Use when adding new error messages to React, or seeing "unknown error code" warnings.
npx skills add neurofoo/agent-skills --skill "aar"
Install specific skill from multi-skill repository
# Description
After-Action Review—structured debrief asking what was expected, what happened, why the difference, and what next. Use after projects, launches, presentations, or any significant event.
# SKILL.md
name: aar
description: After-Action Review—structured debrief asking what was expected, what happened, why the difference, and what next. Use after projects, launches, presentations, or any significant event.
user-invocable: true
After-Action Review
Conduct a structured debrief to extract learning from any significant event or experience.
Instructions
Work through the four core questions honestly and specifically. Focus on events and systems, not blaming individuals.
Output Format
Event: What are we reviewing?
Date: When did it happen?
Participants: Who was involved?
1. What Was Expected?
Before the event, what did we think would happen?
Goals/Objectives
- [What were we trying to achieve?]
Plan
- [What was the plan to achieve it?]
Success Criteria
- [How would we know if we succeeded?]
Assumptions
- [What did we assume would be true?]
2. What Actually Happened?
Facts only—what occurred, not why
Timeline
| Time | Event |
|------|-------|
| [When] | [What happened] |
Outcomes
- [What results did we get?]
Compared to Expected
| Expected | Actual | Gap |
|----------|--------|-----|
| [expectation] | [reality] | [+/-] |
3. Why the Difference?
Analysis of the gap between expected and actual
What Went Well (sustain these)
| Success | Contributing Factors |
|---------|---------------------|
| [what worked] | [why it worked] |
What Didn't Go Well (improve these)
| Problem | Root Cause |
|---------|-----------|
| [what failed] | [why it failed] |
Surprises
- [Things we didn't anticipate]
4. What Do We Do Next?
Specific actions to sustain or improve
Sustain (keep doing these)
| Action | Owner | How to Protect It |
|--------|-------|-------------------|
| [what to continue] | [who] | [mechanism] |
Improve (change these)
| Action | Owner | By When |
|--------|-------|---------|
| [what to change] | [who] | [deadline] |
Key Takeaways
Top 3 lessons from this review:
1. [Lesson]
2. [Lesson]
3. [Lesson]
Follow-up
When will we check if improvements are working?
Guidelines
- Do this soon—memory fades fast
- Be specific: "Communication failed" → "We didn't update Slack until hour 3"
- Balance: Include what went well, not just problems
- Assign owners: Insights without ownership become forgotten
- Make it safe: Blame shuts down honesty
$ARGUMENTS
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.