decision-critic

Stress-test decision reasoning by extracting claims, assumptions, constraints, and judgments.

898|134|Updated Jul 28, 2025
One-click install
npx skills add https://github.com/solatis/claude-config --skill decision-critic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-critic
Source: https://github.com/solatis/claude-config/tree/main/skills/decision-critic
Command: npx skills add https://github.com/solatis/claude-config --skill decision-critic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Structured decision critique to surface assumptions, verify claims, and generate adversarial perspectives before finalizing a decision.

Core Features & Use Cases

  • Decomposition & IDs: Extract claims (C1, C2), assumptions (A1, A2), constraints (K1, K2), and judgments (J1, J2).
  • Verification phase: Generate verification questions for each claim.
  • Challenge phase: Present contrarian perspectives and alternative framings.
  • Synthesis: Provide a verdict and recommended actions.

Quick Start

Run the decision critic: python3 scripts/decision-critic.py --step-number 1 --total-steps 7 --decision "<decision text>" --context "<constraints and background>" --thoughts "<your accumulated analysis, IDs, and status from all previous steps>"

Frequently Asked Questions about decision-critic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stress-test a decision before committing to it?

Stress-testing a decision involves decomposing it into claims, assumptions, constraints, and judgments, then systematically verifying each component through questioning and adversarial challenge. This surfaces hidden assumptions and validates reasoning before implementation, reducing downstream risk.

What's the best way to identify hidden assumptions in my decision rationale?

Decompose your decision into tagged components—claims (C), assumptions (A), constraints (K), and judgments (J)—then generate verification questions for each. Adversarial challenge phases present contrarian perspectives to expose unstated premises and alternative framings you may have overlooked.

Can I use decision critique for complex tradeoff analysis?

Yes. The skill applies across decomposition, verification, challenge, and synthesis workflows for any decision involving tradeoffs. It generates structured verdicts with statuses—VERIFIED, FAILED, or UNCERTAIN—enabling you to evaluate competing options and their underlying reasoning systematically.

How do I know when a decision is ready to finalize?

The synthesis phase produces a verdict summarizing verification results and recommended actions. A decision is ready when key claims verify, assumptions are explicit and validated, and you've considered adversarial perspectives. Uncertain or failed verdicts flag areas needing revision or further evidence.

What happens if verification questions reveal conflicting evidence?

Conflicting evidence surfaces as FAILED or UNCERTAIN verdicts during verification. The challenge phase generates alternative framings and contrarian perspectives; synthesis then recommends actions—revise assumptions, gather more data, or reframe the decision entirely based on the conflict.