Skills for Real Engineers. Straight from my .agents directory.
after-action-report
Agent skill fromrampstackco/claude-skills
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
How to install after-action-report
npx skills add rampstackco/claude-skills# or add only this skill to Claude Code: copy the folder
skills/after-action-report/
# into
~/.claude/skills/after-action-report/ (all projects)
.claude/skills/after-action-report/ (one project)
1# After-Action Report23Run a structured retrospective on a launch, incident, or completed project. Produce actionable lessons, not just a document.45This skill is for after-the-fact analysis. For active incident response, use `incident-response`. For planning launches, use `launch-runbook`.67---89## When to use1011- After any incident (any severity)12- After every major launch13- At the end of a project (sprint retro, quarterly retro, project closeout)14- When a recurring issue has happened enough times to demand investigation15- When a decision didn't work out and the team wants to learn1617## When NOT to use1819- During an active incident (use `incident-response`)20- For pre-launch planning (use `launch-runbook`)21- For one-off bug fixes that don't merit broad analysis2223---2425## Required inputs2627- The event being analyzed (incident, launch, project)28- A timeline reconstructed from logs, chat, tickets29- Participant accounts of what they observed and did30- Outcomes and impact (what actually happened to users, the business)3132---3334## The framework: blameless analysis3536The most important principle: blameless. Without it, retrospectives produce hidden information and theatrical lessons rather than real ones.3738### What blameless means3940- Focus on systems, not individuals41- Assume everyone made reasonable decisions given what they knew at the time42- The question is "why was this decision reasonable to make?" not "who screwed up?"43…
Excerpt shown under the repository's MIT license.
More skills in claude-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
