← Back to Skills Marketplace
GitLab Agent Self Improvement
by
Björn Dieding
· GitHub ↗
· v1.39.1
· MIT-0
44
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xrow-self-improvement
Description
A skill for personal growth and self-improvement.
README (SKILL.md)
Self-Improvement Skill
Your Project: helm-openclaw
- Think about what you have learned and how you can improve yourself
- If you have not found any valuable improvement or if your change is just cosmetic then do stop executing this skill.
- Write down your findings and ideas in a new Merge Request and assign it to yourself.
- Never address two totally separate issues in one merge request; split them into separate MRs.
- Close an older Merge Request created by yourself that has not been accepted for 10 Days after the last recent activity/review state.
For more information about how to behave as a GitLab Agent and work with GitLab, read and follow the skill gitlab-agent.
Usage Guidance
Install only if you intend to let the agent operate on the named GitLab project using your GitLab token. Review proposed merge-request creation or closure manually, and prefer using a narrowly scoped token with access limited to the intended repository.
Capability Assessment
Purpose & Capability
The body is really a GitLab project-maintenance workflow for helm-openclaw, including creating new merge requests and closing older self-created ones, while the name and description frame it broadly as personal self-improvement.
Instruction Scope
The instructions give subjective discretion to decide what is a valuable improvement and then mutate GitLab state, but they do not require explicit user approval, dry-run review, or repository validation before creating or closing merge requests.
Install Mechanism
The metadata transparently declares a dependency on the glab CLI and primary GITLAB_TOKEN environment variable; there are no executable package files beyond the Markdown skill.
Credentials
GitLab mutation authority is partially scoped to a named project, but the requested token-backed access is high-impact relative to the vague frontmatter description and lacks clear containment controls.
Persistence & Privilege
No local persistence, background worker, credential harvesting, or install-time execution is shown; the main privilege concern is use of an existing GitLab token for remote state changes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xrow-self-improvement - After installation, invoke the skill by name or use
/xrow-self-improvement - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.39.1
- Clarified guidelines for submitting and managing self-improvement merge requests.
- Added instructions to avoid cosmetic or unimportant changes.
- Emphasized separating unrelated issues into different merge requests.
- Introduced rule to close stale self-assigned merge requests after 10 days of inactivity.
- Updated links and context for GitLab integration and agent behavior.
Metadata
Frequently Asked Questions
What is GitLab Agent Self Improvement?
A skill for personal growth and self-improvement. It is an AI Agent Skill for Claude Code / OpenClaw, with 44 downloads so far.
How do I install GitLab Agent Self Improvement?
Run "/install xrow-self-improvement" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is GitLab Agent Self Improvement free?
Yes, GitLab Agent Self Improvement is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does GitLab Agent Self Improvement support?
GitLab Agent Self Improvement is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created GitLab Agent Self Improvement?
It is built and maintained by Björn Dieding (@xrow); the current version is v1.39.1.
More Skills