.config/opencode/skills/mr-tracker/SKILL.md
Tracks and monitors GitLab merge request activity including comments, status, and real-time updates
npx skillsauth add alexismanuel/dotfiles mr-trackerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Ensure you have the required dependencies:
# GitLab CLI
pip install glab
# Or follow installation instructions at https://gitlab.com/gitlab-org/cli
# jq for JSON processing (usually pre-installed on most systems)
# On macOS: brew install jq
# On Ubuntu: sudo apt-get install jq
Make sure the script is executable:
chmod +x scripts/mr_tracker.sh
./scripts/mr_tracker.sh comments 123
./scripts/mr_tracker.sh comments 123 5 # Show only 5 most recent comments
./scripts/mr_tracker.sh current
./scripts/mr_tracker.sh watch 123 30 # Check every 30 seconds
./scripts/mr_tracker.sh status 123
./scripts/mr_tracker.sh help
comments <mr_iid> [limit]Displays comments for a specific merge request with rich context including:
currentLists all merge requests for your current git branch, showing:
watch <mr_iid> [interval]Monitors an MR for new comments in real-time:
status <mr_iid>Shows comprehensive MR information:
The MR tracker assumes the project path cnty-ai/continuity. To change this, modify the project path in scripts/mr_tracker.sh:
# Change this line in multiple places:
projects/cnty-ai%2Fcontinuity/merge_requests/
# To your project:
projects/your-group%2Fyour-project/merge_requests/
The script uses jq for JSON processing and formatting. You can modify the jq queries in the script to customize the output format.
# Watch MR #123 for new comments every 30 seconds
./scripts/mr_tracker.sh watch 123 30
Output:
👀 Watching MR #123 for new comments (checking every 30s)...
Press Ctrl+C to stop
📊 Initial comment count: 3
🆕 New comments detected! (Mon Oct 19 10:30:15 EDT 2025)
================================
🔍 DIFF COMMENT
👤 John Doe (@johndoe) - 2025-10-19
📁 File: src/components/Button.tsx
📍 Line: 45→47
Consider adding error handling for the edge case here...
─────────────────────────────────────────────────
./scripts/mr_tracker.sh current
Output:
🔍 Looking for MRs on branch: feature/new-button
==========================================
MR #456: Add new button component (State: opened)
./scripts/mr_tracker.sh status 456
Output:
📊 MR #456 Status
==================
Title: Add new button component
State: opened
Author: Jane Smith
Source Branch: feature/new-button
Target Branch: main
Created: 2025-10-19T09:15:30.000Z
Updated: 2025-10-19T10:30:15.000Z
👍 Approvals: 2
🔁 Merge Status: can_be_merged
📝 Changes: 3 files, +45 -12
📝 Recent Comments:
📝 Comments for MR #456 (with file/line context):
==================================================
💬 GENERAL COMMENT
👤 John Doe (@johndoe) - 2025-10-19
Looks good! Just one suggestion...
──────────────────────────────────────────────────
"glab command not found"
glab auth login"jq command not found"
brew install jq (macOS) or sudo apt-get install jq (Ubuntu)"Not in a git repository"
current command"No MRs found for branch"
"MR #X not found"
For debugging API calls, you can run glab commands directly:
glab api "projects/cnty-ai%2Fcontinuity/merge_requests/123"
To extend this tool:
jq queries for different formattingThis skill is part of the OpenCode project and follows the same license terms.
development
Generate GitLab merge request descriptions from git commits with automatic categorization and Jira integration.
development
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.
development
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.
development
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.