alchaincyf avatar

Huashu Proofreading

This is a three-pass proofreading system designed to strip AI-generated text of its telltale patterns and make it sound human. It targets six specific AI tells: filler phrases like "in today's era," repetitive sentence structures, overly formal vocabulary, mechanical formatting, fence-sitting neutrality, and vague abstractions without concrete details. The workflow is systematic: first pass checks facts and logic, second pass rewrites AI-sounding sentences into conversational Chinese, third pass polishes rhythm and formatting. It includes grep integration to pull real examples from a personal content library of social media posts. Aimed at Chinese content creators who need their AI-assisted writing to pass detection tools while maintaining authentic voice.

skills.sh installs
883
GitHub stars
2.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add alchaincyf/huashu-skills --skill huashu-proofreading --agent claude-code

Installs into .claude/skills of the current project.

Files

AI味审校

系统化降低文章AI检测率,增加人味的三遍审校专业能力。

何时使用此Skill

当检测到以下场景时,自动加载此skill:

  • 用户说"审校一下"、"降低AI味"、"太AI了"
  • 初稿创作完成后
  • 用户提到"AI检测率高"、"没人味"
  • 文章需要最终polish

核心目标

  • 降低AI检测率:目标控制在30%以下
  • 增加人味:让文章有经验感、有温度、像真人在说话
  • 保持花生风格:实践导向、技术深度、易懂表达、有用可落地

三遍审校流程

第一遍:内容审校(逻辑、事实、结构)

目标:确保内容准确、逻辑清晰

检查项:

  • 事实准确?(数据、时间、产品名称)
  • 逻辑清晰?(前后无矛盾)
  • 结构合理?(无跑题)
  • 信息完整?(关键点都说了)
  • 无编造?(所有数据和案例都是真实的)

方法:

  • 从头到尾读一遍,标注疑问点
  • 搜索验证不确定的信息
  • 检查数字和专有名词的准确性

第二遍:风格审校(AI味降重)

目标:去掉AI味,增加人味

核心检查:6大类AI腔识别

1️⃣ 套话连篇

❌ AI常说:

  • "在当今时代"、"在...的大背景下"
  • "综上所述"、"总而言之"
  • "值得注意的是"、"需要强调的是"
  • "随着...的发展"、"伴随着..."

✅ 改写方向:直接切主题,不绕弯子

示例:

❌ "在当今AI技术飞速发展的时代,编程工具也在不断进化..."
✅ "Claude Code出了。我用了两周,确实比Cursor好用。"
2️⃣ AI句式(高频重复模板)

❌ AI常说:

  • "不是...而是..."(连续出现3次以上)
  • "不仅...而且..."(堆叠使用)
  • "一方面...另一方面..."
  • "既...又..."(过度使用)

✅ 改写方向:拆成短句,用多样化表达

示例:

❌ "Claude Code不是简单的工具,而是智能助手。它不仅能写代码,而且能理解意图。"
✅ "Claude Code不只是补全代码。它能理解你的意图,知道你想做什么。这个很关键。"
3️⃣ 书面词汇(距离感强)

❌ AI常说:

  • "显著提升"、"大幅改善"→ 用具体数字
  • "充分利用"→ "用好"
  • "进行操作"→ 直接用动词("点击"、"输入")
  • "实现功能"→ "做到"
  • "促进发展"→ "帮助..."

✅ 改写方向:口语化,具体化

Sponsors

Details

Repository
github.com/alchaincyf/huashu-skills
First seen
Jun 3, 2026

More from alchaincyf/huashu-skills

All 21

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs