01
It starts by itself
launch plan changed. Runs in GitHub Actions or Claude Code routine.
- ↻ launch plan changed
push touching the PRD or launch plan file
phuryn · 10K installsPre-mortem skill
Runs by itself, when your launch plan changes.
Launch risks are found while you can still fix them.
Install the Pre-mortem skill and make it a habit: follow https://gethabit.dev/skills/phuryn/pre-mortem.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
10K installs27K starsMIT licenceSource on GitHub ↗
Pre-mortem
by phuryn · 10K installs
The skill
Imagines your launch failed to find the risks.
Only when you ask.
Safer launches
Launch risks are found while you can still fix them. Fewer bad surprises.
↻ Runs by itselfwhen your launch plan changes
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after one plan per run and at most one retry.
- 01
Read the plan
Your agent reads the PRD or product plan and notes the market, assumptions and timeline.
- 02
Imagine failure
It pictures the launch two weeks out going badly and asks what was missed.
- 03
Sort the risks
Each risk becomes a Tiger, a Paper Tiger or an Elephant, with Tiger as the default when unsure.
- 04
Rank the Tigers
Tigers are marked Launch-Blocking, Fast-Follow or Track.
- 05
Plan the fixes
Every Launch-Blocking Tiger gets a mitigation, an owner role and a due date.
- 06
Save the report
The analysis is saved as PreMortem-[product-name]-[date].md and the board notes open blockers.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inPreMortem-*.md, loops/pre-mortem-loop/**
- Talks tono outside service
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Pre-mortem skill helps.
Use it when
- ✓ a launch is a few weeks away
- ✓ a PRD needs a stress test
- ✓ the team avoids hard questions
Skip it when
- – there is no plan written yet
- – you need a post-launch incident review
Pre-mortem skill, answered.
What is the difference between a Tiger and an Elephant?
A Tiger is a risk you can see clearly. An Elephant is a doubt nobody talks about and that needs checking before launch.
Why run it more than once?
The skill suggests a second look a few weeks before launch. As a loop, each plan change gets a fresh check against the last report.
How do I install the Pre-mortem skill?
Copy the prompt at the top into your agent. It installs the skill from phuryn/pm-skills and sets up the habit. Or run npx skills add phuryn/pm-skills --skill pre-mortem.
Is the Pre-mortem skill free?
Yes. It is published under MIT. Habit is free too.
Pre-mortem. Now as a habit.
Install the Pre-mortem skill and make it a habit: follow https://gethabit.dev/skills/phuryn/pre-mortem.md
All phuryn skills →More planning skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by phuryn, published under MIT. Habit links to the original and never changes it. Is this your skill?