postmortem-writing Skill (wshobson) for Claude: What It Does and How to Install It

Helps Claude write blameless postmortems, with a timeline, root cause analysis, 5 Whys and action items.

Installs: 11K; on skills.sh
Stars: 42.1K; on GitHub
Files: 1; besides SKILL.md
Updated: Oct 2026; last repo commit

This is a writing guide for Claude, from wshobson's agents collection. It sets out blameless principles, six triggers for when to hold a postmortem and a day-by-day timeline. It also gives three templates (a standard postmortem, a 5 Whys analysis and a quick postmortem), a facilitation guide for the meeting and an anti-pattern table.

It loads when you run an incident review, write a postmortem document or improve incident response. It bundles no scripts. You give Claude the facts of the incident, and it drafts the document.

Good for

On-call engineers and incident leads writing up an outage
Engineering managers who run postmortem meetings
Teams that want one consistent postmortem format

Install postmortem-writing

Claude Code

Copy this prompt.

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

/plugin marketplace add wshobson/agents
/plugin install incident-response@claude-code-workflows

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. The plugin routes install the whole incident-response plugin: 6 agents, 2 commands and 4 skills (counted from the plugin folder in the repo tree, which has no hooks or MCP config files). The skills-only routes install just this skill, with no agents or commands. The skill needs the facts of your incident from you.

From the project README. Source.

What's in the skill

When it loads

Write effective blameless postmortems with root cause analysis, timelines, and action items. Use when conducting incident reviews, writing postmortem documents, or improving incident response processes.

Sections in SKILL.md

When to Use This Skill
Core Concepts
1. Blameless Culture
2. Postmortem Triggers
Quick Start
Postmortem Timeline
Templates and detailed worked examples
Template 2: 5 Whys Analysis
Problem Statement
Analysis
Why #1: Why did the service fail?
Why #2: Why were database connections exhausted?
Why #3: Why did the code bypass the connection pool?
Why #4: Why wasn't this caught in code review?
Why #5: Why isn't there a safety net for this type of change?
Root Causes Identified

Key facts

Author: wshobson (repo owner)
License: MIT
Installs on skills.sh: 11,025 (Nov 2, 2026)
GitHub stars: 42,081 for the whole wshobson/agents repo (Nov 2, 2026)
Last repo commit: Oct 30, 2026
What it includes: 2 files including SKILL.md: references/details.md holds the standard postmortem template (no scripts)
Needs: Facts about the incident from you, such as the timeline, metrics and who did what. SKILL.md lists no tools or keys
Part of: The incident-response plugin in wshobson/agents. Counted from the plugin folder: 6 agents, 2 commands and 4 skills
Works in: Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi, per the README. Skills-only installers ask which tool you use

What it includes

Contrasts blame-focused with blameless questions
For example, ask 'What conditions allowed this?' instead of 'Who caused this?'.
Try: “Write a blameless postmortem for last night's 47-minute database outage.”
Read · Blameless culture
Six cases that call for a postmortem
SEV1 or SEV2 incidents, customer-facing outages over 15 minutes, data loss or security incidents, near-misses, novel failure modes and unusual interventions.
Read · Postmortem triggers
Day 0 incident to quarterly pattern review
Draft in days 1-2, meeting in days 3-5, finalize and ticket in days 5-7, actions from week 2.
Read · Postmortem timeline
Summary, timeline, root cause, detection, response, impact, lessons, actions (details.md)
A full document skeleton with sections for what went well, what went wrong and where we got lucky.
Write · Template 1: standard postmortem
Five why questions, each with an answer and evidence
Ends with root causes and a table of systemic improvements by type: prevention, detection or mitigation.
Write · Template 2: 5 Whys
A short format for minor incidents
Date, duration and severity, what happened, a short timeline, root cause, fix and lessons.
Write · Template 3: quick postmortem
A 60-minute meeting plan in five parts
Opening (5 min), timeline review (15), analysis (20), action items (15) and closing (5).
Read · Facilitation guide
Five common mistakes and better approaches
Blame game, shallow analysis, no action items, unrealistic actions and no follow-up.
Read · Anti-patterns

From the official docs

Permissions

Low risk

The main risk is sensitive incident detail ending up in a shared document. Review the draft before you send it.

What it can do

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

Watch out for

The plugin route installs more than this skill
The incident-response plugin has 4 skills, 6 agents and 2 commands. The repo tree shows no hooks or MCP config files in its folder. The skills-only routes install only this skill. github.com
Incident details can be sensitive
Postmortems often hold customer impact, internal system names and decisions by named people. Share only what the document needs and review the draft before you circulate it. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode. Use version control.
Scopes	Claude drafts postmortem documents from the incident details you give it and may save them as files in your project

Questions

What does the postmortem-writing skill do?

It gives Claude a format and rules for blameless postmortems. Claude uses it to draft the timeline, root cause analysis and action items, and to help plan the review meeting.

How do I install postmortem-writing?

Use the install box at the top of this page. It lists the plugin route and two skills-only commands: npx skills add wshobson/agents --skill postmortem-writing and gh skill install wshobson/agents postmortem-writing (GitHub CLI 2.90 or later). The skills-only commands skip the plugin's agents and commands.

What are the three templates?

A standard postmortem (in details.md), a 5 Whys analysis and a quick postmortem for minor incidents. The last two are in SKILL.md.

Does it connect to PagerDuty, Slack or Jira?

SKILL.md names no integrations. It mentions tracking action items in a ticketing system but defines no tool for it, so you paste in the incident facts yourself.

When should I write a postmortem?

SKILL.md lists six triggers, including SEV1 or SEV2 incidents, customer-facing outages longer than 15 minutes, data loss or security incidents, and near-misses that could have been severe.

Is it safe?

Installing it adds a guide and one reference file, with no scripts. It does not define any tool that reads your systems. Incident write-ups can contain customer data, internal hostnames and names of people, so check what you paste into the chat and what ends up in the document.

Is this skill from Anthropic?

No. It is in wshobson/agents, a community collection. The skill sits in the incident-response plugin there.

Should I install the whole incident-response plugin?

Only if you want the rest. The README documents a plugin route for Claude Code and Codex. The plugin folder holds 4 skills, 6 agents and 2 commands, and the repo tree shows no hooks or MCP config files in it.

Information

updated Nov 2, 2026

Repository: wshobson/agents
Folder: plugins/incident-response/skills/postmortem-writing

wshobson/agents skills.sh

Sources

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

Show all 4

postmortem-writing SKILL.md · github.com
wshobson/agents README · github.com
incident-response plugin.json · github.com
postmortem-writing details.md · github.com