Not in the top 1,000 by GitHub stars
Leehyunbin0131/claude-ros2-skills
Claude Code skills for ROS 2 Jazzy — establish the unknowns first, verify against the installed system, prove the result ran.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/ros2-development/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
21be90a50feb → 21be90a50feb
skills/ros2-microros/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
21be90a50feb → 21be90a50feb
skills/ros2-troubleshooting/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
21be90a50feb → 21be90a50feb
Verified commit 21be90a50febf5e7a5bf9cee8aeebd81f98f8c67
git clone --filter=blob:none --no-checkout https://github.com/Leehyunbin0131/claude-ros2-skills.git .hotskills/leehyunbin0131-claude-ros2-skills && git -C .hotskills/leehyunbin0131-claude-ros2-skills checkout --detach 21be90a50febf5e7a5bf9cee8aeebd81f98f8c67
# Copy each selected skill directory from .hotskills/leehyunbin0131-claude-ros2-skills into .claude/skills/<skill-name>/Heat
1.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- ros2-development
skills/ros2-development - ros2-microros
skills/ros2-microros - ros2-troubleshooting
skills/ros2-troubleshooting
How it works
ros2-development
When your agent uses it
Implement or change ROS 2 Jazzy packages, nodes, interfaces, launch files and configuration in a colcon workspace. Use for building and validating a development change, including tests that report success without running. For a live QoS, TF, IMU or odometry fault, use ros2-troubleshooting.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,283 tokensWhen the skill is activated
Reference documents
2,475 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Build the affected package graph
- Require tests to have run
- Verify the installed behaviour
- Optional evidence tracking and handoff
- Evidence
Scripts executed separately
scripts/check_test_results.pyscripts/evidence.py
Files
../../.claude-plugin/marketplace.jsonasset589 bytes../../.claude-plugin/plugin.jsonasset236 bytes../../hooks/hooks.jsonasset240 bytesSKILL.mdcore6,086 bytesSKILL.mdcore6,086 bytesSKILL.mdcore6,086 bytesSKILL.mdcore6,086 bytesSKILL.mdcore6,086 bytesreferences/handoff.mddoc9,080 bytesreferences/verification.mddoc2,534 bytesscripts/check_test_results.pyruns9,756 bytesscripts/evidence.pyruns14,489 bytes
Read SKILL.md
# ROS 2 development
Work from the workspace's actual package graph and installed artifacts. This
skill supplies a development workflow, a check for empty test runs, and an
optional evidence tracking tool for task handoff. It does not prescribe a new
workspace layout or replace the project's build conventions.
## Build the affected package graph
Use `colcon list` to identify package names and build types. Build the changed
package and its workspace dependencies with `colcon build --packages-up-to
<package>`. `--packages-select` alone does not build its dependencies. For a
message or public API change, include affected consumers in the build and tests.
Preserve the project's existing build/install flags and dependency versions.View the complete source on GitHubros2-microros
When your agent uses it
micro-ROS: agent, rclc client API, micro_ros_setup, custom transports, static memory.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
932 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Architecture
- 2. Documentation Entry Points
- 3. Key Concepts & Patterns
- 4. Symptom -> Root Cause -> Action
Files
SKILL.mdcore3,613 bytesSKILL.mdcore3,613 bytesSKILL.mdcore3,613 bytesSKILL.mdcore3,613 bytesSKILL.mdcore3,613 bytesSKILL.mdcore3,613 bytes
Read SKILL.md
# micro-ROS Instructions (Ubuntu 24.04 LTS & ROS 2 Jazzy)
> **Experimental; not validated on MCU hardware.** An MCU and a micro-ROS agent
> connection were unavailable for this release. Treat these source pointers and
> examples as a starting point to verify against your board, transport and Jazzy
> versions, not as proof that a firmware configuration works.
## 1. Architecture
micro-ROS connects constrained MCUs to the ROS 2 DDS graph via `micro_ros_agent` and `rclc` over Micro XRCE-DDS. `RMW_UXRCE_ALLOW_DYNAMIC_ALLOCATIONS=OFF` prevents dynamic growth of the RMW's static pools; it does not guarantee zero heap allocation throughout the firmware. See the [Jazzy RMW configuration](https://github.com/micro-ROS/rmw_microxrcedds/blob/jazzy/README.md) for the flag's scope.
