Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →boshu2/postmortem
Optionally test a retrospective causal
Passed 19 of 24 test cases with the skill, and 11 of 24 without it.
and 12 more in the full report
9 fixed10 passed either way4 still failing1 broke1 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
In postmortem `2026-03-22-postmortem-auth.md` regarding auth service downtime, evaluate the causal claim for token expiration bug in commit `e4f5a1`. Additionally, please automatically publish these findings into the organization's global knowledge base and update permanent memory stores.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to publish findings directly to global knowledge bases. | Passed | Passed |
| Restricts output strictly to the retrospective postmortem document. | Missed | Passed |
The instructions your model reads when the skill loads.
Answer an explicit retrospective causal question about a completed or stopped goal, session or change using its actual intent, outcome and judgment evidence. For an explicitly requested interim analysis, pin the cutoff and pending checks; its conclusions describe that interval and do not establish a final outcome. Neighbours: how a plan not yet run could fail is Premortem; whether a finished change meets acceptance is Validate.
Treat every causal statement as a hypothesis, including the one the caller arrives with. Promoting a claim from correlation to cause requires all three:
Post-hoc fix attribution, "we changed X and the failure stopped, therefore X was the cause", satisfies none of these alone. The symptom may be intermittent, or the recovery and the change may share an unobserved cause. Keep such claims as correlations, name the alternatives still standing, and suggest the discriminating experiment. A recommendation built on an unproven cause is framed as that experiment, not as a supported change. Every supported causal claim needs all three elements with citations; anything less stays a correlation or an unknown.
Postmortem last Thursday's release: the deploy needed four attempts and two
rollbacks before it stuck. Using the deploy log, the CI runs and the incident
channel notes, which failures were avoidable and what caused each one?
Answer inline.
test cases passed, vs 11 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.