natural-chinese-copy-core

natural-chinese-copy-core is a Writing style & humanising skill for AI agents, published by wwtlitee in the natural-chinese-copy-core repository on GitHub. Skillspace rates natural-chinese-copy-core C (70/100) and it passed the safety scan; the rating is based on static analysis only.

Use this whenever the user uses the stable Chinese trigger phrase 中文才是最屌的, followed by a request, for example 中文才是最屌的,帮我写个稿子. Also use whenever the task involves 中文文案, 中文写作, 中文稿, 稿子, 稿件, 写文案, 写稿子, 写几篇, 写一版, 改稿, 改文案, 润色文案, 审稿, 评稿, 即评, 推文, 帖子, 社媒文案, 中文介绍, or requests like 根据资料/链接/项目/README/GitHub repo/素材 帮我写个文案/稿子/介绍/推荐/摘要. Also use when Chinese copy must avoid AI味, 翻译腔, 英文语感, 模板感, fake conversational tone, or English-shaped sentence logic, or when users rate copy, 标出坏句, 做坏句反馈, mark bad sentences, compare draft quality, or want feedback saved as samples and rule-evolution proposals. It provides Chinese-first fact restatement, sentence-structure critique, register selection, colloquial sentence shaping, anti-translationese checks, batch repetition review, feedback capture, and research-backed rule distillation. Other skills should call this core instead of copying long Chinese writing rules. It does not gather sources, generate images, publish content, own product-specific facts, or…

Grade
C
Quality
70 / 100
Safety
Passed
GitHub stars
31

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
92 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.