개발 스킬

List static objects built into a CARLA map and hide or restore them by category or asset name. Adjust buildings, vegetation, fences, and other scenery, preview affected objects, and change both their visibility and collision behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Hide buildings to inspect a scene
• Remove trees and bushes for dataset capture
• Preview which fences a change would affect

Check whether a CARLA feature is usable in the current environment and has a verified procedure. Review known failures, inspect build settings, and identify differences between client, server, and source versions before planning work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether a CARLA feature has a verified procedure
• Review known failures before following a UE4 tutorial
• Inspect build flags for ROS 2 or RSS support

Builds CARLA's ue4-dev branch on Linux, producing the Unreal Engine 4.26 editor, server modules, and an installed Python client package. Fetches required content, optionally compiles native ROS 2 support, and verifies the build against a source-built server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building CARLA ue4-dev from source
• Compiling CARLA with native ROS 2 support
• Building the Python client for an existing environment

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

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

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

Places cameras, lidar, and other sensors in a running CARLA world, attached to vehicles or fixed in place. Configures mounting positions and sensor attributes, enables supported ROS 2 data publishing, and reports sensor IDs for later data reading.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mounting a dashcam on the ego vehicle
• Preparing a lidar for point cloud capture
• Adding GNSS or collision sensors

Adjust how autopilot vehicles behave in CARLA, including speed, following distance, traffic light responses, and lane changes. Apply settings across traffic or to individual vehicles, and configure seeds and synchronization for repeatable traffic runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adjust traffic speed and following distance
• Create traffic that ignores lights or other vehicles
• Change lane behavior for an individual autopilot vehicle

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

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

Import an FBX character into a CARLA source build as a pedestrian available through the Python API. Check its GEN3 skeleton, create assets and a walker blueprint, register it, and verify spawning, ground placement, and movement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a custom FBX character as a CARLA pedestrian
• Check whether an FBX uses the required GEN3 skeleton
• Investigate floating or motionless imported pedestrians

Drives a CARLA vehicle to a specific destination using navigation agents that plan routes, avoid obstacles, and obey traffic lights. Can also plan and draw a route between two points without moving the vehicle.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Driving a vehicle to specified coordinates
• Navigating to a chosen junction
• Planning and drawing a route without driving

Extend CARLA’s native ROS 2 interface to publish sensor data or receive vehicle commands. Covers topic implementation, registration, data connections, and verification, plus adding middleware, the communication layer used to exchange messages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish obstacle sensor data to ROS 2
• Add a topic for vehicle speed commands
• Integrate another communication middleware

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

Read and change a running CARLA server’s timing, physics substeps, and rendering settings. Switch between client-controlled steps and automatic progression, keep Traffic Manager synchronization aligned, and read back the settings to verify each change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting a fixed simulation rate for sensor capture
• Keeping Traffic Manager aligned with synchronous mode
• Disabling rendering or adjusting physics substeps

Organize React and TypeScript frontend code using consistent rules for feature folders, shared components, types, API access, and tests. Use it to guide new code, focused refactoring, and reviews of existing changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a frontend feature with consistent file organization
• Reviewing shared components and type placement
• Refactoring imports and module exports

Structure TypeScript backend features with clear module boundaries, shared definitions, and focused tests. It guides implementation and reviews while keeping request handling in routes and business logic in services.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a backend feature with consistent module organization
• Separating request handling from business logic
• Reviewing shared types and utilities

Extend and audit TVM's T.ptx instruction table for GPU code generation. It guides instruction definitions, checks generated assembly with CUDA tools, and aligns comments and supported forms with a chosen PTX specification version.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding PTX instructions or qualifiers to T.ptx
• Extending supported operand types
• Investigating ptxas certification failures

Launch and troubleshoot the actual AO desktop app to inspect interface changes with local data. Supports reviewing combined pull request branches and diagnosing lingering Electron processes, port conflicts, and mismatches in the app’s preload bridge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect interface changes in the actual AO desktop app
• Test with isolated or existing local AO data
• Review multiple pull request branches together

Calculates added and deleted lines for a pull request and maintains a three-line summary for implementation, tests, and other files. Preserves existing description text and checks the published counts against the current diff.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add change counts to a new pull request
• Refresh counts after the final push
• Classify tests and generated files

Coordinate AO Cloud work sessions through the ao command line. Create and monitor workers, exchange messages, attach pull requests, start reviews, and operate the visible browser using the commands available to each session’s role.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create worker sessions and check their progress
• Send instructions to workers and report results
• Attach a pull request and start an AO review

Build, test, and format CubeSandbox components using make targets and a Docker builder. Also covers the web dashboard’s development workflow, API type synchronization, and troubleshooting for missing services, outdated build tools, and environment requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build all components or a specific CubeSandbox component
• Run component tests or a single targeted test
• Format Go and Rust code and lint the web interface

Set up portless to give local development servers stable, named URLs instead of changing port numbers. It covers multiple apps, separate Git worktree URLs, HTTPS setup, and checks for proxy, domain resolution, and certificate problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Giving local development apps stable, named URLs
• Running multiple services in a monorepo
• Keeping Git worktrees on separate URLs

Configure OAuth, the authorization flow used for provider sign-in, with portless development URLs. It guides callback registration and authentication library settings, helping diagnose rejected domains, redirect URL mismatches, and callbacks that point to the wrong address.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up provider sign-in with portless development URLs
• Diagnosing redirect URL mismatch errors
• Using an owned domain when .localhost is rejected