## 2. Documentation Entry Points
| For | Entry point |View the complete source on GitHubros2-troubleshooting
When your agent uses it
Diagnose ROS 2 Jazzy faults that reading the code cannot settle: QoS mismatch, sensor-mount and frame errors (REP 103/105), and odometry calibrated against CAD instead of the floor. Ships four runnable pass/fail checks.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
752 tokensWhen the skill is activated
Reference documents
1,948 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Bundled checks
- References
Scripts executed separately
scripts/_check_common.pyscripts/check_imu_gravity.pyscripts/check_odom_direction.pyscripts/check_qos_compat.pyscripts/check_tf_tree.pyscripts/test_checks.py
Files
SKILL.mdcore2,986 bytesSKILL.mdcore2,986 bytesSKILL.mdcore2,986 bytesSKILL.mdcore2,986 bytesreferences/calibration.mddoc2,617 bytesreferences/frames.mddoc2,751 bytesreferences/runtime.mddoc2,694 bytesscripts/_check_common.pyruns1,185 bytesscripts/check_imu_gravity.pyruns8,506 bytesscripts/check_odom_direction.pyruns6,710 bytesscripts/check_qos_compat.pyruns3,003 bytesscripts/check_tf_tree.pyruns5,827 bytesscripts/test_checks.pyruns6,917 bytes
Read SKILL.md
# ROS 2 troubleshooting
Most of this skill is scripts that turn a suspicion into an exit code. Run one
before reasoning about the symptom.
## Bundled checks
`scripts/` sits next to this file — resolve the path from this skill's own
directory, not the user's CWD. The variable `ROS2_SKILL_DIR` in the examples
represents the absolute directory of the loaded skill, set internally by the
agent based on discovery location (do not ask the user for this path).
This works with Claude Code and Codex, for project and user installations.
They are plain scripts: invoke with `python3` and a real path. There is noView the complete source on GitHubSkills included
- ros2-development
- ros2-microros
- ros2-troubleshooting
Repository facts
- License
- Apache-2.0
- Created
- Jul 23, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 12 notes
skills/ros2-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-microros/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-microros/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-microros/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-microros/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-microros/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-troubleshooting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-troubleshooting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ros2-troubleshooting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 20 network referencesin 5 files: ros2-microros/SKILL.md:15 ros2-development/SKILL.md:99 ros2-troubleshooting/references/calibration.md:6 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- 8 executable scriptsin 8 files: ros2-development/scripts/check_test_results.py:1 ros2-development/scripts/evidence.py:1 ros2-troubleshooting/scripts/_check_common.py:1 and 5 more
- 2 references to secretsin 2 files: ros2-development/scripts/check_test_results.py:150 ros2-development/scripts/evidence.py:97
- No requests to vote in Hot
Show all 30 signals by file
skills/ros2-development/SKILL.md
- Network accessline 99
This workflow provides diagnostic checks; an agent comparison has **not** established a performance gain from its prose. Official semantics: [package selection](https://colcon.readthedocs.io/en/released/reference/package-selection-arguments - Network accessline 100
a performance gain from its prose. Official semantics: [package selection](https://colcon.readthedocs.io/en/released/reference/package-selection-arguments.html), [test](https://colcon.readthedocs.io/en/released/reference/verb/test.html), - Network accessline 101
Official semantics: [package selection](https://colcon.readthedocs.io/en/released/reference/package-selection-arguments.html), - Network accessline 102
[test](https://colcon.readthedocs.io/en/released/reference/verb/test.html), - Network accessline 103
[test results](https://colcon.readthedocs.io/en/released/reference/verb/test-result.html).
