
Gitlab
A solid wrapper around GitLab's official glab CLI that handles the full workflow: issues, merge requests, pipelines, and repos. The Python script formats read operations into markdown for better LLM consumption, while write operations go straight to glab. Supports GitLab.com, self-managed, and dedicated instances. You'll need to install glab and authenticate first, but after that it's straightforward. The real value is in code review workflows where you can list MRs, view diffs, approve, and merge without leaving the terminal. Includes sensible examples like daily MR reviews and pipeline monitoring. Lightweight enough that you don't need a heavy model to run it.
- skills.sh installs
- 303
- GitHub stars
- 13
- last updated
- Aug 21, 2026
Install
$ npx -y skills add odyssey4me/agent-skills --skill gitlab --agent claude-codeInstalls into .claude/skills of the current project.
Files
GitLab Skill
This skill provides GitLab integration using the official glab CLI tool. A Python wrapper script produces markdown-formatted output for read/view operations. Action commands (create, merge, close, comment) should use glab directly.
Network access
GitLab commands (glab and the Python wrapper) require outbound HTTPS to GitLab API and authentication endpoints, or the configured self-managed GitLab host. Git fetch/push requires HTTPS or SSH to the repository host. Remote operations require outbound network access. If the agent environment restricts it, obtain access through that environment's approval or network controls before the first remote command, reusing authorization already granted. Local help and file processing do not need network access. Skill instructions do not grant network permission. Report DNS, connection, and timeout failures as network errors; do not reset credentials to resolve them. If approved access also fails, stop and report it. Authentication and permission errors require user action.
Resolving script paths
Sponsors
Details
- Repository
- github.com/odyssey4me/agent-skills
- Categories
- DevOps & CI/CD, Git & Pull Requests, Code Review & Quality, AI & Agent Building, CLI & Terminal
- First seen
- Jun 3, 2026