Skip to content
Back to skills

Chat

ASecurity

Learns communication preferences from explicit feedback. Adapts tone, format, and style.

  • 17 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 6, 2026
documentationgotesting

Works with

  • cli

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add clawic/skills --skill chat --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Chat?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Chat
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/clawic-chat/badge)](https://www.skillsdirectory.com/skills/clawic-chat)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: Chat
slug: chat
version: 1.1.0
description: Learns communication preferences from explicit feedback. Adapts tone, format, and style.
homepage: https://clawic.com/skills/chat
changelog: Preferences now persist in external memory instead of self-modifying SKILL.md
metadata:
  clawdbot:
    emoji: πŸ’¬
    requires:
      bins: []
    os:
    - linux
    - darwin
    - win32
    displayName: Chat
---

## Data Storage

```
~/Clawic/data/chat/
β”œβ”€β”€ memory.md       # Confirmed preferences (≀50 lines)
β”œβ”€β”€ 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:
- βœ… Learns preferences from explicit user corrections
- βœ… Stores patterns in ~/Clawic/data/chat/memory.md
- βœ… Adapts communication style based on stored preferences
- ❌ NEVER modifies SKILL.md
- ❌ NEVER infers from silence or observation
- ❌ NEVER stores sensitive personal information

## Quick Reference

| Topic | File |
|-------|------|
| Preference dimensions | `dimensions.md` |
| Confirmation criteria | `criteria.md` |

## 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 |
| Confirmed | memory.md | User approved |
| Rejected | rejected.md | User declined |

### 3. Compact Storage Format
One line per preference in memory.md:
```
- Concise responses, no fluff
- Uses πŸš€ for launches, βœ… for done
- Prefers bullets over paragraphs
- Technical jargon OK
- Hates "Great question!" openers
```

### 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 ~/Clawic/data/chat/memory.md)"
- On request, show full memory.md contents
- "Forget X" removes from all files

Files in this skill

  • SKILL.md2.2 KB
  • _meta.json310 B
  • criteria.md1.2 KB
  • dimensions.md1.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…