mcpbeat

Thesis Style Polisher

willoscar/thesis-style-polisher

| 对中文毕业论文做最终润色与去 AI 味:重点处理章首导言、章末小结、贡献描述、总结与展望中的模板腔、宣传腔与 AI 口癖。

654 tokens
context cost
the whole folder, loaded on every use
6
files
instructions only
0
copies elsewhere
how many repositories repackaged it
496
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill thesis-style-polisher

What comes with it

1 245 bytes besides the instruction
assets/style_polish_contract.json
references/examples_bad.md
references/examples_good.md
references/overview.md
references/style_principles.md

The instruction itself

6 sections, as written by the author

Thesis Style Polisher

Inputs

  • 稳定版正文
  • 中文写作要求.md
  • GPT口癖与高频用词调研.md
  • 最新 review checklist

Outputs

  • 更自然的中文终稿

Load Order

Always read:

  • references/overview.md
  • references/style_principles.md
  • references/examples_good.md
  • references/examples_bad.md

Machine-readable contract:

  • assets/style_polish_contract.json

Workflow

  • 先识别结构性重复与模板句
  • 再处理章首导言、章末小结、贡献描述、总结与展望
  • 最后处理局部措辞与节奏

Key Rule

如果一段话的问题本质上是“没想清楚”,不要在这里强行润色。

How to use it

Copy the folder

Take willoscar/thesis-style-polisher from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.