pre-mortem · borghei — Claude Code skill: what it does, how to install
pre-mortem — a skill for Claude Code that structures prospective hindsight exercises to anticipate launch disasters. Triggers during release planning, large migrations, or major architectural overhauls.
LicenseRef-MIT-Commons-Clause 124 installs ★ 1,183 updated 2026-11-08
npx skills add borghei/Claude-Skills --skill pre-mortem -a claude-codeWhat pre-mortem does
Runs across Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It asks the team to picture the project failing two weeks after launch, then reconstructs the exact missteps that caused the breakdown.
Reported issues get grouped into verified hazards (tigers), anxiety-driven assumptions (paper tigers), and suppressed team concerns (elephants). The included risk_categorizer.py script validates the generated JSON catalog. Running this validation utility requires a local Python 3 setup.
What it helps with
- identify unvoiced failure points before committing build resources
- filter out speculative panics from evidenced launch blockers
- assign concrete owners and decision dates to project-stopping items
- validate risk inventory files using
risk_categorizer.py
Example prompts for the agent
- Run a pre-mortem imagining our auth overhaul failed two weeks after launch
- Help sort these launch concerns into tigers, paper tigers, and elephants
- Check our pre-mortem entries using
risk_categorizer.pyto catch missing owners
How to install pre-mortem
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill pre-mortem -a claude-code2Manually: put the files in place
~/.claude/skills/pre-mortem/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pre-mortem/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill pre-mortem -a codex2Manually: put the files in place
.agents/skills/pre-mortem/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill pre-mortem -a cursor2Manually: put the files in place
.cursor/skills/pre-mortem/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install borghei/Claude-Skills project-management/discovery/pre-mortem2Manually: put the files in place
.github/skills/pre-mortem/SKILL.md1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill pre-mortem -a gemini-cli2Platform CLI
gemini skills install https://github.com/borghei/Claude-Skills --path project-management/discovery/pre-mortemManually: put the files in place
.devin/skills/pre-mortem/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill pre-mortem -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pre-mortem
How to install pre-mortem in Claude Code?
Run npx skills add borghei/Claude-Skills --skill pre-mortem -a claude-code in your terminal. You can also place the file directly at ~/.claude/skills/pre-mortem/SKILL.md.
What does pre-mortem do?
It orchestrates prospective hindsight sessions inspired by Gary Klein. The skill separates speculative worries from actual blockers, ensuring critical issues get an assigned owner.
What dependencies does risk_categorizer.py require?
It depends on a local Python 3 environment. The script flags invalid inputs, unassigned launch blockers, and hazards backed merely by speculative wording.
Similar skills
All skills for Notes, tasks and projects →pre-mortem by other authors comes first.