개발 스킬

Prepare a pull request to contribute local qm changes back to the shared project. Builds a clean contribution branch and checks commit history, files, authorship, and review materials for private organizational details before submission.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Contribute a local qm bug fix to the shared project
• Check outgoing commit history for private details
• Prepare a clean contribution branch from a private fork

Index reference libraries locally with XERJ and retrieve relevant implementations before coding. Use the retrieved source to understand unfamiliar API behavior, port algorithms, or investigate errors that repeated attempts have not resolved.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking how an unfamiliar API behaves
• Porting an algorithm from a reference implementation
• Investigating errors after repeated failed attempts

Find the development workflow for updating the Playwright dependency or preparing a playwright-cli release. This skill points the agent to a separate guide for each task, providing an entry point for these two maintenance activities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Updating the Playwright dependency
• Preparing a playwright-cli release
• Finding the guide for a maintenance task

Prepare and launch Autoware with CARLA on UE 5.8 through its native ROS 2 interface. Check communication topics and sensors, generate required maps, and configure either the classical stack or camera-only VAD model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether a CARLA build supports Autoware
• Inspect topics exchanged between CARLA and Autoware
• Generate lanelet2 and point-cloud maps for a town

Import a custom pedestrian into CARLA on UE 5.8, connect it to the shared animation skeleton, and verify that it moves. Export an existing walker as an FBX starting point or investigate a walker that stands still.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a custom pedestrian to CARLA
• Export an existing walker as an FBX for editing
• Investigate a walker that spawns but does not move

Import FBX 3D models into CARLA on UE 5.8 and register them as props that can be placed in a simulation. Check measured dimensions, adjust scale, verify placement on a running server, and undo imports when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a custom bench or object to CARLA
• Fix imported props missing from the blueprint library
• Import a folder of props organized by tag

Guides custom map imports into CARLA on UE 5.8, from FBX geometry and OpenDRIVE road data to packaging or temporary road generation. Helps choose a supported route and verify map files and loading.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing a road network from an OpenDRIVE file
• Importing a town with buildings into the editor
• Including a custom map in a server package

Build CARLA for Unreal Engine 5.8 using CMake, the tool that configures its build process. The skill guides engine setup, optional ROS 2 support, Python API rebuilding, editor builds, and checks that the expected files were actually produced.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building CARLA for Unreal Engine 5.8
• Building and verifying native ROS 2 support
• Rebuilding the Python API after client changes

Inspect a vehicle or another object in a running CARLA simulation. Read position, speed, and acceleration from the same simulation frame, check vehicle controls and steering angle, or stream the object's state over time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking the ego vehicle's speed and heading
• Streaming acceleration data for ten seconds
• Inspecting a specific vehicle's controls

Explore roads, lanes, and junctions in a CARLA simulation map through text reports and visual overlays. Locate places described in everyday language, inspect nearby lane details, and trace a path forward or backward along a lane.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understand a map's road and lane layout
• Compare the road network overlay with visible roads
• Locate the four-way junction nearest the map center

Create and edit CARLA driving routes by placing waypoints and scenario triggers in the simulator. Inspect routes visually, review summary tables, check XML structure and trigger positions, and convert older route files to the 2.x format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a short route for testing one scenario
• Investigate scenarios that never trigger
• Review route lengths and scenario types

Inspect data published by a ROS 2-enabled CARLA server using Docker, without installing ROS 2 locally. Check topic contents and rates, run a sensor-equipped vehicle demo, and view lidar data and supported map markers in RViz2.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether CARLA is publishing ROS 2 data
• Inspecting sensor data contents and publishing rates
• Viewing lidar data and road markers in RViz2

Import a four-wheel FBX vehicle into a CARLA source build, configure its physics, wheels, and animation, and register it for the Python API. Verify that the resulting vehicle can spawn, drive, and steer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Importing a custom van or truck into CARLA
• Registering a vehicle for spawning through the Python API
• Checking why an imported vehicle will not drive or steer

Control CARLA’s on-screen camera to view a vehicle from behind, above, the driver’s seat, or the front. Select vehicles by name, role, or ID, frame them once, or follow them as they move.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Following the ego vehicle from behind
• Viewing a Toyota Prius from the driver’s seat
• Watching a vehicle from above

Install the CARLA Python client into a chosen Python environment using bundled packages or PyPI. The skill checks existing installations, selects a suitable package, and verifies imports and version compatibility with a reachable simulator.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up the Python client for a downloaded CARLA release
• Install a client for a remote simulator
• Resolve a cannot import carla error

Record a running CARLA simulation to a .log file for later replay or inspection. Capture object creation, movement, and traffic-light states, optionally include controls and velocities, and verify that the recording contains simulation frames.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording thirty seconds of simulated traffic
• Saving a scenario while it runs
• Capturing vehicle velocities and controls

Control street, building, and vehicle light sources in CARLA. Switch groups on or off, adjust their color and brightness, and enable automatic nighttime lighting to prepare illuminated city scenes or blackouts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an illuminated nighttime city
• Adjusting streetlight colors and brightness
• Creating a citywide blackout

Creates a Python agent skeleton for CARLA Leaderboard and checks its sensor configuration offline against the installed version’s rules. Covers version-specific initialization, driving logic, and ROS1 or ROS2 agent integration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an agent with a front camera and lidar
• Checking sensor limits and configuration errors
• Porting a Leaderboard 1.0 agent to 2.1

Install Scenic, a language for describing scenarios with randomized conditions, into the Python environment used by CARLA. Check command-line tools and version compatibility, optionally download example scenarios and map assets, and save the installation paths.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing Scenic to work with CARLA
• Diagnosing scenario model import failures
• Checking missing vehicle definition tables

Inspect a running CARLA simulation and identify vehicles or pedestrians by type, role, color, or proximity. Retrieve their IDs, scene snapshots, static object bounds, ground positions, and expected ROS 2 topics with reasons for missing publications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find the red Prius and retrieve its actor ID
• Identify the pedestrian nearest the ego vehicle
• Inspect scene state and ground height

Import RoadRunner geometry and road data into a CARLA source build, then verify the map loads and supports driving. Handle tiled maps and generate and inspect pedestrian navigation areas for standard maps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Importing a custom RoadRunner map into CARLA
• Importing a large city split into tiles
• Rebuilding navigation areas for missing pedestrians

Add a message type to CARLA's native ROS 2 interface. Create its C++ data structure, serialization code for transmission, type identity hash, registration, and tests, with Docker-based hash calculation and build checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a standard ROS 2 message type missing from CARLA
• Defining a custom carla_msgs message
• Investigating type-hash warnings

Draws points, lines, arrows, boxes, and text over a running CARLA world to visually check positions, paths, and objects. Sets colors and display lifetimes for temporary debugging overlays, without creating persistent actors or output files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Marking a world position for inspection
• Visualizing paths and waypoints
• Adding a box and label around a target

Add pedestrians to a CARLA map and let them walk autonomously. Adjust crowd size, walking speed, road-crossing frequency, and placement seeds, create stationary crowds, and remove pedestrians together with their movement controllers in the correct order.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding pedestrians who walk around a map
• Reusing pedestrian placement with a fixed seed
• Adjusting walking speeds and road crossings