name: chat-distill description: > Distill a person's chat style from exported conversation records and generate replies that mimic their voice. Use when (1) analyzing chat history to extract vocabulary, tone, emoji habits, sentence patterns, and personality traits, (2) generating replies in someone's specific chat style, (3) creating a style profile from WeChat, TG, Discord, or text chat exports, (4) asking to analyze chat records or mimic a speaker's tone. Supports .txt, .json, and WeChat chat export formats.

Chat Distill — Style Analysis & Mimicry

Workflow

來源於7w4.net。

1. Parse → extract messages per speaker from raw export (see references/format-parsers.md)
2. Analyze → build style profile (see references/style-dimensions.md)
3. Report → output analysis report using template in references/output-template.md
4. Mimic → generate replies on demand using the profile

Quick Start

Given a chat export file:

1. Read the file and identify the format (WeChat export, plain text, JSON array, TG export).
2. Normalize into { speaker, text, time? } messages using parsing rules in references/format-parsers.md.
3. Pick the target speaker — the one whose style to learn. If multiple speakers exist, ask which one.
4. Run analysis following references/style-dimensions.md.
5. Output the report per references/output-template.md § Analysis Report.
6. When the user asks for a mimicked reply, use the profile + references/output-template.md § Mimic Reply.

Key Principles

• Show, don't tell: Include concrete examples from the actual chat when reporting style traits.
• Preserve quirks: Capture tics the speaker doesn't notice — repeated filler words, capitalization habits, punctuation style.
• Respect privacy: Never echo sensitive content (passwords, addresses, financials) from chats into reports. Anonymize if needed.
• Minimum sample: Require at least 20 messages from the target speaker. If fewer, warn that analysis may be unreliable.

這是一個實用性不錯的聊天風格分析工具，能夠從聊天記錄中提煉出說話風格並模仿生成回覆。優點是支援平臺多、分析維度全面、輸出格式規範。缺點是使用指南比較簡略，新手可能不容易把握分析標準，缺少實際案例參考。總體質量中等偏上，對於需要模仿特定人說話風格的使用者有一定幫助。