1.7 KiB
1.7 KiB
name, description, version, author, type, tags, homepage, license
| name | description | version | author | type | tags | homepage | license | |||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| self-improving-agent | 分析对话质量、识别改进机会并持续优化响应策略的自我改进代理系统。 | 1.0.0 | xiucheng | skill |
|
https://github.com/xiucheng/self-improving-agent | MIT |
Self-Improving Agent
An intelligent self-improvement system for OpenClaw agents that analyzes conversation quality and continuously optimizes performance.
Features
- 📊 Quality Analysis: Evaluates conversation effectiveness
- 🎯 Improvement Tracking: Identifies areas for enhancement
- 📝 Learning Log: Records insights and lessons learned
- 📈 Weekly Reports: Generates improvement summaries
- 🔄 Strategy Optimization: Adapts response patterns over time
Installation
clawhub install self-improving-agent
Usage
Automatic Analysis
The skill automatically analyzes conversations after each session.
Manual Improvement Logging
from self_improving import SelfImprovingAgent
sia = SelfImprovingAgent()
sia.log_improvement("Need to be more concise in technical explanations")
Generate Weekly Report
report = sia.generate_weekly_report()
print(report)
Configuration
| Setting | Default | Description |
|---|---|---|
| improvement_log | ./improvement_log.md | Learning log file |
| soul_file | ./SOUL.md | Personality anchor file |
| auto_analyze | true | Auto-analyze conversations |
Integration
Works best with:
memory-manager: For tracking improvement history- Custom agent personalities (SOUL.md)
License
MIT License - Help agents get better every day!