Gitlab Explorer logo

Gitlab Explorer

Organization
Wide-Moat
gitlab-explorer

Explore GitLab repositories using glab CLI and git commands. Use when user asks to: clone repositories, search projects or code in GitLab, view merge requests, explore project structure, check CI/CD pipelines, work with issues, or analyze git history. IMPORTANT: Always run authentication check script first before any GitLab operation.

Overview

PublisherWide-Moat
Repositoryopen-computer-use
Skill namegitlab-explorer
Stars
123
Forks
29
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Wide-Moat on GitHub. Read the source before you install it.

Installation

Install the Gitlab Explorer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git /tmp/open-computer-use
mkdir -p .claude/skills
cp -r /tmp/open-computer-use/skills/public/gitlab-explorer .claude/skills/gitlab-explorer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gitlab Explorer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gitlab Explorer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gitlab Explorer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GitLab Explorer

This skill enables exploring GitLab repositories, searching code, viewing merge requests, and working with git history.

Before Any GitLab Operation

ALWAYS run the authentication check first:

bash
bash /mnt/skills/public/gitlab-explorer/scripts/check_gitlab_auth.sh

This script will:

  • Verify if GitLab token is configured
  • Validate the token by calling GitLab API
  • Show logged-in user info if valid
  • Provide setup instructions if not configured

DO NOT try to read or echo $GITLAB_TOKEN directly - the script handles validation securely without exposing the token.

If authentication is not configured, inform the user:

To use GitLab features, please go to and add your GitLab Personal Access Token. Then start a NEW chat to apply the token.

Quick Start

Clone a Repository

bash
git clone https://gitlab.com/group/project.git
cd project

Search for Projects

bash
# Search projects by name
glab api "projects?search=keyword" | jq '.[].path_with_namespace'

# List projects in a group
glab api "groups/GROUP_NAME/projects" | jq '.[].name'

Check Current User

bash
glab api user | jq '{username, email, name}'

Exploring Code

Repository Structure

bash
# Show directory tree
tree -L 2

# Find files by pattern
find . -name "*.py" -type f

# Search for text in files
git grep "pattern"

Git History

bash
# View commit history
git log --oneline -20

# Visual branch history
git log --oneline --graph --all -20

# Who changed what
git blame filename

# Show specific commit
git show COMMIT_HASH

# Changes between branches
git diff main..feature-branch

Top Contributors

bash
git shortlog -sn --all | head -10

Working with Merge Requests

bash
# List open MRs
glab mr list

# View specific MR
glab mr view 123

# Show MR diff
glab mr diff 123

# Checkout MR branch locally
glab mr checkout 123

CI/CD Pipelines

bash
# Current pipeline status
glab ci status

# List recent pipelines
glab ci list

# View pipeline details
glab ci view PIPELINE_ID

# Watch job logs in real-time
glab ci trace

Issues

bash
# List issues
glab issue list

# View issue details
glab issue view 123

# Create new issue
glab issue create --title "Bug report" --description "Description here"

Reference Materials

For detailed command reference, see:

  • references/glab-commands.md - Complete glab CLI reference
  • references/git-commands.md - Git commands for code exploration

Common Workflows

Explore Unknown Repository

  1. Clone the repo
  2. Check README and documentation
  3. Explore directory structure with tree
  4. Find main entry points
  5. Use git log to understand recent changes
  6. Use git blame to find who wrote specific code

Review Merge Request

  1. glab mr view ID - read description
  2. glab mr diff ID - review changes
  3. glab mr checkout ID - test locally if needed
  4. Check CI status with glab ci status

Find Code by Pattern

bash
# Search in all files
git grep "function_name"

# Search with context
git grep -n -C 3 "pattern"

# Search in specific file types
git grep "pattern" -- "*.py"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gitlab Explorer AI skill do?

Explore GitLab repositories using glab CLI and git commands. Use when user asks to: clone repositories, search projects or code in GitLab, view merge requests, explore project structure, check CI/CD pipelines, work with issues, or analyze git history. IMPORTANT: Always run authentication check script first before any GitLab operation.

Why use Gitlab Explorer on TypingMind?

Because you install it once and use it with any model. Gitlab Explorer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gitlab Explorer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/gitlab-explorer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gitlab Explorer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gitlab Explorer?

As many as you like. As long as a model supports skills, you can use Gitlab Explorer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gitlab Explorer AI skill free?

It is published on GitHub by Wide-Moat. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