agentleFS
runxhqrunxhq/runx/skills/postmortem-maker/SKILL.md

postmortem-maker

Skill97 starsChanged 32 days agoApache-2.0View on GitHub

Turn 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.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read incident_ref and incident_fragments from step inputs.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Postmortem Maker

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

  1. Native data.digest binds the exact fragment set.
  2. The drafting agent assembles a summary, an evidence-cited timeline, a root cause with a status of known, suspected, or unknown, open unknowns, and owned action items.
  3. 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.
  4. The verdict separates completeness from honesty: a fully cited postmortem with a supported root cause and no open unknowns is publishable and carries a publish proposal gated on a human approver through send-as; a grounded but incomplete one seals needs_more_evidence and 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.