Blameless Post-Mortem Writer
Blameless review of one incident or failed project: sourced timeline, real impact, contributing factors, and owned, verifiable actions.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good moment to evaluate. You'd want to revisit your original assumption about what success looked like, check actual results against those targets, understand what surprised you. Did you document your pre-decision hypothesis? What were the success metrics? What actual outcomes did you see? Doing a thoughtful retrospective helps close the loop.
Delivers POST-MORTEM REPORT showing ORIGINAL ASSUMPTIONS: price point, adoption curve, customer segment response, revenue target. ACTUAL OUTCOMES: revenue delta percent, customer retention versus forecast, segment split. ASSUMPTION SCORING: hit, miss, or exceeded on each dimension. DISSENT RECORD: capture minority views at decision time. ROOT CAUSE ANALYSIS: what drove variance: market, execution, or assumption flaw, and FORWARD GUIDANCE: go/stay/pivot decision with conviction level. Closes the strategic sprint loop. Activates automatically when the request matches post-mortem. For executing decisions effectively.
About this skill
Most post-mortems name 'human error' and end with 'be more careful'. This one rebuilds what happened from evidence, finds the conditions that made failure easy, and ends with a few actions someone owns and can verify.
What it does
- Builds the timeline from logs and system timestamps, marking gaps to confirm
- Quantifies impact: duration, affected users, revenue, SLA or error budget
- Separates the trigger from contributing conditions and detection delays, with 5 whys used carefully
- Rewrites hindsight and blame into blameless findings
- Produces 3-7 ranked actions with owner, due date, and a done-when test, plus an optional customer-facing RCA
What you get
An internal post-mortem document, a 60-minute review agenda, and a short customer RCA when needed.
Best for
Engineering, SRE, and product teams after an outage, data incident, failed migration, or missed launch.
SKILL.md preview
---
name: post-mortem
description: Run and write a blameless post-mortem for one incident or failed project - an outage, data loss, security event, botched launch, missed deadline, or a decision that did not deliver - with an evidence-based timeline, impact in real numbers, contributing factors instead of a single "root cause", and a small set of owned, dated, verifiable action items. Use when the user says "write the postmortem", "incident review for yesterday's outage", "what went wrong with the launch?", "run a 5 whys on this", "the migration failed, help me write it up", "RCA for the customer", or casually "we screwed up, how do we make sure it doesn't happen again?".
---
… (sign up to view the full skill)More development skills
View all Development skills →Chaos Experiment and Game Day Planner
Plans chaos experiments and game days: hypothesis, blast radius, abort conditions, tool manifests, rollback, and post-run review.
Claude Code Cost and Latency Routing
Configure Claude Code Router with model tiers, explicit fallbacks, compatibility checks, and a cost-aware validation plan.
CI/CD Pipeline Builder with Gated Deploys
Generates CI/CD workflows from your repo's real stack: cached fast-fail checks, pinned actions, and staging-to-prod deploys with gates.
Terraform Modules and Safe Deployments
Get reusable Terraform modules, safe state migrations, explicit provider wiring, and CI gates tied to reviewed plans.