Production-grade robotics knowledge for AI coding agents to generate better ROS1/ROS2 software.
robotics-agent-skills is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add arpitg1304/robotics-agent-skillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This repository provides skill files that teach AI coding assistants how to write professional robotics software. It covers ROS1, ROS2, design patterns, testing, and security, helping agents generate safer and more reliable code.
Robotics Agent Skills is a collection of SKILL.md files designed to enhance AI coding agents like Claude Code, Cursor, and Copilot with deep robotics engineering knowledge. The skills cover ROS1 and ROS2 development, software design principles (SOLID, fail-safe defaults), architecture patterns (behavior trees, FSMs), perception systems, testing strategies, Docker integration, and security best practices. By loading these skills, agents produce code that respects QoS compatibility, lifecycle management, bounded callbacks, sensor health checks, and proper shutdown procedures. The repository includes an evaluation directory showing significant improvements in code quality when skills are used, such as moving from plain nodes to lifecycle nodes, adding sensor QoS, implementing thread-safe buffers, and generating hundreds of test lines. The skills are modular and can be installed individually or in recommended bundles for different robotics applications.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 12 days ago.
262 GitHub stars indicate community interest.
2 open issues signal maintenance load.
Apache-2.0 license detected.
Improve code quality of AI-generated ROS2 nodes with lifecycle management and proper QoS
Add comprehensive testing to robotics projects using pytest and launch_testing
Implement secure robot bringup with Docker and DDS configuration
Design perception pipelines with camera, LiDAR, and sensor fusion patterns
Migrate ROS1 code to ROS2 with correct patterns and compatibility
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Skills may generate code that requires manual review for safety-critical systems
Dependency on third-party AI agents may introduce unpredictable behavior
262
Stars
38
Forks
2
Issues
Apache-2.0
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
4 security/trust notes recorded.
Setup difficulty is 2/5.
Browser automation CLI built for AI agents — breaks anti-bot walls, supports multi-session parallel execution.