arpitg1304/robotics-agent-skills

Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.

What it solves

General-purpose AI coding agents often lack the deep domain expertise required for production-grade robotics software. While they may know basic ROS syntax, they frequently overlook critical engineering details such as Quality of Service (QoS) compatibility, deterministic startup, thread-safe buffers, and safe shutdown procedures, leading to fragile or unsafe code.

How it works

The project provides a collection of SKILL.md files—structured knowledge modules—that can be integrated into AI agents (like Claude Code, Cursor, or custom frameworks). These files act as specialized context that guides the agent to follow robotics best practices. When an agent loads a skill, it shifts from generating generic code to implementing production patterns, such as using lifecycle nodes instead of plain nodes or implementing bounded buffers for sensor data.

Who it’s for

Robotics engineers and developers who use AI coding assistants to write ROS1 or ROS2 software and want to ensure the generated code meets production standards for safety, reliability, and maintainability.

Highlights

  • Comprehensive Domain Coverage: Includes skills for ROS1/ROS2 development, perception systems, system bringup, security (SROS2), and Docker containerization.
  • Production-Focused: Emphasizes real-world failure modes, anti-patterns, and safety-critical defaults over simple tutorials.
  • Agent-Agnostic: Compatible with various tools including Claude Code, Autohand Code, and custom Python-based agent frameworks.
  • Coded Examples: Provides working examples and specific trigger descriptions to help agents identify when to apply a particular skill.

Related

  • Project
    davidondrej/skills

    A collection of reusable skill modules and instructions that AI agents can load to execute specific workflows like research, coding orchestration, and system operations.

  • Project
    Masriyan/Claude-Code-CyberSecurity-Skill

    A collection of 20 Claude Code “skills” that embed cybersecurity methodologies (recon, vulnerability scanning, exploit dev, reverse engineering, threat hunting, AI‑LLM security, etc.) into Anthropic’s Claude Code assistant. Install the `skills/*` directories into `~/.claude/skills/` (or project‑local) and Claude will automatically activate the appropriate workflow when you ask a matching prompt, returning ready‑to‑run commands, reports, detection rules, or code. MIT‑licensed, Python‑based helpers, optional external tools (nmap, YARA, Ghidra, etc.), and built‑in safety gates for offensive actions.

  • Project
    mxyhi/ok-skills

    A curated collection of reusable skills and playbooks for AI coding agents like Claude Code and Cursor, providing structured workflows for tasks like browser automation and codebase planning.

  • Project
    Kotlin/kotlin-agent-skills

    A collection of standardized AI agent skills that provide specialized instructions and resources to help AI coding agents perform Kotlin-specific development tasks.

  • Project
    KKKKhazix/khazix-skills

    A collection of standardized AI agent skills (instruction sets) for goal definition, disk cleanup, deep research, and project documentation maintenance.