writing-postmortems skill (riekelt) for Claude Code: blameless postmortems from evidence

Makes Claude write blameless postmortems from evidence: a checkable timeline, the mechanism of the failure and owned action items.

Installs: 20.4K; on skills.sh
Stars: 36; on GitHub
Updated: Sep 2026; last repo commit

writing-postmortems gives Claude a fixed postmortem outline: summary, impact, timeline, root cause and contributing factors, wrong turns during the response, action items and sign-off. Blameless means naming roles, gates and missing guards, never people. Every timeline entry must trace to something checkable, such as an alert, a log line or a commit. It is for after an incident, not during one, and it lists technical-writing as required background.

Good for

Engineers writing up an outage, data issue or near miss
Teams turning an incident channel or alert log into a lasting document
Leads who want blameless write-ups that produce action items

Install writing-postmortems

Claude Code

Copy this prompt.

Install the writing-postmortems skill in Claude Code. Run this command:

/plugin marketplace add riekelt/technical-writer
/plugin install technical-writer@technical-writer

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route, not both, or you get every skill twice. The skills CLI route must include technical-writing, which writing-postmortems lists as REQUIRED BACKGROUND in its SKILL.md.

From the project README. Source.

What's in the skill

When it loads

Use when writing a postmortem, incident report, or root-cause analysis after an outage, a defect that reached users, a data issue, or a near miss - or when turning an incident channel, alert log, or war-room thread into a durable document. Encodes the blameless framing, the evidence-only timeline, contributing factors, and owned action items. Use whenever something broke and the write-up must outlive the incident.

Sections in SKILL.md

Overview
When to invoke, and not
Skeleton
Summary
Impact
Timeline
Root cause and contributing factors
Wrong turns during the response
Action items
Sign-off
Rules

Key facts

Author: riekelt (owner of the GitHub repo)
License: MIT (LICENSE file and plugin manifest)
Installs on skills.sh: 20,426 as of 2026-11-02
GitHub stars: 36 for the whole riekelt/technical-writer repo, 2026-11-02
What is inside: 1 file: SKILL.md
Needs: The technical-writing skill (SKILL.md lists it as REQUIRED BACKGROUND)
Part of: The technical-writer plugin: 11 skills, 2 agents and 2 commands
Last repo commit: 2026-09-13
Works in: Claude Code per the README install section. The repo also ships Codex and Cursor plugin manifests.

What it includes

Seven sections from summary to sign-off
Summary, Impact, Timeline, Root cause and contributing factors, Wrong turns during the response, Action items and Sign-off, under a header table with incident date, duration, severity and status.
Write · Skeleton
Each entry traces to an alert, log line, commit or message
Timestamps come from the systems rather than memory. Where memory is the only source, the document says so, and interpretation stays out of the timeline.
Try: “Write a postmortem from this incident channel export and the deploy log.”
Write · Evidence-only timeline
Names roles, gates and dependencies, never people
Naming a person stops at be more careful. Naming a structure produces an action item. Wrong first fixes are kept as content.
Write · Blameless rules
Each has an owner and an acceptance check, filed as issues
Items follow the writing-issues skill and are linked from the postmortem. When filing is not possible, each is marked as to be filed and the postmortem stays Draft.
Write · Action items
Reviewed postmortems change only by dated addenda
A reviewed postmortem is not rewritten. Near misses use the same outline, with impact described as the counterfactual it is.
Write · Immutability and near misses

From the official docs

Permissions

Low risk

Claude reads whatever incident material you give it. Strip secrets and customer data before you paste logs or chat exports.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Incident material is your input
SKILL.md has Claude build the timeline from alerts, log lines, commits and messages. Our advice: remove secrets and customer data from logs and chat exports before you give them to Claude. github.com
The plugin route adds 2 agents and 2 commands
The plugin ships agents prose-reviewer and doc-grounder (both with Read, Glob, Grep and Bash tools) and the commands /prose-review and /ground-docs. The plugin folder has no hooks or MCP config. Use the skills command in the install box if you want only this skill. github.com

Technical details

Turning on read-only	No read-only mode. The skill tells Claude to write or edit documents.
Sign-in and keys	SKILL.md names no account or API key.
Data retention	SKILL.md names no logging or telemetry.
Scopes	Claude reads incident material you provide and writes the postmortem document in your repo

Questions

What does writing-postmortems do?

It makes Claude write a blameless incident report from evidence, with a timeline anchored to logs, alerts and commits and action items that each have an owner.

How do I install writing-postmortems?

Use the install box at the top of this page. The plugin route installs the whole set. The skills command route names technical-writing as well, because this skill lists it as required background.

Can I use it during an incident?

No by its own rule. SKILL.md says not to invoke it during the live incident, where the runbook governs, and not for a status update to stakeholders.

Does it name who caused the incident?

No. SKILL.md says blameless means structural: name the role, gate or missing guard, never the person. Action-item ownership is assignment and lives in the linked tracker issue.

Does it file the action items?

SKILL.md says action items follow the writing-issues skill and are filed and linked. When filing is not possible from where Claude sits, each is marked as to be filed and the postmortem stays a draft.

Is writing-postmortems safe to install?

The skill folder holds only SKILL.md, so it bundles no scripts. It makes Claude read incident material you give it and write a postmortem document in your repo. Review the diff, as you would any edit. Our advice: remove secrets and customer data from logs and chat exports before you hand them over.

Can I use writing-postmortems in the Claude app or Cursor?

The README documents Claude Code, and the repo also ships Codex and Cursor plugin manifests. It does not mention the Claude app. Our advice: this page offers no Claude app upload because the skill works on documents inside a repository, so use Claude Code or Codex.

Information

updated Nov 2, 2026

Repository: riekelt/technical-writer
Folder: plugins/technical-writer/skills/writing-postmortems

riekelt/technical-writer skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

README · github.com
marketplace.json · github.com
writing-postmortems on skills.sh · skills.sh
SKILL.md · github.com
LICENSE · github.com
writing-issues SKILL.md · github.com