Postmortem Maker
SkillMonitoring & opsTurn resolved-incident fragments into a traceable postmortem that separates fragment-cited facts from hypotheses, blocks publication while unknowns remain, and keeps the comms send behind a human gate.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Postmortem Maker skill
What this skill tells your AI
The instructions your AI receives, as published by runxhq/runx in skills/postmortem-maker/SKILL.md and read by ahel’s review.
Produce a postmortem that never pretends unknowns are facts. The supplied incident fragments are the only evidence; the drafting agent separates what happened from what is suspected, and deterministic code verifies every claimed fact against the fragments. Publication is a gated proposal, never an effect of this skill.
Procedure
- Native
data.digestbinds the exact fragment set. - The drafting agent assembles a summary, an evidence-cited timeline, a root
cause with a status of
known,suspected, orunknown, open unknowns, and owned action items. - Deterministic enforcement checks every timeline entry and any non-unknown root cause: the cited fragment must exist and the quote must appear verbatim in that fragment's text. An invented citation refuses the whole run. Action items must carry an action and an owner.
- The verdict separates completeness from honesty: a fully cited postmortem
with a supported root cause and no open unknowns is
publishableand carries a publish proposal gated on a human approver throughsend-as; a grounded but incomplete one sealsneeds_more_evidenceand publishes nothing.
To build the fragment set from live systems, compose web-fetch or
data-store reads upstream; the digest binds whatever evidence was supplied.
incident-commander owns running the incident; this skill owns explaining it
afterward.
Output
postmortem (runx.postmortem.v1) carries decision (publishable,
needs_more_evidence, refused), summary, the cited timeline,
root_cause, unknowns, action_items, the gated publish_proposal or
null, validation, and the fragments digest. publish_performed is always
false.
Inputs are incident_ref and incident_fragments.
Agent task contracts
postmortem-maker-draft
Read incident_ref and incident_fragments from step inputs. Return
postmortem_draft with summary, timeline entries (each entry,
fragment_id, quote), root_cause (status, and for known or suspected a
statement, fragment_id, and quote), unknowns, and action_items
(each action, owner). Quote fragments verbatim, mark anything the
fragments do not support as unknown rather than asserting it, and never
invent fragments, quotes, owners, or deadlines.
Signals
- GitHub stars
- 87
- Forks
- 101
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
postmortem-maker- Source
- github.com/runxhq/runx