Generates data-driven engineering retrospective reports based on git repository history.
Install
mkdir -p .claude/skills/retro-mrunreal && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15880" && unzip -o skill.zip -d .claude/skills/retro-mrunreal && rm skill.zipInstalls to .claude/skills/retro-mrunreal
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Data-driven retrospective from git history. Analyzes commits, contributors, and trends. Produces actionable reports.Key capabilities
- →Gather git commit data
- →Compute metrics like LOC changes and test ratio
- →Analyze work focus distribution
- →Produce retrospective reports
- →Save JSON snapshots for trend tracking
How it works
The skill runs git commands to collect data, computes various metrics, analyzes patterns, and then produces a report using a predefined template.
Inputs & outputs
When to use retro
- →Generate 7-day retro
- →Analyze contribution trends
- →Track code change volume
- →Measure shipping cadence
About this skill
/retro — Engineering Retrospective Workflow
Data-driven retrospective from git history. Analyzes commits, contributors, and trends. Produces actionable reports.
Usage
/retro — Last 7 days
/retro --days 14 — Last 14 days
/retro --since 2024-01-01 --until 2024-01-31 — Custom range
/retro --save — Save JSON snapshot for trend tracking
Procedure
1. Gather Data
Run git commands to collect commits, authors, file changes, and timestamps for the specified period.
2. Compute Metrics
- Commits (total + per-contributor)
- LOC added/removed, net change
- Test ratio (commits touching test files vs. total)
- Fix ratio (commits with "fix"/"bug" in message vs. total)
- Peak activity hours
- Biggest ship (largest change by scope)
3. Analyze Patterns
- Work focus distribution (features, fixes, refactoring, infra)
- Shipping cadence (regular vs. batched)
- Test-to-feature code ratio trends
- Contributor patterns
4. Produce Report
Use the template at templates/retro-report.md for output format.
5. Save Snapshot (optional, with --save)
Save a JSON snapshot for trend comparison across retros.
Scripts
- Windows:
scripts/retro.ps1 - Unix:
scripts/retro.sh
Agent Instructions
- Run the retro script for the user's platform to gather raw data.
- Analyze the data per the procedure above.
- Produce the report using the template.
- Always follow
.github/agents/retro.agent.mdfor persona and rules.
When not to use it
- →When not specifying a time period for analysis
- →When not using the provided scripts for data gathering
- →When not following the `retro-report.md` template for output
Limitations
- →Requires git history as input
- →Requires scripts for data gathering
- →Requires `templates/retro-report.md` for output format
How it compares
This skill provides a data-driven retrospective by analyzing git history for specific metrics and patterns, unlike subjective team discussions.
Compared to similar skills
retro side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| retro (this skill) | 0 | 5mo | Review | Intermediate |
| github-project-board-generate-board-analytics | 0 | 4mo | Review | Beginner |
| prompt-analysis | 8 | 4mo | Review | Beginner |
| bv | 3 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
github-project-board-generate-board-analytics
vamseeachanta
Sub-skill of github-project-board: Generate Board Analytics.
prompt-analysis
git-ai-project
Analyze AI prompting patterns and acceptance rates
bv
Dicklesworthstone
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
org-health-diagnostic
alirezarezvani
Cross-functional organizational health check combining signals from all C-suite roles. Scores 8 dimensions on a traffic-light scale with drill-down recommendations. Use when assessing overall company health, preparing for board reviews, identifying at-risk functions, or when user mentions org health, health check, or health dashboard.
rollup
Alexanderjcarls
Coverage summary — per-scope, per-system, or per-migration-state breakdown of article + capability + functionality counts.
churn-detector
ekatasingh1107
>