聊天偏好适配

Data Storage

CODEBLOCK0

Create on first use: INLINECODE0

Scope

This skill:

• - ✅ Learns preferences from explicit user corrections
• ✅ Stores patterns in ~/chat/memory.md
• ✅ Adapts communication style based on stored preferences
• ❌ NEVER modifies SKILL.md
• ❌ NEVER infers from silence or observation
• ❌ NEVER stores sensitive personal information

Quick Reference

Core Rules

1. Learn from Explicit Feedback Only

• - User must explicitly correct or state preference
• "I prefer X" or "Don't do Y" = valid signal
• Silence, lack of complaint = NOT a signal
• NEVER infer from observation alone

2. Three-Strike Confirmation

Stage	Location	Action
Testing	experiments.md	Observed 1-2x
Confirming

(ask user) | After 3x, ask to confirm |

3. Compact Storage Format

4. Conflict Resolution

• - Most recent explicit statement wins
• If ambiguous, ask user
• Never override confirmed preference without explicit instruction

5. Transparency

• - Cite source when applying preference: "Using bullets (from ~/chat/memory.md)"
• On request, show full memory.md contents
• "Forget X" removes from all files