# MrGeDiao/shuorenhua

说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts.

Repository: https://github.com/MrGeDiao/shuorenhua
Canonical: https://ross.abutalabs.com/products/shuorenhua
Homepage: https://chatgpt.com/g/g-6a5829b1163481919e1e45851f6bc709-shuo-ren-hua
Language: Python
License: MIT
License Family: permissive
Topics: ai-writing, anti-slop, chatgpt, chinese, claude-code, cursor, prompt, prompt-engineering, skill, writing, openclaw, agent-skill, codex, developer-tools, rewriting, text-quality
Last push: 2026-08-26T02:51:19+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 11
- inputs: {"age_days": 164, "days_push": 7, "days_rel": 12, "gap_med": 3, "n_releases_24m": 34}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1245, forks 67 (observed 2026-08-28T04:04:06.939556+00:00)

## What it is
A Chinese-first rewrite skill that removes AI-generated tone (template phrasing, performative language, translationese) from text while preserving facts like numbers, versions, commands, and attribution. It installs as a skill/plugin into AI coding agents such as Claude Code, Codex, Cursor, and ChatGPT.

## Use cases
- remove AI tone from Chinese text
- rewrite AI-drafted Chinese release notes naturally
- clean up AI-sounding README and forum posts
- rewrite chat updates without losing facts
- de-slop Chinese long-form writing
- annotate AI-flavored text without rewriting

## When to choose
- you draft Chinese text with AI and it reads robotic or templated
- you need fact-preserving rewrites where numbers and claims must survive
- you use Claude Code, Codex, Cursor, or ChatGPT and want a reusable rewrite skill

## When to avoid
- you need English or non-Chinese text rewriting
- you want a standalone app rather than an agent skill/prompt
- you need automated style checking in CI rather than agent-driven rewriting

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, nlp, developer-tools
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: ai-writing, chinese, rewriting, agent-skill, anti-slop, text-quality, claude-code, codex, cursor, chatgpt, natural-language-processing, localization

## Member repositories
- MrGeDiao/shuorenhua (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:06.939556+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:08:07.239742+00:00, confidence not recorded.
  - readme: https://github.com/MrGeDiao/shuorenhua (fetched 2026-08-28T04:04:06.939556+00:00, sha 327e86e1c314)
  - homepage: https://chatgpt.com/g/g-6a5829b1163481919e1e45851f6bc709-shuo-ren-hua (fetched 2026-08-29T12:19:37.017469+00:00, sha 64533363597c)
- Data as of 2026-08-30T08:39:29.467469+00:00.