#59 · Primary category: Prompt Engineering Tools

shuorenhua

agent-skill ai-writing anti-slop chatgpt chinese claude-code codex cursor developer-tools openclaw prompt prompt-engineering rewriting skill text-quality writing

Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts.

Project last updated:08/29/26

GitHub Stars

1.3K

Forks

68

Contributors

1

License

MIT

Why we included this project

Writing Chinese with an AI assistant often means getting back prose that reads like a model performing rather than a person talking. This skill fixes that. It's a drop-in instruction file for Codex, Claude Code, Cursor, and ChatGPT that rewrites chat replies, status updates, READMEs, release notes, and forum posts, cutting the over-eager acknowledgments and salesy closings that make AI text easy to spot while locking in facts, versions, commands, and attribution. It ships a lite and a full variant, plus a documented benchmark of 84 cases and real scenario samples, so you can see exactly what it changes and what it refuses to touch. That makes it a practical, opinionated editing assistant rather than a generic style guide, and teams publishing Chinese-facing content through AI tools can adopt it quickly.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category