Skills
.Work. You
Rest

thoughtproof-reasoning-check

Official

Pre-check AI reasoning before high-stakes actions

Finance & Accounting#verification#reasoning#risk-management#ai-governance#thoughtproof#decision-verification#adversarial-critique
Authormoonpay
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Verifies and critiques an AI agent's decision before executing high-value actions to reduce risk and improve outcomes.

Core Features & Use Cases

  • Adversarial multi-model critique (Claude, Grok, DeepSeek) to surface objections and improve decision quality.
  • Returns a signed verdict with one of ALLOW, BLOCK, or UNCERTAIN and a confidence score.
  • Use before high-stakes decisions in trading, asset management, or autonomous workflows to enforce risk controls.

Quick Start

Provide the agent's planned decision to ThoughtProof for critique before execution

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: thoughtproof-reasoning-check
Download link: https://github.com/moonpay/skills/archive/main.zip#thoughtproof-reasoning-check

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.