📋
WritingTypeScript

Write a Postmortem

by inkeep

Write a Postmortem is a Writing skill for Claude Code, published by inkeep in open-knowledge.

3.5K stars219 forkson inkeep/open-knowledgeAdded 2026/08/16+1% in starsRepository updated 2026/08/16
2nd-brainagent-skillsclaudecodexcompany-braindocsknowledge-knowledge-baseknowledge-managementllmllm-wikillm-wiki-karpathymarkdownmarkdown-editormdmdxnotespkmsecond-brainskills
Install in seconds
Install Write a Postmortem
Copy Write a Postmortem into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/software-lifecycle/write-a-postmortem ~/.claude/skills/write-a-postmortem

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/inkeep/open-knowledge.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
packages/server/assets/skills/packs/software-lifecycle/write-a-postmortem/SKILL.md in inkeep/open-knowledge
Installs to
~/.claude/skills/write-a-postmortem
Collection
One of 18 skills cataloged from this repository
Category
Writing1012 skills

What Write a Postmortem does

Write a Postmortem produces a blameless incident postmortem following the Google SRE shape — evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and owned+dated+verifiable action items. Use it when asked to write a postmortem, do an incident review, or document an outage.

Write a Postmortem is cataloged under Writing on DirSkills. Write a Postmortem comes from a repository tagged 2nd-brain, agent-skills, claude, codex and company-brain.

Documentation

README

Write a postmortem

The platform /open-knowledge skill still governs every markdown operation here — folder scope, the read/write tool surface, linking, and preview. This skill layers postmortem craft on top of it; it does not replace those rules.

A postmortem is not a status update and not a blame ledger. It is a durable, blameless reconstruction of one incident, built from evidence, that makes the system's failure mode legible and produces action items someone will actually verify. The value compounds only when postmortems that share a subsystem link to each other — that is how a repeat class stops being invisible.

This is the opening of the README. Read the full README on GitHub.

Commands Write a Postmortem provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /open-knowledge
  • /frame-a-proposal
  • /review-a-design

Frequently asked about Write a Postmortem

  • What else does inkeep publish alongside Write a Postmortem?

    Write a Postmortem is one of 18 skills that DirSkills catalogs from inkeep/open-knowledge, the repository it ships in. Its siblings there include Codebase Wiki, Consolidate Notes and Frame a Proposal. Each one is a separate skill with its own page in this directory, installs the same way Write a Postmortem does, and is maintained by inkeep in that same repository. The rest of the collection is listed on the inkeep/open-knowledge page.

  • How does Write a Postmortem compare to other Writing skills?

    Write a Postmortem ranks #190 by stars among the 1012 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Write a Postmortem against them. Open each page to compare what they document and how they install.

More from inkeep/open-knowledge

Write a Postmortem is one of 18 skills cataloged on DirSkills from inkeep/open-knowledge.

See all 18 skills
📚
2w ago

Codebase Wiki

Codebase Wiki guides agents in generating and refreshing a source-grounded, version-controlled wiki of a codebase, with per-folder rules, freshness and log discipline, and audience/depth knobs. Use when the project has a wiki/ knowledge base or when asked to generate or refresh a wiki of the codebase.
AI Engineering
3.5K219
📚
2w ago

Consolidate Notes

Consolidate Notes promotes existing research into a stable-status canonical article under articles/. Use it when a decision has been made and the team wants the source of truth written down, or when asked to consolidate, canonicalize, promote research, or supersede an older article.
Writing
3.5K219
📝
2w ago

Frame a Proposal

Frame a Proposal turns a problem into a reviewable RFC-shaped design document under proposals/. Use it when asked to frame a proposal, write an RFC, propose a design, pitch a change, or draft a PRD-style design doc.
Writing
3.5K219
📚
2w ago

Knowledge Base

Knowledge Base defines the three-layer source-grounded layout (external-sources, research, articles) and the per-folder rules and status flows for working in a Knowledge Base project. Use it when setting up or operating a project with ingest-research-consolidate stages.
Writing
3.5K219
📝
2w ago

Note Taking

Note Taking guides agents on how to work in a Plain Notes project, a flat notes folder plus a daily journal for jotting notes, capturing quick thoughts, and writing today's journal entry. Use it when the project has these folders or when asked to capture a thought or write a daily entry.
Writing
3.5K219
🤖
2w ago

Open Knowledge

Open Knowledge defines the agent-runtime contract for working inside an OpenKnowledge project, a markdown-CRDT knowledge base exposed over MCP. Use it when reading, listing, searching, editing, or linting any .md or .mdx file, and before any mcp__open-knowledge__* tool call.
AI Engineering
3.5K219