retro

Reflect on the completed feature, document lessons learned, and improve workflows.

12 stars

Best use case

retro is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Reflect on the completed feature, document lessons learned, and improve workflows.

Teams using 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

$curl -o ~/.claude/skills/retro/SKILL.md --create-dirs "https://raw.githubusercontent.com/lionbenjamin/agent-templates/main/skills/retro/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/retro/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How retro Compares

Feature / AgentretroStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Reflect on the completed feature, document lessons learned, and improve workflows.

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

# Retro Skill

Continuous improvement through structured reflection.

## When to Activate

This skill is relevant when:
- Feature deployment is complete
- Reflecting on what was learned
- Improving team processes
- Updating workflows and documentation

## Core Principles

### Systemic Improvements
- Success or failure, how can we improve?
- Make it easier next time
- Make it safer next time
- Make it faster next time

### Quality Over Speed
- Long-term code health
- Maintainability matters
- Technical debt awareness
- Sustainable pace

### Skeptical & Thorough
- Question assumptions
- Did it work because it's robust?
- Or did we get lucky?
- Root cause analysis

### Constructive
- Improve the system
- Not just critique
- Actionable recommendations
- Update workflows and docs

## Quick Checks

When conducting retrospectives, verify:
- [ ] Feature completion reflected on
- [ ] What went well identified
- [ ] What went wrong identified
- [ ] What could improve identified
- [ ] Technical insights captured
- [ ] Process insights captured
- [ ] Lessons documented with date and feature
- [ ] Impact level assessed (High/Medium/Low)
- [ ] Actionable next steps defined
- [ ] Workflow changes identified
- [ ] Specific files to update listed
- [ ] Changes applied if approved
- [ ] Team knowledge improved
- [ ] System improved for next time

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.