agentleFS
Sign inStart free
DataKnifeAIDataKnifeAI/agent-skills/skills/glab-cli/SKILL.md

glab-cli

Skill0 starsChanged 7 months agoApache-2.0View on GitHub

Uses the GitLab CLI (`glab`) for merge requests, issues, CI/CD, releases, and GitLab API access from the terminal. Apply when the remote is GitLab (GitLab.com or self-managed) or when the user mentions MRs, pipelines, or GitLab projects.

  • Reads credentials

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create or review merge requests, issues, milestones, and labels from the shell.

    line 14
  2. Very specific:

    Call the GitLab HTTP API via glab api with the same auth as the CLI.

    line 16
  3. Very specific:

    Treat GITLAB_TOKEN like a password.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitLab CLI (glab)

When to use

  • Create or review merge requests, issues, milestones, and labels from the shell.
  • Inspect or retry pipelines and jobs (glab ci, glab job).
  • Call the GitLab HTTP API via glab api with the same auth as the CLI.

Prerequisites

  • glab installed (glab version). Install and reference: GitLab CLI documentation.
  • Auth: glab auth login (interactive) or tokens. Common env vars:
    • GITLAB_TOKEN (or GITLAB_ACCESS_TOKEN / OAUTH_TOKEN per deployment)
    • GITLAB_HOST or GL_HOST for self-managed GitLab (e.g. https://gitlab.example.com)
  • In GitLab CI, GLAB_ENABLE_CI_AUTOLOGIN=true can use CI_JOB_TOKEN for supported commands; token precedence is documented upstream.

Patterns

  • Help: glab --help, glab <cmd> --help.
  • Repo scope: from current directory’s Git remote, or -R group/project / --repo where supported.
  • JSON: many commands offer -F json or --output json (check each command’s help).

Core commands (orienting)

AreaExamples
Authglab auth status, glab auth login
MRsglab mr list, glab mr create, glab mr view, glab mr checkout <id>, glab mr approve
Issuesglab issue list, glab issue create, glab issue view
CI/CDglab ci view, glab ci list, glab job trace (exact subcommands: glab ci --help)
Repoglab repo clone, glab repo view
APIglab api projects/:id (paths and methods: glab api --help)

Safety

  • Treat GITLAB_TOKEN like a password; never echo it in logs.
  • Destructive operations (merge, delete, pipeline retry) require explicit user alignment.

References

  • Official documentation: GitLab CLI
  • Local help: glab --help, glab <cmd> --help (authoritative for your installed glab version)

Download now (ZIP)

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. flc1125/skills★ 38same name
    2. nb-99/skillektion★ 1same name
    3. bryanus1/agent-skills★ 0same name
    4. chenwei791129/agent-skills★ 0same name
    5. danielsitek/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free