Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
pmprompt avatar

Thinking In Bets

  • 381 installs
  • 43 repo stars
  • Updated March 7, 2026
  • pmprompt/claude-plugin-product-management

thinking-in-bets is an agent skill that applies Annie Duke's probabilistic decision framework with pre-mortems, explicit assumptions, and outcome-versus-process evaluation for developers and PMs choosing between uncertai

About

thinking-in-bets is a product management agent skill from pmprompt/claude-plugin-product-management that implements the Thinking in Bets framework for decisions under uncertainty. Install with `npx skills add pmprompt/claude-plugin-product-management --skill thinking-in-bets`. The skill separates decision quality from outcomes, surfaces testable assumptions, and runs pre-mortems and kill criteria when comparing roadmap bets, pricing moves, or risky feature investments. It ships as one skill inside a plugin advertising 26+ PM frameworks for Claude Code, Cursor, and compatible agents. Reach for thinking-in-bets when teams need probabilistic framing, bias reduction, and explicit bet documentation instead of hindsight-driven postmortems or gut-feel prioritization.

  • Probabilistic decision framing
  • Assumption surfacing and tests
  • Pre-mortem and scenario planning
  • Reversible versus one-way door calls
  • Outcome tracking for learning

Thinking In Bets by the numbers

  • 381 all-time installs (skills.sh)
  • +11 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #819 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/pmprompt/claude-plugin-product-management --skill thinking-in-bets

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs381
repo stars43
Last updatedMarch 7, 2026
Repositorypmprompt/claude-plugin-product-management

How do you decide between roadmap options under uncertainty?

Frame product bets with probabilities, explicit assumptions, and pre-mortems when choosing between roadmap options, pricing moves, or risky feature investments.

Who is it for?

Engineering leads and PMs comparing uncertain feature bets, pricing moves, or investments where luck can distort outcome-based judgment.

Skip if: Skip thinking-in-bets for trivial low-stakes choices or decisions that already have complete, verified data.

When should I use this skill?

A developer asks to think in bets, decide probabilistically, run a pre-mortem, avoid resulting, or separate decision quality from outcomes.

What you get

Bet statements with probability estimates, assumption lists, pre-mortem risks, kill criteria, and process-quality evaluation notes.

  • bet brief
  • assumption log
  • pre-mortem document

By the numbers

  • Part of pmprompt/claude-plugin-product-management with 26+ product management framework skills

Files

SKILL.mdMarkdownGitHub ↗

Domain Context

This skill implements a proven product management framework. The approach combines best practices from industry leaders and is designed for practical application in day-to-day PM work.

Input Requirements

  • Context about your product, feature, or problem
  • Relevant data, research, or constraints (recommended but optional)
  • Clear articulation of what you're trying to achieve

Thinking in Bets

What It Is

Thinking in Bets is a framework for improving decision quality by separating decisions from outcomes. The core insight: a good decision can have a bad outcome, and a bad decision can have a good outcome—luck is always involved.

Most people judge decisions by their outcomes (called "resulting"). This is backwards. You can only control the quality of your decision, not the outcome.

The key shifts:

  • Move from "Was I right?" to "Was my thinking process good?"
  • Move from "What happened?" to "What did I know at the time?"
  • Move from implicit assumptions to explicit, testable beliefs

When to Use It

Use Thinking in Bets when you need to:

  • Evaluate past decisions without outcome bias clouding judgment
  • Make decisions under uncertainty where luck will influence results
  • Improve team decision-making in meetings and planning
  • Set up pre-mortems and kill criteria for projects
  • Shorten feedback loops on decisions with delayed outcomes
  • Reduce cognitive biases like overconfidence, hindsight bias, and sunk cost
  • Run better meetings that surface true opinions, not groupthink

When Not to Use It

  • The decision is trivial with low stakes
  • You have perfect information (rare)
  • You're looking for permission to take a risk you've already decided on

Resources

Books:

  • Thinking in Bets by Annie Duke
  • Quit: The Power of Knowing When to Walk Away by Annie Duke
  • Thinking, Fast and Slow by Daniel Kahneman

Related skills

How it compares

Use thinking-in-bets for probabilistic commitment decisions; use prioritization frameworks when ranking a known backlog with stable estimates.

FAQ

When should thinking-in-bets be used?

thinking-in-bets fits uncertain roadmap, pricing, or investment choices where luck influences outcomes. The skill documents probabilities, assumptions, and pre-mortems so teams judge process quality instead of resulting from whatever happened afterward.

How is thinking-in-bets installed?

Install thinking-in-bets via `npx skills add pmprompt/claude-plugin-product-management --skill thinking-in-bets`. The skill is part of the open-source Claude product management plugin that bundles 26+ PM frameworks for Claude Code, Cursor, and OpenCode.

What artifacts does thinking-in-bets produce?

thinking-in-bets yields explicit bet statements, probability estimates, written assumptions, pre-mortem risk lists, and kill criteria. These artifacts help engineering and product teams align on decision quality before code ships or budgets commit.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.