cfn-retro
MUST BE USED at end of each week to review velocity, identify hotspot files, and surface workflow bottlenecks. Weekly retrospective from git history. Analyzes velocity, session patterns, file hotspots, commit types, and streaks.
Best use case
cfn-retro is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
MUST BE USED at end of each week to review velocity, identify hotspot files, and surface workflow bottlenecks. Weekly retrospective from git history. Analyzes velocity, session patterns, file hotspots, commit types, and streaks.
Teams using cfn-retro should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cfn-retro/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cfn-retro Compares
| Feature / Agent | cfn-retro | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
MUST BE USED at end of each week to review velocity, identify hotspot files, and surface workflow bottlenecks. Weekly retrospective from git history. Analyzes velocity, session patterns, file hotspots, commit types, and streaks.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# CFN Retro **Purpose:** Analyze git history to surface development patterns, velocity trends, and improvement opportunities. ## Usage Invoke as `/retro` or `/retro <window>` where window is: 7d (default), 24h, 14d, 30d ## Analysis Phases ### Phase 1: Data Collection - `git log --format` for the specified window - Parse commits by: author, timestamp, type (feat/fix/refactor/chore/docs/test), files changed, insertions/deletions ### Phase 2: Metrics Output a metrics table: - Total commits - Lines changed (insertions + deletions) - Test ratio (test commits / total commits) - Feat/fix/refactor breakdown - Files touched ### Phase 3: Session Analysis Group commits by 45-minute gaps to identify work sessions: - Deep work sessions (3+ commits, 1+ hour) - Micro sessions (1-2 commits, quick fixes) - Peak hours (when most commits happen) ### Phase 4: Hotspot Analysis Most frequently changed files in the window. Files changed 5+ times are hotspots worth investigating for: - Instability (frequent bug fixes) - Active development (new feature work) - Potential extraction (doing too many things) ### Phase 5: Streak Tracking Count consecutive days with at least one commit. Surface current streak and longest streak in window. ### Phase 6: Commit Type Analysis Categorize using conventional commit prefixes. Flag: - High fix ratio (>40% of commits are fixes, may indicate instability) - Low test ratio (<10% of commits touch tests, may indicate coverage gaps) - Refactor clusters (3+ refactors in a row, good sign of paying down debt) ### Phase 7: Summary Concrete, specific observations. No generic praise. Each observation anchored to actual data from the analysis. Format: 3-5 bullet points, each citing specific numbers and file names. ## Output Format ``` ## Retro: <project> (<window>) ### Metrics | Metric | Value | |--------|-------| | Commits | N | | Lines changed | +X / -Y | | Test ratio | N% | | Streak | N days | ### Sessions - N deep work sessions, N micro sessions - Peak hours: HH:00-HH:00 ### Hotspots 1. path/to/file (N changes) 2. ... ### Commit Types feat: N | fix: N | refactor: N | chore: N | test: N | docs: N ### Observations - ... ``` ## Integration - No external dependencies. Uses only git log and bash. - Results are ephemeral (displayed, not persisted) unless user asks to save.
Related Skills
Retrospective Report Generator Skill
## Purpose
supabase-schema-sync
Introspects Supabase DB after migrations and updates project db-query skill with current schema. Run after any migration to keep agent context accurate.
commit
Stage, commit, and push changes using a background github-commit-agent. Accepts optional args for message override or push control.
cfn-vote-implement
MUST BE USED after cfn-dry-review or cfn-alpha-launch:manifest produces a manifest. Also the verification phase of /cfn-loop-task. Do not manually implement code review suggestions - always route through this skill. 3-agent specialized voting. Unanimous (3/3) auto-implemented with TDD. 2/3 routed to product-owner agent. 1/3 surfaced to user via AskUserQuestion (batched 4 per call, at end).
cfn-utilities
Reusable bash utility functions for CFN Loop - logging, error handling, retry, file operations. Use when you need structured logging, atomic file operations, retry logic with exponential backoff, or standardized error handling in bash scripts.
CFN Test Runner Skill
**Version:** 1.0.0
cfn-test-framework
Test execution, running, and webapp testing for CFN
cfn-task-planning
Classify tasks, initialize structured configs with scope boundaries, decompose complex tasks
Specialist Injection Skill
## Purpose
!/bin/bash
# cfn-task-intelligence.sh
Task Complexity Estimator
**Version:** 1.0.0
task-classifier
Analyzes task descriptions and classifies them into categories for agent selection