ajaygunalan

Ros2 Engineering Skills — Productivity skill for Claude Code

Productivity community

Agent skill for production-grade ROS 2 development.

How to install Ros2 Engineering Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ajaygunalan/ros2-engineering-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Ros2 Engineering Skills does

Agent skill for production-grade ROS 2 development. Progressive-disclosure SKILL.md covering workspace, nodes, executors, QoS, ros2_control, Nav2, MoveIt 2, real-time, and deployment. Works with Claude Code, Codex, Cursor, Gemini CLI.

Alternatives in Productivity

  • Swarm Worker — You are a swarm worker agent for the {{tentacleName}} tentacle 1.4k ★
  • Build In Public — Build-in-Public — generate posts from your engineering work, anonymize, and schedule via Buffer 705 ★
  • MathModel Skill — Agent-native mathematical modeling workflow skills for Trae, Claude Code, and Codex, covering problem parsing 345 ★

README

ros2-engineering-skills

[![Test](https://github.com/dbwls99706/ros2-engineering-skills/actions/workflows/test.yml/badge.svg)](https://github.com/dbwls99706/ros2-engineering-skills/actions/workflows/test.yml) [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE) [![GitHub stars](https://img.shields.io/github/stars/dbwls99706/ros2-engineering-skills?style=social)](https://github.com/dbwls99706/ros2-engineering-skills/stargazers)

Production-grade ROS 2 engineering guidance for coding agents, with focused reference documents, static validators, regression tests, and a multi-distribution ROS 2 CI matrix.

The project is intended for work that crosses ROS 2 layers: package and launch structure, executors and callback groups, DDS QoS, lifecycle, tf2, ros2_control, Nav2, MoveIt 2, perception, hardware safety, runtime provenance, testing, and deployment.

Why this exists

A syntactically correct ROS 2 answer can still be operationally wrong. Common examples include:

  • changing subscriber QoS without first inspecting the live publisher;
  • editing a YAML file in src/ while the process loads another installed copy;
  • treating a zero command on a topic as proof that the driver and hardware stopped;
  • generating APIs for a different ROS 2 distribution or package version;
  • reporting static checks as if they were hardware validation.

This skill makes those evidence boundaries explicit and routes each task to the smallest relevant reference document.

Before / After

**Prompt:** *"My ROS 2 subscriber isn't receiving any sensor messages. Help me fix it."*

Without this skill With this skill loaded
# Guess at the fix before inspecting the live endpoints.
from rclpy.qos import qos_profile_sensor_data

sub = node.create_subscription(
    Image, '/camera/image_raw',
    callback, qos_profile_sensor_data)

May work by accident, but assumes the publisher exist