\", \"a pedestrian crosses in front....\n- **`run-scenic-scenario`** — Runs Scenic probabilistic scenarios against a running CARLA server with the `scenic FILE --simulate --2d` CLI — the carlaChallenge1-10 traffic....\n\n### `setup`\n\n- **`check-feature-support`** — Answers \"can CARLA do X here, and is there a vetted procedure for it\" before you promise anything, and detects client/server/tree version skew — a....\n- **`download-carla`** — Downloads CARLA so nothing has to be fetched by hand — an official release package for any published version (resolved live from the GitHub....\n- **`install-leaderboard`** — Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact....\n- **`install-python-api`** — Installs the CARLA Python client (the `carla` package) into a chosen interpreter so the other python-api skills work — from a wheel bundled with....\n- **`install-scenario-runner`** — Installs CARLA's ScenarioRunner (the official scenario engine) and picks the branch that matches the CARLA in use — master for 0.9.14-0.9.16....\n- **`install-scenic`** — Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds....\n\n### `ue4`\n\n- **`build-carla-ue4`** — Builds CARLA (branch ue4-dev, Unreal Engine 4.26) from source on Linux end-to-end — UE4 fork, the Carla server (editor C++ modules), the LibCarla....\n- **`import-carla-map`** — Imports a custom RoadRunner map (FBX geometry + XODR OpenDRIVE) into a CARLA source build as a drivable map — reads the map from the directory the....\n- **`import-carla-prop`** — Imports FBX meshes into a CARLA source build as spawnable static.prop.* blueprints — pass a directory whose subdirectories name the semantic tags,....\n- **`import-carla-vehicle`** — Imports an FBX vehicle into a CARLA source build as a spawnable vehicle.<make>.<model> — checks the FBX carries CARLA's 4-wheel bone rig, imports....\n- **`import-carla-walker`** — Imports an FBX pedestrian into a CARLA source build as a spawnable walker.pedestrian.NNNN — checks the FBX is skinned to CARLA's GEN3 rig, imports....\n- **`package-carla-ue4`** — Cooks and packages CarlaUE4 into distributable tarballs under Dist/ — either the full simulator or a standalone asset package of selected maps and....\n- **`run-carla-server`** — Launches a CARLA RPC server a carla.Client can connect to, working out for itself what you pointed it at — a downloaded/extracted release, a....\n\n### `ue5`\n\n- **`check-ue5-limitations`** — Tells you what CARLA on UE 5.5 (branch ue5-dev) cannot do that UE 5.8 (ue58-dev) can, so you do not attempt an unsupported workflow there — no....\n\n### `ue58`\n\n- **`build-carla-ue58`** — Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal /....\n- **`carla-vehicle-authoring`** — Create, migrate, improve, or debug detailed vehicle assets for CARLA using Blender and Unreal, including reference-based geometry, materials,....\n- **`import-carla-ue58-map`** — Gets a custom map into CARLA on UE 5.8 — the four distinct routes and which one to pick — via Util/Tools/Import.py for FBX+OpenDRIVE assets into a....\n- **`import-carla-ue58-prop`** — Imports FBX meshes into CARLA on UE 5.8 as spawnable props — drives the editor headlessly to import the mesh, derives the prop size from its....\n- **`import-carla-ue58-walker`** — Imports a pedestrian into CARLA on UE 5.8 as a spawnable, animating walker — imports the skinned FBX bound to CARLA's shared pedestrian skeleton,....\n- **`package-carla-ue58`** — Cooks and packages a shippable CARLA server from a UE 5.8 ue58-dev checkout via the CMake `package` targets (shipping/development/debug/test),....\n- **`run-autoware-ue58`** — Runs the Autoware autonomous-driving stack against CARLA on UE 5.8 over CARLA's native ROS 2 interface — no bridge process.\n- **`run-carla-ue58-server`** — Starts a CARLA UE 5.8 server from a ue58-dev tree — the editor binary in -game mode (the working headless server), the packaged shipping build, or....\n\n## Repository conventions\n\n- `LibCarla/` — the C++ client/server library. `PythonAPI/` — bindings, docs\n  (`PythonAPI/docs/*.yml`) and examples.\n- `Docs/python_api.md` is **generated** from `PythonAPI/docs/*.yml` by\n  `PythonAPI/docs/doc_gen.py`. Never edit it directly; edit the YAML and\n  regenerate.\n- Smoke tests live in `PythonAPI/test/smoke/` and need a running server on\n  port 3654.\n- Add a `CHANGELOG.md` entry under `## LATEST Changes` for user-visible changes.