alexismanuel/mr-generator
.pi/agent/skills/mr-generator/SKILL.md
Generate GitLab merge request descriptions from git commits with automatic categorization and Jira integration.
development
Updated Apr 1, 2026
$ install --global
skillsauthnpx skillsauth add alexismanuel/dotfiles mr-generatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 2, 2026, 3:38 AM55.8s2 files scanned
SKILL.md
- name:
- mr-generator
- description:
- Generate GitLab merge request descriptions from git commits with automatic categorization and Jira integration.
MR Generator
Generate MR descriptions from git commits.
Usage
# Basic (output to terminal)
python3 ~/.pi/agent/skills/mr-generator/scripts/mr_generator.py
# With Jira ticket (non-interactive)
python3 ~/.pi/agent/skills/mr-generator/scripts/mr_generator.py --jira RD-XXXX
# Create MR directly
python3 ~/.pi/agent/skills/mr-generator/scripts/mr_generator.py --create --jira RD-XXXX
# Save to file
python3 ~/.pi/agent/skills/mr-generator/scripts/mr_generator.py --output mr_description.md
Best Practices
- Include project-specific testing instructions (check project's AGENTS.md for testing patterns)
- Replace template placeholders with actual working examples reviewers can copy-paste
- Keep "What's new" concise - implementation details belong in commit messages
- In monorepos, adapt testing section to the specific project's conventions
MR Template
Closes #X or Relates to [link]
## What's new
- ✨ [New feature description - 1-2 bullets max]
## Testing
Run the following commands [project-specific setup]:
```bash
# Include actual working commands from AGENTS.md
Then test with [specific example]:
# Real working example, not placeholders
## Commit Categorization
Automatic emoji mapping:
- 🎉 Init: `init`, `initial`
- ✨ Feature: `feat`, `add`
- 🐛 Bug: `fix`, `bug`, `patch`
- 🔥 P1: `p1`, `critical`
- 💄 Style: `style`, `ui`
- 🚀 Deploy: `deploy`, `release`
- 🔧 Refactor: `refactor`, `cleanup`
- 📚 Docs: `docs`
- 🧪 Tests: `test`
## Requirements
- Python 3.10+
- GitLab CLI (`glab auth login`)
Related Skills
alexismanuel/workflow-validate-plan
development
VerifiedTrustedCommunity
This skill should be used when validating that an implementation plan was correctly executed. It verifies success criteria, runs tests, identifies deviations, and presents structured completion options including MR creation or discard.
SKILL.mdUpdated Apr 1, 2026
alexismanuel/workflow-review-code
development
VerifiedTrustedCommunity
This skill should be used when reviewing code changes in a branch against main/master/develop. It analyzes commits, integrates JIRA ticket and MR context when available, and produces a structured code review using Conventional Comments format.
SKILL.mdUpdated Apr 1, 2026
alexismanuel/workflow-research-codebase
development
VerifiedTrustedCommunity
This skill should be used when conducting comprehensive codebase research to answer questions, understand architecture, or prepare context for implementation planning. It spawns parallel sub-agents and synthesizes findings into a structured research document.
SKILL.mdUpdated Apr 1, 2026
alexismanuel/workflow-implement-plan
testing
VerifiedTrustedCommunity
This skill should be used when executing an approved implementation plan with batch checkpoints. It implements tasks in batches of 3, stops for review after each batch, and handles mismatches or blockers by asking for guidance rather than guessing.
SKILL.mdUpdated Apr 1, 2026