agentleFS
YassimbaYassimba/loom/skills/glab/SKILL.md

glab

Skill9 starsChanged 2 months agoApache-2.0View on GitHub

Use when creating, reading, updating, or closing GitLab issues and merge requests with the glab CLI.

  • Commits and pushes

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use glab for GitLab issue and merge request operations.

    line 11
  2. Distinctive:

    Create one feature branch and one commit before opening its merge request.

    line 15
  3. Distinctive:

    Create the merge request with an explicit target branch and self-assignment:

    line 24
  4. Very specific:

    Use conventional commit prefixes in MR titles: feat:, fix:, chore:, refactor:, or docs:.

    line 44
  5. Very specific:

    Use --draft for draft MRs.

    line 46
  6. Distinctive:

    Read or inspect MRs:

    line 48
  7. Distinctive:

    Create and inspect issues:

    line 58
  8. Very specific:

    Use glab issue note <issue-number> --message "..." for comments.

    line 66
  9. Distinctive:

    Check authentication before write operations:

    line 70
  10. Distinctive:

    If authentication fails, stop.

    line 76
  11. Distinctive:

    Before opening an MR:

    line 80
  12. Very specific:

    After opening an MR, record its URL and inspect its pipeline status with glab mr view <mr-number>.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 7 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

Use glab for GitLab issue and merge request operations. Run commands from the repository root so glab can infer the project.

Merge requests

Create one feature branch and one commit before opening its merge request.

git switch -c feat/short-description
git add <files>
git commit -m "feat: short description"
git push -u origin feat/short-description

Create the merge request with an explicit target branch and self-assignment:

glab mr create \
  --title "feat: short description" \
  --description "$(cat <<'EOF'
## Summary
- What changed and why
EOF
)" \
  --target-branch main \
  --assignee @me

Use branch names:

  • feat/short-desc
  • fix/short-desc
  • chore/short-desc

Use conventional commit prefixes in MR titles: feat:, fix:, chore:, refactor:, or docs:.

Use --draft for draft MRs. Never force-push to main.

Read or inspect MRs:

glab mr list
glab mr view <mr-number> --comments
glab mr diff <mr-number>

Issues

Create and inspect issues:

glab issue create --title "Short title" --description "Description"
glab issue view <issue-number> --comments
glab issue list -F json

Use glab issue note <issue-number> --message "..." for comments. Apply labels with glab issue update <issue-number> --label "label"; remove labels with --unlabel. Close an issue with glab issue close <issue-number>.

Authentication

Check authentication before write operations:

glab auth status

If authentication fails, stop. Keep tokens out of commands and output.

Verification

Before opening an MR:

git status --short --branch

After opening an MR, record its URL and inspect its pipeline status with glab mr view <mr-number>.

Download now (ZIP)

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.