- name
- self-improving-agent
- description
- |
Self-Improving Agent Skill
Core Principle
Every interaction is a learning opportunity. The agent should actively improve itself based on feedback and experiences.
Learning Triggers
Activate this skill when:
- User provides explicit feedback (positive or negative)
- Agent makes an error or mistake
- User says things like "learn from this", "remember", "don't do X again"
- Agent notices a repeated mistake pattern
- Task completes with lessons to extract
Self-Improvement Workflow
Step 1: Capture Learning
After any triggering event, immediately:
- Update
MEMORY.mdwith new insights/lessons - Update
memory/YYYY-MM-DD.mdwith the event - If mistake: add to "本猫犯过的错误/教训" section in MEMORY.md
- If preference: update "腿腿哥的新偏好/要求" section
Step 2: Reflect
Ask: "What can I learn from this?"
- What went wrong?
- What should I do differently?
- What files need updating?
Step 3: Act
Immediately update relevant files:
- MEMORY.md for long-term improvements
- Daily memory files for event-specific lessons
- AGENTS.md or SOUL.md if persona/tone changes needed
Step 4: Confirm
Tell the user what the agent learned and what changed.
File Update Guidelines
MEMORY.md Updates
Add to "本猫犯过的错误/教训" section:
- ❌ [Date]: [What went wrong]
→ 改进：[What to do differently]Add to "腿腿哥的新偏好/要求" section:
- [New preference or requirement] (added [date])Daily Memory Updates
Add to "做得不好/需要改进的地方":
- ❌ [What went wrong]: [Context]
- 教训：[Learning]Pattern Detection
Actively look for:
- Repeated mistakes (same error multiple times)
- User preferences that aren't recorded
- Missing knowledge that should be in memory
- Workflow inefficiencies
Quick Reference
When user says "learn from this":
- Read relevant memory files
- Identify the lesson
- Update MEMORY.md immediately
- Confirm update to user
When agent makes a mistake:
- Acknowledge the mistake
- Explain what went wrong
- Update relevant files
- Tell user what will change
*This skill is part of the agent's self-improvement system.*