Ros2 Robotics

What it does

When your agent uses it

• Creating ROS 2 packages
• Writing nodes in rclpy
• Defining custom messages/services/actions
• Writing launch files

Example prompts

• “/ros2-robotics”

Requirements

• Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Scaffold the package — Run ros2 pkg create --build-type ament_python (Python) or --build-type ament_cmake (C++) inside a colcon…
2. 2Define interfaces — Add custom .msg, .srv, or .action files under msg/, srv/, action/ only when a standard interface (std_msgs…
3. 3Implement nodes — Write focused, composable nodes; declare parameters explicitly; choose topics for streams, services for quick…
4. 4Write launch files — Compose nodes, parameters, and remappings in a launch/*.launch.py file using launch_ros.actions.Node.
5. 5Set QoS profiles intentionally — Match publisher/subscriber QoS (reliability, durability, history depth) for sensor data vs…
6. 6Build the workspace — Run colcon build --symlink-install from the workspace root, then source install/setup.bash.
7. 7Test — Add unit tests (pytest for Python, gtest/launch_testing for C++/integration) and run colcon test.
8. 8Run and inspect — Use ros2 run, ros2 launch, ros2 topic echo, ros2 node info, and ros2 doctor to verify runtime behavior.

What it can do on your machine

Read from SKILL.md and the folder at commit 7682ca7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ros2 Robotics loads about 2k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 739 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~100

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Mindrally/skills at commit 7682ca7, republished under its Apache-2.0 licence (© Mindrally). 739 words, ~2,021 tokens.

name

ros2-robotics

description

Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles, working with tf2 transforms, or building and testing a colcon workspace.

metadata.maintainer

Mindrally

metadata.source

https://github.com/Mindrally/skills

import rclpy
from rclpy.node import Node
from rclpy.qos import QoSProfile, ReliabilityPolicy, HistoryPolicy
from geometry_msgs.msg import Twist


class SafeVelocityPublisher(Node):
    """Publishes bounded velocity commands at a fixed rate."""

    def __init__(self) -> None:
        super().__init__("safe_velocity_publisher")

        self.declare_parameter("rate_hz", 10.0)
        self.declare_parameter("max_linear_speed", 0.5)
        rate_hz = self.get_parameter("rate_hz").value
        self._max_linear = self.get_parameter("max_linear_speed").value

        # Reliable QoS for a low-rate command topic; sensor streams would
        # typically use BEST_EFFORT with a shallow history instead.
        qos = QoSProfile(
            reliability=ReliabilityPolicy.RELIABLE,
            history=HistoryPolicy.KEEP_LAST,
            depth=10,
        )
        self._publisher = self.create_publisher(Twist, "cmd_vel", qos)
        self._timer = self.create_timer(1.0 / rate_hz, self._on_timer)
        self._target_linear = 0.0

    def _on_timer(self) -> None:
        msg = Twist()
        msg.linear.x = max(-self._max_linear, min(self._max_linear, self._target_linear))
        self._publisher.publish(msg)


def main(args: list | None = None) -> None:
    rclpy.init(args=args)
    node = SafeVelocityPublisher()
    try:
        rclpy.spin(node)
    except KeyboardInterrupt:
        pass
    finally:
        node.destroy_node()
        rclpy.shutdown()


if __name__ == "__main__":
    main()

© Mindrally, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ros2-robotics of Mindrally/skills.

Open the folder on GitHubat commit 7682ca7