This skill provides GitLab integration using the official glab CLI tool. A Python wrapper script produces markdown-formatted output for read/view operations. Action commands (create, merge, close, comment) should use glab directly.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongitlabExecute the skills CLI command in your project's root directory to begin installation:
Fetches gitlab from odyssey4me/agent-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate gitlab. Access via /gitlab in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
2
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
2
stars
This skill provides GitLab integration using the official glab CLI tool. A Python wrapper script produces markdown-formatted output for read/view operations. Action commands (create, merge, close, comment) should use glab directly.
Install glab CLI: installation guide
# Authenticate with GitLab
glab auth login
# Verify authentication
glab auth status
Supports GitLab.com, GitLab Dedicated, and GitLab Self-Managed instances. See GitLab CLI Authentication for details.
The wrapper script (scripts/gitlab.py) formats output as markdown. Use it for read/view operations to get agent-consumable output. Use glab directly for action commands (create, merge, close, comment). See permissions.md for read/write classification of each command.
# Check glab CLI is installed and authenticated
$SKILL_DIR/scripts/gitlab.py check
# Issues
$SKILL_DIR/scripts/gitlab.py issues list --repo GROUP/REPO
$SKILL_DIR/scripts/gitlab.py issues view 123 --repo GROUP/REPO
# Merge Requests
$SKILL_DIR/scripts/gitlab.py mrs list --repo GROUP/REPO
$SKILL_DIR/scripts/gitlab.py mrs view 456 --repo GROUP/REPO
# Pipelines
$SKILL_DIR/scripts/gitlab.py pipelines list --repo GROUP/REPO
$SKILL_DIR/scripts/gitlab.py pipelines view 123456 --repo GROUP/REPO
# Repositories
$SKILL_DIR/scripts/gitlab.py repos list
$SKILL_DIR/scripts/gitlab.py repos view GROUP/REPO
All commands support --limit N for list commands (default 30).
For action commands, use glab directly:
glab issue list # List issues
glab issue view 123 # View issue details
glab issue create # Create new issue
glab issue note 123 # Add comment
glab issue close 123 # Close issue
glab issue update 123 --label bug # Edit issue
Full reference: glab issue
glab mr list # List merge requests
glab mr view 456 # View MR details
glab mr create # Create new MR
glab mr approve 456 # Approve MR
glab mr merge 456 # Merge MR
glab mr checkout 456 # Checkout MR branch
glab mr diff 456 # View MR diff
glab mr note 456 # Add comment to MR
Full reference: glab mr
glab ci list # List pipelines
glab ci view 123456 # View pipeline details
glab ci run # Trigger pipeline
glab ci trace # Watch pipeline logs
glab ci retry 123456 # Retry failed pipeline
glab ci status # Show pipeline status
Full references:
glab repo list # List repositories
glab repo view GROUP/REPO # View repository
glab repo create # Create repository
glab repo clone GROUP/REPO # Clone repository
glab repo fork GROUP/REPO # Fork repository
Full reference: glab repo
glab release list # List releases
glab release view v1.0.0 # View release details
glab release create v1.0.0 # Create release
glab release delete v1.0.0 # Delete release
Full reference: glab release
# List MRs assigned to you
glab mr list --assignee=@me
# Review a specific MR
$SKILL_DIR/scripts/gitlab.py mrs view 456
glab mr diff 456
glab mr approve 456
# Verify approval was recorded
$SKILL_DIR/scripts/gitlab.py mrs view 456 # check approval status
# Create issue
glab issue create --title "Bug: Login fails" --description "Description" --label bug
# Verify: note the issue number from output
# Create MR that closes it (use issue number from above)
glab mr create --title "Fix login bug" --description "Closes #123"
# Verify MR was created and linked
$SKILL_DIR/scripts/gitlab.py mrs view <number>
# Check current pipeline status
glab ci status
# Watch pipeline logs in real-time
glab ci trace
# Retry failed jobs
glab ci retry
# Verify pipeline restarted
$SKILL_DIR/scripts/gitlab.py pipelines list
See common-workflows.md for more examples.
# Get JSON output
glab issue list --output json
# Process with jq
glab mr list --output json | jq '.[] | "\(.iid): \(.title)"'
For operations not covered by glab commands:
# Make authenticated API request
glab api projects/:id/issues
# POST request
glab api projects/:id/issues -X POST -f title="Issue" -f description="Text"
# Process response
glab api projects/:id | jq '.star_count'
Full reference: glab api
# Create shortcuts
glab alias set mrs 'mr list --assignee=@me'
glab alias set issues 'issue list --assignee=@me'
glab alias set pipelines 'ci list'
# Use them
glab mrs
glab issues
glab pipelines
# View configuration
glab config get
# Set default editor
glab config set editor vim
# Set default Git protocol
glab config set git_protocol ssh
Configuration stored in ~/.config/glab-cli/config.yml
This skill wraps an official CLI. A fast, lightweight model is sufficient.
# Check authentication
glab auth status
# Re-authenticate
glab auth login
# Enable debug logging
DEBUG=1 glab issue list
# Check glab version
glab version
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
We added gitlab from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Keeps context tight: gitlab is the kind of skill you can hand to a new teammate without a long onboarding doc.
gitlab fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
gitlab has been reliable in day-to-day use. Documentation quality is above average for community skills.
gitlab fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
gitlab has been reliable in day-to-day use. Documentation quality is above average for community skills.
Solid pick for teams standardizing on skills: gitlab is focused, and the summary matches what you get after install.
gitlab reduced setup friction for our internal harness; good balance of opinion and flexibility.
gitlab fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend gitlab for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 33