What

Improve docs/zh/llm-prompt.md — the prompt that drives LLM-generated Chinese translations — to eliminate common AI-style writing patterns.

Problem

The current Chinese translations are grammatically correct but read like AI output: overly formal, verbose, with English-influenced sentence structure. Examples from the live docs:

The root cause: the translation prompt has glossary and formatting rules, but zero guidance on writing style.

Changes

Added a "Writing style" section to docs/zh/llm-prompt.md:

1. 5 core rules — one sentence one idea, short sentences, spoken Chinese word order, keep English technical terms, no hedging
2. 12 anti-patterns with real examples — each taken from actual FastAPI zh translations, with the fix and the reason
3. 8 more patterns to watch for — "你可以在...中找到", "值得注意的是", "在这种情况下", etc.
4. 3 reference style guides — Vue.js zh docs, 阮一峰, Go by Example zh
5. Expanded glossary — from 4 to 22 terms (dependency injection, middleware, validation, endpoint, decorator, etc.)

Also refined "Grammar and tone" to explicitly state "用'你'不用'您'" and add guidance on dropping unnecessary subjects.

Total: 1 file changed, +73/-4 lines.

Why this approach

FastAPI's contributing guide says the best way to improve zh translations is to improve the LLM prompt — this changes the source, not the symptoms.