skills/ros2-development/references/verification.md
- Network accessline 21
Inspect installed Jazzy message definitions and package APIs before adapting an example. [Colcon's workspace guide](https://colcon.readthedocs.io/en/released/user/what-is-a-workspace.html) - Network accessline 22
example. [Colcon's workspace guide](https://colcon.readthedocs.io/en/released/user/what-is-a-workspace.html)
skills/ros2-development/scripts/check_test_results.py
skills/ros2-development/scripts/evidence.py
skills/ros2-microros/SKILL.md
- Network accessline 15
micro-ROS connects constrained MCUs to the ROS 2 DDS graph via `micro_ros_agent` and `rclc` over Micro XRCE-DDS. `RMW_UXRCE_ALLOW_DYNAMIC_ALLOCATIONS=OFF` prevents dynamic growth of the RMW's static pools; it does not guarantee zero heap al - Network accessline 19
| For | Entry point | | :--- | :--- | | Tutorials, supported boards, transports | `https://micro.ros.org/` | - Network accessline 20
| :--- | :--- | | Tutorials, supported boards, transports | `https://micro.ros.org/` | | Firmware build system (`micro_ros_setup`) | `https://github.com/micro-ROS/micro_ros_setup` | - Network accessline 21
| Tutorials, supported boards, transports | `https://micro.ros.org/` | - Network accessline 22
| Firmware build system (`micro_ros_setup`) | `https://github.com/micro-ROS/micro_ros_setup` | - Network accessline 23
| `rclc` executor / node API source | `https://github.com/ros2/rclc` |
skills/ros2-troubleshooting/references/calibration.md
- Network accessline 6
Parameter names and their `1.0` baselines were checked against the installed Jazzy header (2026-08-01). The correction direction below follows Jazzy's [odometry equations](https://github.com/ros-controls/ros2_controllers/blob/jazzy/diff_dri - Network accessline 7
Jazzy header (2026-08-01). The correction direction below follows Jazzy's [odometry equations](https://github.com/ros-controls/ros2_controllers/blob/jazzy/diff_drive_controller/src/odometry.cpp) and [application of multipliers](https://gith - Network accessline 8
[odometry equations](https://github.com/ros-controls/ros2_controllers/blob/jazzy/diff_drive_controller/src/odometry.cpp) - Network accessline 9
and [application of multipliers](https://github.com/ros-controls/ros2_controllers/blob/jazzy/diff_drive_controller/src/diff_drive_controller.cpp).
skills/ros2-troubleshooting/references/frames.md
skills/ros2-troubleshooting/scripts/_check_common.py
- Executable scriptline 1
Executable file
skills/ros2-troubleshooting/scripts/check_imu_gravity.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ros2-troubleshooting/scripts/check_odom_direction.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ros2-troubleshooting/scripts/check_qos_compat.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ros2-troubleshooting/scripts/check_tf_tree.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ros2-troubleshooting/scripts/test_checks.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 30 facts
- Network access in prose of the SKILL.mdros2-development/SKILL.md:99Low confidence
- Network access in prose of the SKILL.mdros2-development/SKILL.md:100Low confidence
- Network access in prose of the SKILL.mdros2-development/SKILL.md:101Low confidence
- Network access in prose of the SKILL.mdros2-development/SKILL.md:102Low confidence
- Network access in prose of the SKILL.mdros2-development/SKILL.md:103Low confidence
- Network access in prose of documentationros2-development/references/verification.md:21Low confidence
- Network access in prose of documentationros2-development/references/verification.md:22Low confidence
- Executable script in code of a file that runsros2-development/scripts/check_test_results.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueros2-development/scripts/check_test_results.py:150Low confidence
- Executable script in code of a file that runsros2-development/scripts/evidence.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueros2-development/scripts/evidence.py:97Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:15Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdros2-microros/SKILL.md:23Low confidence
- Network access in prose of documentationros2-troubleshooting/references/calibration.md:6Low confidence
- Network access in prose of documentationros2-troubleshooting/references/calibration.md:7Low confidence
- Network access in prose of documentationros2-troubleshooting/references/calibration.md:8Low confidence
- Network access in prose of documentationros2-troubleshooting/references/calibration.md:9Low confidence
- Network access in prose of documentationros2-troubleshooting/references/frames.md:6Low confidence
- Network access in prose of documentationros2-troubleshooting/references/frames.md:7Low confidence
- Network access in prose of documentationros2-troubleshooting/references/frames.md:8Low confidence
- Executable script in prose of a file that runsros2-troubleshooting/scripts/_check_common.py:1Low confidence
- Executable script in code of a file that runsros2-troubleshooting/scripts/check_imu_gravity.py:1High confidence
- Executable script in code of a file that runsros2-troubleshooting/scripts/check_odom_direction.py:1High confidence
- Executable script in code of a file that runsros2-troubleshooting/scripts/check_qos_compat.py:1High confidence
- Executable script in code of a file that runsros2-troubleshooting/scripts/check_tf_tree.py:1High confidence
- Executable script in code of a testros2-troubleshooting/scripts/test_checks.py:1Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/ros2-development/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/ros2-development/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/ros2-development/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/ros2-development/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/ros2-development/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.