ros2-engineering-skills

Name: ros2-engineering-skills
Author: dbwls99706

50installs13forks

How to install ros2-engineering-skills?

dbwls99706/ros2-engineering-skills/ros2-engineering-skills

$npx -y skills add dbwls99706/ros2-engineering-skills --skill ros2-engineering-skills

Installs into the current project.

Summary

TRIGGER when the user: writes or reviews ROS 2 nodes (rclcpp/rclpy), creates packages (colcon/ament), edits launch files (.launch.py), configures QoS or DDS, writes URDF/xacro, implements ros2_control hardware interfaces or controllers, sets up Nav2/MoveIt 2 pipelines, processes

Files · 1

View on GitHub

SKILL.md

1	# ROS 2 Engineering Skills
2
3	> Single responsibility: This skill is an API reference & code template guide
4	> for ROS 2 development. It tells you how to use ROS 2 APIs correctly and
5	> what mistakes to avoid. It does NOT do CI/CD orchestration, incident response,
6	> data analysis, or deployment automation — those are separate skill categories.
7
8	A progressive-disclosure skill for ROS 2 development — from first workspace to
9	production fleet deployment. Detailed patterns and code templates live in
10	`references/`; read the relevant file before writing code.
11
12	## How to use this skill
13
14	Progressive disclosure — do NOT read everything at once. This always-loaded
15	file carries routing, core principles, pitfalls, and anti-patterns; that is
16	enough for quick questions and architectural decisions. `references/*.md` load
17	on demand — use the Decision Router to pick the 1–2 files matching the task,
18	never all of them. `scripts/` are tools to run (scaffolding, QoS checking,
19	launch validation), not reading material.
20
21	Steps:
22
23	1. Identify what the user is building (see Decision Router below).
24	2. Read only the matching `references/*.md` file(s) for detailed guidance.
25	3. Check the AI pitfalls table before generating any code.
26	4. Apply the Core Engineering Principles in every artifact you produce.
27	5. When multiple domains intersect (e.g. Nav2 + ros2_control), read both files
28	but favor safety > determinism > simplicity when recommendations conflict.
29
30	Execution log (opt-in): When the Stop hook runs (Claude Code only) and
31	the `SKILL_RUNS_LOG` environment variable is set, a session summary is
32	appended to `.skill-runs.log`. If that file exists in the workspace, read the
33	last few lines to avoid repeating past mistakes. Without the opt-in — and on
34	platforms without hooks — the file is never created, so a read-only session
35	leaves the working tree untouched.
36
37	Platform support: `SKILL.md` and `references/` are platform-neutral
38	knowledge documents. `scripts/` can be run manually on any platform whose
39	environment has Python and the repository dependencies. The hook wiring
40	(automatic execution) and `.skill-runs.log` are Claude Code-specific; on
41	other platforms run the validators manually from the skill root:
42	`SKILL_WORKSPACE=<dir> python3 scripts/skill_stop_hook.py` and
43	`python3 scripts/skill_validate_hook.py --file <src> / --command '<cmd>'`
44	(the command string is inspected only, never executed; without those flags
45	the validate hook expects a Claude Code PreToolUse payload and checks
46	nothing on its own).
47
48	## Decision router
49
50	\| User is doing... \| Read \|
51	\|---------------------------------------------------\|-----------------------------------\|
52	\| Creating a workspace, package, or build config \| `references/workspace-build.md` \|
53	\| Writing nodes, executors, callback groups \| `references/nodes-executors.md` \|
54	\| Topics, services, actions, custom interfaces, QoS \| `references/communication.md` \|
55	\| Lifecycle nodes, component loading, composition \| `references/lifecycle-components.md` \|
56	\| Launch files, conditional logic, event handlers \| `references/launch-system.md` \|
57	\| tf2, URDF, xacro, robot_state_publisher \| `references/tf2-urdf.md` \|
58	\| ros2_control, hardware interfaces, controllers \| `references/hardware-interfa

People who liked this also viewed

6 picks

Type

ros2-engineering-skills

50installs13forks

View on GitHub

How to install ros2-engineering-skills?

dbwls99706/ros2-engineering-skills/ros2-engineering-skills

$npx -y skills add dbwls99706/ros2-engineering-skills --skill ros2-engineering-skills

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# ROS 2 Engineering Skills
2
3	> Single responsibility: This skill is an API reference & code template guide
4	> for ROS 2 development. It tells you how to use ROS 2 APIs correctly and
5	> what mistakes to avoid. It does NOT do CI/CD orchestration, incident response,
6	> data analysis, or deployment automation — those are separate skill categories.
7
8	A progressive-disclosure skill for ROS 2 development — from first workspace to
9	production fleet deployment. Detailed patterns and code templates live in
10	`references/`; read the relevant file before writing code.
11
12	## How to use this skill
13
14	Progressive disclosure — do NOT read everything at once. This always-loaded
15	file carries routing, core principles, pitfalls, and anti-patterns; that is
16	enough for quick questions and architectural decisions. `references/*.md` load
17	on demand — use the Decision Router to pick the 1–2 files matching the task,
18	never all of them. `scripts/` are tools to run (scaffolding, QoS checking,
19	launch validation), not reading material.
20
21	Steps:
22
23	1. Identify what the user is building (see Decision Router below).
24	2. Read only the matching `references/*.md` file(s) for detailed guidance.
25	3. Check the AI pitfalls table before generating any code.
26	4. Apply the Core Engineering Principles in every artifact you produce.
27	5. When multiple domains intersect (e.g. Nav2 + ros2_control), read both files
28	but favor safety > determinism > simplicity when recommendations conflict.
29
30	Execution log (opt-in): When the Stop hook runs (Claude Code only) and
31	the `SKILL_RUNS_LOG` environment variable is set, a session summary is
32	appended to `.skill-runs.log`. If that file exists in the workspace, read the
33	last few lines to avoid repeating past mistakes. Without the opt-in — and on
34	platforms without hooks — the file is never created, so a read-only session
35	leaves the working tree untouched.
36
37	Platform support: `SKILL.md` and `references/` are platform-neutral
38	knowledge documents. `scripts/` can be run manually on any platform whose
39	environment has Python and the repository dependencies. The hook wiring
40	(automatic execution) and `.skill-runs.log` are Claude Code-specific; on
41	other platforms run the validators manually from the skill root:
42	`SKILL_WORKSPACE=<dir> python3 scripts/skill_stop_hook.py` and
43	`python3 scripts/skill_validate_hook.py --file <src> / --command '<cmd>'`
44	(the command string is inspected only, never executed; without those flags
45	the validate hook expects a Claude Code PreToolUse payload and checks
46	nothing on its own).
47
48	## Decision router
49
50	\| User is doing... \| Read \|
51	\|---------------------------------------------------\|-----------------------------------\|
52	\| Creating a workspace, package, or build config \| `references/workspace-build.md` \|
53	\| Writing nodes, executors, callback groups \| `references/nodes-executors.md` \|
54	\| Topics, services, actions, custom interfaces, QoS \| `references/communication.md` \|
55	\| Lifecycle nodes, component loading, composition \| `references/lifecycle-components.md` \|
56	\| Launch files, conditional logic, event handlers \| `references/launch-system.md` \|
57	\| tf2, URDF, xacro, robot_state_publisher \| `references/tf2-urdf.md` \|
58	\| ros2_control, hardware interfaces, controllers \| `references/hardware-interfa

People who liked this also viewed

6 picks

Type