Skill of Skills
📄 skillActivePromisingmedium

zereight/gitlab-mcp

by zereight

First gitlab mcp for you, building together

Supported Platforms

🤖 Claude Code

Stars

1.7k

Skill Type

📖 Library & API Reference

Quality Score

94/200

License

MIT

Forks

307

Last Updated

Jun 11, 2026

Discovered

Apr 15, 2026

Validation

Passed

github.com/zereight/gitlab-mcp

Quality Breakdown

94/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
â—‹Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
â—‹Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multi-agent spawning capability: Repository contains 27+ agent definitions (.github/agents/) that can be orchestrated, including coordinator and executor agents
  • Autonomous operation patterns: Contains 'omg-autopilot' skill and multiple orchestration agents (omg-coordinator, planner, executor) designed for autonomous execution
  • External code execution: MCP server design enables remote execution of GitLab operations without explicit human approval gates per operation
  • Pre/post hooks for automation: Contains .github/hooks/pre-tool-use.sh and post-tool-use.sh that can modify system behavior
  • Complex skill system: 23+ skills including security-scan, self-improve, and ultrawork that could chain autonomously
  • OAuth and credential handling: Supports multiple authentication methods (PAT, OAuth2, remote authorization) which could be exploited if misconfigured