devopsby composio-community
GitLab CLI (glab)
composio-community/GitLab CLI (glab)
Manage GitLab merge requests, issues, pipelines, and CI/CD from the terminal.
What it changes
Passed 22 of 23 test cases with the skill, and 18 of 23 without it.
Without skill78%
With skill96%
Checks it passed that the model alone missed
- Includes the `--output json` flag.
- Uses `glab issue list` to query issues.
- Uses `glab ci list` to view pipeline runs.
and 2 more in the full report
4 fixed18 passed either way1 still failing0 broke
- Pass-rate lift
- +17 pp
- Tokens
- -42%
- Agent turns
- 0%
- Response time
- -51%
Model gemini-3.6-flashMeasured 8/27/2026v122 of 23 cases passed with skill
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat command displays recent pipeline execution runs for a repository in the official GitLab terminal client?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Uses `glab ci list` to view pipeline runs. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md31 linessingle file
GitLab CLI (glab)
MRs, issues, pipelines, and CI/CD management from the terminal.
Installation
brew install glab
glab auth login
Key Commands
glab mr list --output json
glab mr create --title "Feature" --description "Details"
glab issue list --output json
glab issue create --title "Bug" --description "Details"
glab ci list
glab ci view <pipeline-id>
glab repo clone owner/repo
Agent-Friendly Features
--output json for structured output- Token auth via
GITLAB_TOKEN
- Non-interactive CI/CD management
Track record
Benchmark
22 / 23
test cases passed, vs 18 / 23 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedImported 8/3/2026Version v1