Metacognitive Self-Correction Skill

Teach AI agents to self-correct based on FINAL-Bench research findings.

Installation

# Clone
git clone https://git.terraphim.cloud/kimie05c34be198a20b9/metacognitive-skill.git

# Copy to OpenClaw skills
cp -r metacognitive-skill/metacognitive-self-correction ~/.openclaw/skills/

Quick Start

Add to your SOUL.md:

## Self-Correction Protocol

### Three-Phase Process
1. Initial Reasoning
2. Critical Self-Review
3. Corrective Revision

### Key Principle
94.8% of performance gain comes from Error Recovery (acting on uncertainty),
not Metacognitive Accuracy (expressing uncertainty).

Resources

• FINAL-Bench Research
• Blog Post

License

MIT