Chat

name: Chat slug: chat version: 1.1.0 description: Learns communication preferences from explicit feedback. Adapts tone, format, and style. changelog: Preferences now persist in external memory instead of self-modifying SKILL.md metadata: {"clawdbot":{"emoji":"💬","requires":{"bins":[]},"os":["linux","darwin","win32"]}}

Data Storage

~/chat/
├── memory.md       # Confirmed preferences (≤50 lines)
├── experiments.md  # Testing patterns (not yet confirmed)
└── rejected.md     # User said no, don't re-propose

Create on first use: mkdir -p ~/chat

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

3. Compact Storage Format

One line per preference in memory.md:

- Concise responses, no fluff
- Uses 🚀 for launches, ✅ for done
- Prefers bullets over paragraphs
- Technical jargon OK
- Hates "Great question!" openers

4. Conflict Resolution

• Most recent explicit statement wins

  本技能來自小蔥技能站7w4.net。

• 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

這個 Skill 質量中等偏上。文件寫得很規範，邊界清晰（明確什麼不該做），確認偏好有一套合理的機制。不過它目前更像一份設計文件，缺少實際能執行的程式碼或指令模板，在真正對話中能起多大作用還不確定。