after-action-report
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.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines what the skill does, when to use it, and provides comprehensive trigger terms covering abbreviations, synonyms, and situational contexts. It uses proper third-person voice, is specific about the outputs (timeline, root cause analysis, contributing factors, actionable lessons), and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'capture timeline, root cause analysis, contributing factors, and actionable lessons' and specifies the contexts (launch, incident, completed project). Very concrete about what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (run a structured after-action review capturing timeline, root cause analysis, contributing factors, and actionable lessons) and 'when' (explicit 'Use this skill whenever...' clause plus detailed trigger list and situational triggers). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including abbreviations and synonyms: 'postmortem, retrospective, AAR, after-action review, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys.' Also includes situational triggers like 'just shipped something' or 'just resolved an incident.' | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around post-event retrospective analysis. The specific trigger terms like 'AAR', 'postmortem', 'five whys', 'blameless postmortem' are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides genuinely actionable guidance for running after-action reviews. Its main strengths are the concrete examples (five whys walkthrough, action item table with criteria), clear workflow sequencing, and comprehensive output template. Its main weakness is length — some sections explain concepts Claude likely already understands (blameless culture philosophy, general meeting facilitation) and the failure patterns section, while useful, could be more concise.
Suggestions
Trim the 'What blameless means / does not mean' section to 2-3 bullet points total — Claude understands the concept and needs only the specific framing to apply.
Move the 'Failure patterns' section to a reference file (e.g., references/aar-antipatterns.md) to reduce the main skill's token footprint while preserving the information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-structured but includes some content Claude already knows (e.g., explaining what 'blameless' means in detail, general facilitation advice). The failure patterns section and some of the meeting logistics could be trimmed. However, the framework-specific guidance (five whys example, action item criteria, output template) earns its place. | 2 / 3 |
Actionability | Provides a concrete five whys example, a specific action items table format with clear criteria (specific, owned, dated, sized, closeable), a complete output template with all fields, and a detailed meeting agenda with time allocations. This is copy-paste ready for running an AAR. | 3 / 3 |
Workflow Clarity | The 6-step workflow (Schedule → Gather inputs → Run meeting → Write document → Distribute → Track action items) is clearly sequenced with explicit validation checkpoints: action items must be tracked to closure, unclosed items resurface in the next AAR, and the timeline serves as the 'source of truth' where disagreements get resolved. The feedback loop for action item tracking is explicit. | 3 / 3 |
Progressive Disclosure | The skill references a template file at `references/aar-template.md` which is good, but the main document is quite long (~250 lines) and could benefit from splitting the detailed framework sections (root cause analysis techniques, failure patterns) into separate reference files. The inline content is well-organized with clear headers but borders on monolithic. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.