Skip to content
Get packs

Pre-Mortem Plan Challenge

Stress-test a plan by imagining it failed and working backwards to find weak assumptions

Source Download skill
Repository
alirezarezvani/claude-skills
Stars
29,149
Licence
MIT
Files
1 file

What it does

When you give the agent a plan, it imagines the plan failed a year from now and works backwards to explain why. It lists the assumptions the plan relies on, rates how confident you should be in each and how bad it would be if each were wrong, and maps which risks depend on others. It finishes with a report of critical risks, reversible versus irreversible bets, go/kill checkpoints at 30, 60 and 90 days, and concrete validation steps.

Great for

  • Founders or managers about to commit significant money, staff time or resources to a plan
  • People preparing a plan for a board, investors or senior leadership
  • Teams whose feedback has been uniformly positive and want a deliberate critic
  • Anyone who feels excited about a plan and wants a sanity check before moving fast

Skip it if

  • Quick decisions or low-stakes choices, where a full assessment adds overhead
  • Replacing expert legal, financial or regulatory advice; the framework only surfaces questions and the agent's judgement can be wrong about market or financial facts
  • Plans that rely on confidential data you would not share with an AI service, since the plan text is sent to the agent for analysis

Try asking

  • “/em:challenge Launch our B2B invoicing product in Q3 with three enterprise pilots and a self-serve tier”
  • “/em:challenge Hiring plan: add 6 engineers in 2 months to support the new platform roadmap”
  • “/em:challenge Fundraising plan: raise a 2M seed round in 3 months with our current runway of 9 months”
Step-by-step guide: how to use Pre-Mortem Plan ChallengeInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    challenge.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip challenge.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip challenge.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Paste the full plan with its timeline, budget and key dependencies so the agent has concrete assumptions to test.
  • Ask for the bear case and the question 'what would an enemy of this plan attack first?' to get the hardest critiques.
  • Treat the output as a vulnerability map to act on, then validate the Low-confidence, Critical-impact assumptions with real data.

What's inside

  • SKILL.md

Redistributed unmodified from alirezarezvani/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.