\n","isInternal":false,"tokens":3227,"sizeBytes":13330},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/marketplace.json","title":"Claude Plugin Marketplace Catalog","category":"marketplace","format":"json","content":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":200},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/plugin.json","title":"claude-plugin Plugin Manifest","category":"plugin-manifest","format":"json","content":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":186},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.cursor/mcp.json","title":"Model Context Protocol (MCP) Configuration","category":"mcp-config","format":"json","content":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":179}],"systemPromptSnippet":"<yakaai_skills repo=\"carla-simulator/carla\">\n<!-- File: AGENTS.md (Tokens: ~3227 | Category: root-instruction) -->\n# AGENTS.md\n\nGuidance for any coding agent working in this repository.\n\n## Skills\n\nThis repo ships a library of **62 vetted CARLA procedures** under\n[`Skills/`](Skills/). Each is a directory containing a `SKILL.md` with YAML\nfrontmatter (`name`, `description`, `compatibility`, `metadata`), the step-by-step\nprocedure, and often `scripts/` and `references/` beside it.\n\n**These skills are the source of truth** for building, packaging, cooking,\nmap/vehicle/asset import, running servers, scenarios and ROS 2, and they cover\nmost of the commands those tasks need.\n\n### How to use them\n\n1. Match the user's request against the catalogue below.\n2. Read that skill's `SKILL.md` in full before acting — each encodes the\n   failure modes that make the naive approach fail.\n3. Run its `scripts/check_env.sh` (when `metadata.prerequisites` names one)\n   before starting.\n4. Follow the procedure rather than improvising; the gotchas sections exist\n   because those mistakes have already cost someone a day.\n\nPaths (`CARLA_ROOT` and friends) are configured on first need, not up front.\nNever guess a path — several CARLA checkouts on one machine is normal and the\nwrong one fails slowly. Ask the user, then record the answer.\n\n### Optional: MCP server\n\n[`Util/AgenticTools/`](Util/AgenticTools/) serves the same skills over MCP\n(`list_skills`, `read_skill`, `check_prerequisites`, `get_config`,\n`set_config`), which adds environment detection and persistent path config.\nProject config is in [`.mcp.json`](.mcp.json); clients that read it get the\ntools automatically. Agents without MCP should read `Skills/` directly — the\nfiles are the source of truth either way.\n\n## Skill catalogue\n\n### `docs`\n\n- **`audit-carla-docs`** — Finds undocumented and rotting documentation in a CARLA checkout — unreleased features, bindings missing from the API reference, documented API that no longer exists....\n- **`document-carla-feature`** — Writes the missing CARLA documentation that the audit found, one category at a time, in CARLA's house style....\n\n### `leaderboard`\n\n- **`create-leaderboard-route`** — Creates and edits CARLA Leaderboard route files — placing waypoints and scenario trigger points interactively from the spectator camera....\n- **`package-leaderboard-agent`** — Packages an agent for CARLA Leaderboard submission — builds the docker image with make_docker.sh (plain or ROS variant), checks the four required....\n- **`read-leaderboard-results`** — Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the....\n- **`run-leaderboard-evaluation`** — Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selection, checkpoint and....\n- **`write-leaderboard-agent`** — Writes an autonomous agent for the CARLA Leaderboard — an AutonomousAgent subclass with setup/sensors/run_step/destroy, a sensor suite inside the....\n\n### `python-api`\n\n- **`bounding-boxes`** — Gets actor and level 3D bounding boxes and projects them into a camera image as 2D boxes — the dataset-annotation workflow.\n- **`control-lights`** — Controls the map's light sources through the CARLA LightManager — turn street lamps, building/facade lights, vehicle lights or all of them on/off,....\n- **`control-spectator`** — Moves the CARLA spectator camera, frames an actor, or follows one live — third-person/chase, first-person/driver, top-down, or front views,....\n- **`control-traffic`** — Tunes the CARLA Traffic Manager that drives autopilot vehicles — global and per-vehicle speed, following distance, running lights/signs,....\n- **`control-traffic-lights`** — Controls the traffic-light actors on a running CARLA server — set a light green/red/yellow/off, freeze all lights (optionally all-green), set....\n- **`control-vehicle`** — Directly drives a specific vehicle on a running CARLA server — raw VehicleControl (throttle/steer/brake/reverse/hand-brake), Ackermann speed....