Glab logo

Glab

Organization
skillmds
glab

GitLab CLI for managing issues, merge requests, CI/CD pipelines, and repositories. Use when: (1) Creating, reviewing, or merging MRs, (2) Managing GitLab issues, (3) Monitoring or triggering CI/CD pipelines, (4) Working with self-hosted GitLab instances, (5) Automating GitLab workflows from the command line. Requires GITLAB_TOKEN (recommend minimal scopes). The `glab api` command enables arbitrary API calls - use read-only tokens when possible.

Overview

Publisherskillmds
Repositoryskillmd
Skill nameglab
Stars
249
Forks
3
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

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

  • Open source

    Published by skillmds on GitHub. Read the source before you install it.

Installation

Install the Glab 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.
    https://github.com/skillmds/skillmd/tree/main/plugins/cloud-devops/skills/glab
  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/skillmds/skillmd.git /tmp/skillmd
mkdir -p .claude/skills
cp -r /tmp/skillmd/plugins/cloud-devops/skills/glab .claude/skills/glab
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Glab 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 Glab 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 Glab 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 CLI (glab)

Official CLI for GitLab. Manage issues, merge requests, pipelines, and more from the terminal.

Source: Inspired by NikiforovAll/glab-skill on Smithery.

⚠️ Security Notice

The glab api command provides unrestricted GitLab API access with your token.

  • A compromised or overly-permissive token can delete projects, modify settings, expose secrets
  • Recommendation: Use tokens with minimal scopes:
    • read_api - Read-only operations
    • api - Full access (only when write operations needed)
  • For automation, consider project-level tokens with limited scope
  • Never use tokens with sudo scope unless required

Prerequisites

Required binaries:

  • glab - GitLab CLI
  • jq - JSON processor (for scripts and API parsing)

Required credentials:

  • GITLAB_TOKEN - GitLab personal access token

Optional configuration:

  • GITLAB_HOST - Self-hosted GitLab instance (default: gitlab.com)
bash
# Verify installation
glab --version
jq --version

# Authenticate (interactive)
glab auth login

# Or via environment
export GITLAB_TOKEN="glpat-xxxxxxxxxxxxxxxxxxxx"
export GITLAB_HOST="gitlab.example.org"  # for self-hosted

# Verify auth
glab auth status

Quick Reference

Merge Requests:

bash
glab mr create --title "Fix" --description "Closes #123"
glab mr list --reviewer=@me          # MRs awaiting your review
glab mr checkout 123                  # Test MR locally
glab mr approve 123 && glab mr merge 123

Issues:

bash
glab issue create --title "Bug" --label=bug
glab issue list --assignee=@me
glab issue close 456

CI/CD:

bash
glab ci status                        # Current pipeline status
glab pipeline ci view                 # Watch pipeline live
glab ci lint                          # Validate .gitlab-ci.yml
glab ci retry                         # Retry failed pipeline

Working Outside Repo:

bash
glab mr list -R owner/repo            # Specify repository

Advanced API Access:

See references/api-advanced.md for glab api usage. This command enables arbitrary GitLab API calls and should be used with appropriately-scoped tokens.

Core Workflows

Create and Merge MR

bash
# 1. Push branch
git push -u origin feature-branch

# 2. Create MR
glab mr create --title "Add feature" --description "Implements X" --reviewer=alice,bob --label="enhancement"

# 3. After approval, merge
glab mr approve 123
glab mr merge 123 --remove-source-branch

Review MR

bash
# List MRs for review
glab mr list --reviewer=@me

# Checkout and test
glab mr checkout 123

# Approve or comment
glab mr approve 123
glab mr note 123 -m "Looks good, just one suggestion..."

Monitor Pipeline

bash
# Watch current branch pipeline
glab pipeline ci view

# Check specific pipeline
glab ci view 456

# View failed job logs
glab ci trace

# Retry
glab ci retry

Self-Hosted GitLab

bash
# Set default host
export GITLAB_HOST=gitlab.example.org

# Or per-command
glab mr list -R gitlab.example.org/owner/repo

Scripts

ScriptDescription
glab-mr-await.shWait for MR approval and successful pipeline
glab-pipeline-watch.shMonitor pipeline with exit codes for CI
bash
# Wait for MR to be approved and merged
./scripts/glab-mr-await.sh 123 --timeout 600

# Watch pipeline, exit 0 on success, 1 on failure
./scripts/glab-pipeline-watch.sh --timeout 300

Script environment variables:

  • TIMEOUT - Max wait time in seconds (default varies by script)
  • INTERVAL - Polling interval in seconds (default 5-10s)

Troubleshooting

ErrorFix
command not found: glabInstall glab
command not found: jqInstall jq
401 UnauthorizedSet GITLAB_TOKEN or run glab auth login
404 Project Not FoundVerify repo name and permissions
not a git repositoryUse -R owner/repo flag
source branch already has MRglab mr list to find existing

For detailed troubleshooting, see references/troubleshooting.md.

Progressive Disclosure

  • references/api-advanced.md - glab api usage with security considerations
  • references/commands-detailed.md - Full command reference with all flags
  • references/troubleshooting.md - Detailed error scenarios and solutions

Load these when you need specific flag details or are debugging issues.

Best Practices

  1. Always verify auth: glab auth status
  2. Use minimal-scope tokens for read operations
  3. Link MRs to issues: "Closes #123" in description
  4. Lint CI config before pushing: glab ci lint
  5. Use --output=json for scripting
  6. Most commands have --web to open in browser

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 Glab AI skill do?

GitLab CLI for managing issues, merge requests, CI/CD pipelines, and repositories. Use when: (1) Creating, reviewing, or merging MRs, (2) Managing GitLab issues, (3) Monitoring or triggering CI/CD pipelines, (4) Working with self-hosted GitLab instances, (5) Automating GitLab workflows from the command line. Requires GITLAB_TOKEN (recommend minimal scopes). The `glab api` command enables arbitrary API calls - use read-only tokens when possible.

Why use Glab on TypingMind?

Because you install it once and use it with any model. Glab 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 Glab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/skillmds/skillmd/tree/main/plugins/cloud-devops/skills/glab. 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 Glab?

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 Glab?

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

Is the Glab AI skill free?

Yes. It is published on GitHub by skillmds under the MIT license. 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 👇