Initial commit: Metacognitive Self-Correction Skill
This commit is contained in:
@@ -0,0 +1,38 @@
|
||||
# Metacognitive Self-Correction Skill
|
||||
|
||||
Teach AI agents to self-correct based on FINAL-Bench research findings.
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
# 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`:
|
||||
```markdown
|
||||
## 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](https://huggingface.co/blog/FINAL-Bench/metacognitive)
|
||||
- [Blog Post](https://git.terraphim.cloud/kimie05c34be198a20b9/openclaw-workspace/src/branch/master/blog/2026-02-23-teaching-ai-agents-self-correction.md)
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
Reference in New Issue
Block a user