\n- **`create-sensor`** — Spawns and attaches sensors on a running CARLA server — cameras (rgb/depth/semantic/instance/optical-flow/normals), lidar, radar, IMU, GNSS,....\n- **`debug-draw`** — Draws debug overlays in a running CARLA world via world.debug — points, lines, arrows, bounding boxes, and text strings, each with a colour and....\n- **`debug-navmesh`** — Visualises and validates a map's pedestrian navigation mesh by sampling walkable locations (get_random_location_from_navigation) and drawing them....\n- **`load-map`** — Loads, reloads, and reshapes the map on a running CARLA server via the Python API — get_available_maps, load_world and reload_world (with or....\n- **`map-waypoints`** — Explores a CARLA map's road network through the Map/Waypoint API — a natural-language rundown of the whole map (\"give me the topology\"), drawing....\n- **`navigate-to`** — Drives a vehicle to a destination autonomously using CARLA's navigation agents (BasicAgent/BehaviorAgent/ConstantVelocityAgent), or plans a route....\n- **`query-recording`** — Inspects a recorded CARLA .log without replaying it — show_recorder_file_info for the header/actors/frames, collision queries between actor....\n- **`read-sensor`** — Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the....\n- **`record-simulation`** — Records a running CARLA simulation to a .log file via start_recorder/stop_recorder for later deterministic replay — capturing actor spawns,....\n- **`replay-recording`** — Replays a CARLA .log recorded by the recorder — the whole run or a time window, at any speed, following a chosen actor, optionally regenerating....\n- **`set-weather`** — Reads and sets the weather on a running CARLA server via get_weather/set_weather, and turns natural-language weather requests (\"heavy rain at....\n- **`set-world-settings`** — Reads and changes a running CARLA server's WorldSettings via apply_settings — synchronous vs asynchronous mode, fixed_delta_seconds (fps), physics....\n- **`spawn-vehicles`** — Spawns vehicles on a running CARLA server and destroys them — scattered across the map's spawn points on Traffic Manager autopilot, a row queued....\n- **`spawn-walkers`** — Spawns pedestrians that wander autonomously via WalkerAIController, and destroys them in the correct order.\n- **`telemetry`** — Reads a specific actor's live telemetry from a running CARLA server — location and rotation, velocity and speed, acceleration, angular velocity,....\n- **`toggle-env-objects`** — Lists and toggles a map's static environment objects via get_environment_objects / enable_environment_objects — hide or show buildings,....\n- **`world-data`** — Queries the live CARLA world and resolves an entity description into a concrete actor id — find actors by type, role, or colour, or the single one....\n\n### `ros2`\n\n- **`add-ros-message-type`** — Adds a new ROS 2 message type to CARLA's native ROS 2 interface — the hand-written POD struct under LibCarla/source/carla/ros2/types/msg, its....\n- **`add-ros-publisher`** — Adds a new topic to CARLA's native ROS 2 interface — a publisher (BasePublisher + PublisherImpl, topic suffix, QoS, registration in....\n- **`visualize-ros-rviz`** — Inspects and visualises a ROS-2-enabled CARLA server from Docker containers, with no local ROS 2 install — list/echo/rate-check topics (the \"are....\n\n### `scenario-runner`\n\n- **`analyze-scenario-results`** — Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result....\n- **`create-scenario`** — Writes a new ScenarioRunner scenario — a Python class deriving from BasicScenario with its behaviour tree assembled from srunner atomic behaviours....\n- **`run-openscenario`** — Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs and ParameterDeclaration....\n- **`run-route-scenario`** — Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego — the same mechanism the....\n- **`run-scenario`** — Runs a single ScenarioRunner Python scenario (or a whole group) against a running CARLA server — FollowLeadingVehicle, ControlLoss,....\n\n### `scenic`\n\n- **`create-scenic-scenario`** — Writes a new Scenic scenario (.scenic) from a natural-language description — \"a car cuts in from the right lane\", \"a pedestrian crosses in front....\n- **`run-scenic-scenario`** — Runs Scenic probabilistic scenarios against a running CARLA server with the `scenic FILE --simulate --2d` CLI — the carlaChallenge1-10 traffic....\n\n### `setup`\n\n- **`check-feature-support`** — Answers \"can CARLA do X here, and is there a vetted procedure for it\" before you promise anything, and detects client/server/tree version skew — a....