home / skills / rohanpatriot / thinking-skills / decision-auditor

decision-auditor skill

/skills/decision-auditor

This skill helps you audit decisions for cognitive biases, run premortems, and reframe choices to reveal hidden assumptions under uncertainty.

npx playbooks add skill rohanpatriot/thinking-skills --skill decision-auditor

Review the files below or copy the command above to add this skill to your agents.

Files (11)
SKILL.md
2.8 KB
---
name: decision-auditor
description: Audits decisions for cognitive biases, runs premortems on plans, and reframes choices to reveal hidden assumptions. Use when evaluating decisions under uncertainty, reviewing plans for bias, assessing probability and risk, running premortems, checking for anchoring or availability bias, or analyzing why a judgment might be wrong.
---

# Decision Auditor

Based on *Thinking, Fast and Slow* by Daniel Kahneman.

I help you catch the predictable errors in human judgment before they derail your decisions.

## What I Do

Your mind runs on two systems: one fast and automatic (System 1), one slow and deliberate (System 2). Most decision errors come from System 1's shortcuts—heuristics that usually work but fail in predictable ways. I help you spot these failures and correct for them.

## When to Use Me

- Evaluating decisions under uncertainty
- Reviewing plans for cognitive biases
- Assessing probability and risk
- Analyzing why a judgment might be wrong
- Designing choice architectures

## Workflows

### Bias Check
When checking a decision for cognitive biases, follow [workflows/bias-check.md](workflows/bias-check.md)

### Premortem
When running a premortem analysis on a plan, follow [workflows/premortem.md](workflows/premortem.md)

### Reframe
When reframing a decision to reveal hidden assumptions, follow [workflows/reframe.md](workflows/reframe.md)

## Reference Guides

For detailed detection and correction guides:
- [Heuristics and Biases](references/heuristics-biases.md) - How to detect and fix common mental shortcuts
- [Decision Principles](references/principles.md) - Actionable rules for better judgment
- [System 1 vs System 2](references/two-systems.md) - Understanding the two modes of thinking
- [Prospect Theory](references/prospect-theory.md) - Loss aversion and risk assessment
- [Overconfidence](references/overconfidence.md) - Calibrating your certainty
- [Two Selves](references/two-selves.md) - Experiencing vs remembering
- [Anti-Patterns](references/anti-patterns.md) - Common mistakes to avoid

## Quick Bias Checklist

Use this when you need a fast scan without the full workflow:

- [ ] **Substitution**: Did we answer the actual question, or an easier one?
- [ ] **WYSIATI**: What information is missing that would be relevant?
- [ ] **Base rates**: What happens to similar cases? Are we treating ours as special?
- [ ] **Anchoring**: Where did our initial estimate come from? Would a different starting point change it?
- [ ] **Availability**: Are we overweighting vivid, recent, or personal examples?
- [ ] **Affect**: Are we conflating "I like this" with "this will succeed"?
- [ ] **Overconfidence**: Is our confidence level justified by the evidence?
- [ ] **Planning fallacy**: Are our estimates based on best-case scenarios?

Overview

This skill audits decisions for common cognitive biases, runs premortems on plans, and reframes choices to surface hidden assumptions. It is built to catch predictable judgment errors and improve the calibration of probability, risk, and confidence. Use it to make decisions more robust under uncertainty and to reduce avoidable mistakes in planning.

How this skill works

The skill inspects a decision or plan through a bias-focused lens: it scans for substitution, anchoring, availability, affect, overconfidence, and planning fallacy. It runs premortems to imagine failure modes and extract root causes, then reframes the choice to expose implicit assumptions and missing information. Outputs are concrete nudges and corrective prompts you can apply immediately to revise estimates or redesign choices.

When to use it

  • Evaluating high-stakes decisions under uncertainty or time pressure
  • Reviewing project plans for optimistic timelines or underestimated risks
  • Running a premortem before committing resources to a new initiative
  • Checking estimates for anchoring, availability, or base-rate neglect
  • Designing choice architectures or decision policies to reduce bias

Best practices

  • Start with the quick bias checklist for a fast scan before deeper analysis
  • Use premortems early—preventative reframing is cheaper than repair
  • Calibrate confidence numerically; ask for predicted probabilities, not yes/no
  • Compare against base rates and similar historical cases rather than isolated intuition
  • Document assumptions explicitly and test the most critical ones first

Example use cases

  • A product team runs a premortem to identify why a launch could fail and adjusts milestones accordingly
  • A hiring panel checks for availability and affect biases when shortlisting candidates
  • An investor calibrates probability estimates, reducing overconfidence in a pitch
  • A planner tests multiple reframes to reveal hidden dependencies in a rollout plan
  • A manager uses the bias checklist to improve estimates for time and cost

FAQ

How long does a typical audit take?

A quick bias scan takes 10–20 minutes; a full premortem and reframing session usually takes 60–90 minutes depending on complexity.

Will this remove all bias from a decision?

No. The skill reduces predictable errors and improves calibration, but it cannot eliminate all bias. It makes judgments more resilient and highlights where further evidence or structure is needed.