An AI agent skill that provides comprehensive GitLab integration — fetch issues and merge requests, generate executive summaries, perform structured code reviews, and automate end-to-end issue resolution workflows.
# Gitlab Skill An AI agent skill for GitLab integration — fetch issues and merge requests, generate executive summaries, perform structured code reviews, and automate issue resolution workflows. Built as a [Claude Code / Cursor skill](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/skills), it works with any AI coding assistant that supports skill-based orchestration. ## Quick Install ```bash curl -fsSL https://raw.githubusercontent.com/ekohe/gitlab-skill/main/install.sh | bash ``` This clones the repo into your skills directory, installs dependencies, and creates a config file for you to fill in. Re-run to update. **Manual install:** ```bash git clone https://github.com/ekohe/gitlab-skill.git ~/.cursor/skills/gitlab-skill cd ~/.cursor/skills/gitlab-skill pip install -r requirements.txt cp gitlab_config.json.template gitlab_config.json ``` ## Features - **Multi-instance** — manage multiple GitLab servers from one config - **Project aliases** — short names with automatic instance routing - **Issue summaries** — executive-level summaries focused on business impact - **Code reviews** — structured analysis across Security, Logic, Performance, and Quality - **Issue resolution** — end-to-end: fetch issue, branch, implement, MR, comment - **Project insights** — aggregate statistics and trend analysis ## Creating a GitLab Personal Access Token A Personal Access Token (PAT) is required to authenticate with the GitLab API. ### Steps 1. Sign in to your GitLab instance 2. Go to **User Settings > Access Tokens** - GitLab.com: https://gitlab.com/-/user_settings/personal_access_tokens - Self-hosted: `https://<your-gitlab>/–/user_settings/personal_access_tokens` 3. Click **Add new token** 4. Fill in the fields: - **Token name:** e.g. `Gitlab Skill` - **Expiration date:** set a reasonable expiry (max 1 year recommended) - **Scopes:** select **`api`** (full API access — required for reading issues/MRs and posting comments) 5. Click **Create
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.