\n- **`download-carla`** — Downloads CARLA so nothing has to be fetched by hand — an official release package for any published version (resolved live from the GitHub....\n- **`install-leaderboard`** — Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact....\n- **`install-python-api`** — Installs the CARLA Python client (the `carla` package) into a chosen interpreter so the other python-api skills work — from a wheel bundled with....\n- **`install-scenario-runner`** — Installs CARLA's ScenarioRunner (the official scenario engine) and picks the branch that matches the CARLA in use — master for 0.9.14-0.9.16....\n- **`install-scenic`** — Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds....\n\n### `ue4`\n\n- **`build-carla-ue4`** — Builds CARLA (branch ue4-dev, Unreal Engine 4.26) from source on Linux end-to-end — UE4 fork, the Carla server (editor C++ modules), the LibCarla....\n- **`import-carla-map`** — Imports a custom RoadRunner map (FBX geometry + XODR OpenDRIVE) into a CARLA source build as a drivable map — reads the map from the directory the....\n- **`import-carla-prop`** — Imports FBX meshes into a CARLA source build as spawnable static.prop.* blueprints — pass a directory whose subdirectories name the semantic tags,....\n- **`import-carla-vehicle`** — Imports an FBX vehicle into a CARLA source build as a spawnable vehicle.<make>.<model> — checks the FBX carries CARLA's 4-wheel bone rig, imports....\n- **`import-carla-walker`** — Imports an FBX pedestrian into a CARLA source build as a spawnable walker.pedestrian.NNNN — checks the FBX is skinned to CARLA's GEN3 rig, imports....\n- **`package-carla-ue4`** — Cooks and packages CarlaUE4 into distributable tarballs under Dist/ — either the full simulator or a standalone asset package of selected maps and....\n- **`run-carla-server`** — Launches a CARLA RPC server a carla.Client can connect to, working out for itself what you pointed it at — a downloaded/extracted release, a....\n\n### `ue5`\n\n- **`check-ue5-limitations`** — Tells you what CARLA on UE 5.5 (branch ue5-dev) cannot do that UE 5.8 (ue58-dev) can, so you do not attempt an unsupported workflow there — no....\n\n### `ue58`\n\n- **`build-carla-ue58`** — Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal /....\n- **`carla-vehicle-authoring`** — Create, migrate, improve, or debug detailed vehicle assets for CARLA using Blender and Unreal, including reference-based geometry, materials,....\n- **`import-carla-ue58-map`** — Gets a custom map into CARLA on UE 5.8 — the four distinct routes and which one to pick — via Util/Tools/Import.py for FBX+OpenDRIVE assets into a....\n- **`import-carla-ue58-prop`** — Imports FBX meshes into CARLA on UE 5.8 as spawnable props — drives the editor headlessly to import the mesh, derives the prop size from its....\n- **`import-carla-ue58-walker`** — Imports a pedestrian into CARLA on UE 5.8 as a spawnable, animating walker — imports the skinned FBX bound to CARLA's shared pedestrian skeleton,....\n- **`package-carla-ue58`** — Cooks and packages a shippable CARLA server from a UE 5.8 ue58-dev checkout via the CMake `package` targets (shipping/development/debug/test),....\n- **`run-autoware-ue58`** — Runs the Autoware autonomous-driving stack against CARLA on UE 5.8 over CARLA's native ROS 2 interface — no bridge process.\n- **`run-carla-ue58-server`** — Starts a CARLA UE 5.8 server from a ue58-dev tree — the editor binary in -game mode (the working headless server), the packaged shipping build, or....\n\n## Repository conventions\n\n- `LibCarla/` — the C++ client/server library. `PythonAPI/` — bindings, docs\n  (`PythonAPI/docs/*.yml`) and examples.\n- `Docs/python_api.md` is **generated** from `PythonAPI/docs/*.yml` by\n  `PythonAPI/docs/doc_gen.py`. Never edit it directly; edit the YAML and\n  regenerate.\n- Smoke tests live in `PythonAPI/test/smoke/` and need a running server on\n  port 3654.\n- Add a `CHANGELOG.md` entry under `## LATEST Changes` for user-visible changes.\n\n<!-- File: .claude-plugin/marketplace.json (Tokens: ~300 | Category: marketplace) -->\n# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/marketplace.json)\n\n<!-- File: .claude-plugin/plugin.json (Tokens: ~300 | Category: plugin-manifest) -->\n# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.claude-plugin/plugin.json)\n\n<!-- File: .cursor/mcp.json (Tokens: ~300 | Category: mcp-config) -->\n# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/carla-simulator/carla/HEAD/.cursor/mcp.json)\n</yakaai_skills>"}