chat-export-report

name	chat-export-report
description	Use when user provides exported chat history (WeChat / Telegram / iMessage / QQ exports as .md / .txt / .json) and asks "我和 X 聊了啥"、"看完整个 md"、"细说 XX"、"是不是有 Y"、"what did I and X talk about", wants topical breakdown, requests detail on specific themes (relationships / work / health / events), or seeks honest interpretation of conversation dynamics. Triggers on large chat dumps (>1000 lines) where direct full read is impractical.
metadata	{"author":"innei","version":"0.1.0"}

chat-export-report

Analyze massive exported chat logs (thousands to hundreds of thousands of lines) and produce a layered, drill-downable report grounded in original quotes.

When to invoke

• User provides path to exported chat (WeChat / Telegram / iMessage / QQ; .md / .txt / .json)
• File far exceeds a single Read window (>2000 lines)
• User asks "what did we talk about", "read the whole file", "tell me more about X", "was there Y between us"
• User wants an honest read of relationship dynamics, emotional tone, or missed opportunities

Do not use for:

• Single messages or short conversations
• Looking up one specific fact (just grep)
• Full line-by-line translation or re-export

Reading strategy

Step 1 — Measure size

wc -l <file>

Step 2 — Three-zone sampling

Never read the whole file at once. Establish baseline tone first:

Zone	offset