Borrowing it
Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/writing-polish/SKILL.mdgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zimoliao/scholaraio/writing-polish)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/writing-polish"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/writing-polish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/writing-polish"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/writing-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00938 |
| Opus 5.5 | $0.00014 | $0.00375 |
| Sonnet 5.5 | $0.00007 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
writing-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
学术写作润色
去除 AI 痕迹、提升表达质量、匹配目标风格。支持中英文。
执行逻辑
1. 了解需求
向用户确认:
- 待润色文本:粘贴、文件路径、或 workspace 中的文件
- 润色方向:去 AI 味 / 学术规范 / 风格适配 / 全部
- 目标语言:中文 / English(是否需要翻译)
- 风格参考(可选):用户提供同期刊/同领域的范文,你来提取风格特征并仿照
2. 风格分析(如有范文)
当用户提供风格参考时,先分析范文的:
- 句式特征:句子平均长度、主动/被动语态比例、从句嵌套深度
- 术语习惯:领域专用词的选择偏好(如 "utilize" vs "use")
- 段落结构:每段几句话、topic sentence 位置、过渡方式
- 引用风格:引用密度(每段几处)、引用位置(句首/句中/句尾)
- 形式化程度:口语化 vs 高度形式化
将分析结果展示给用户确认,然后据此润色。
3. AI 痕迹检测与消除
常见 AI 写作模式(必须消除):
英文:
- 空洞开头:"In recent years, X has garnered significant attention..."
- 过度连接词:"Furthermore", "Moreover", "It is worth noting that"
- 虚假精确:"a myriad of", "a plethora of", "a paradigm shift"
- 套话结尾:"paving the way for future research"
- 过度对称的段落结构(每段长度几乎相同)
- 不必要的元叙述:"This section discusses...", "As mentioned above..."
中文:
- "值得注意的是"、"不可忽视的是"
- "近年来,X引起了广泛关注"
- "具有重要的理论意义和实践价值"
- "为...提供了新的思路/视角"
- 过度使用"进行"("进行研究"→"研究")
4. 学术规范检查
- 逻辑连贯:段落间是否有清晰的因果/对比/递进关系
- 表述精确:模糊表达("很多"、"一些"、"significantly")替换为具体数据
- 被动语态适度:科技写作允许被动,但不应全文被动
- 术语一致:同一概念全文统一用词
- 时态正确:方法/结果用过去时,普遍结论用现在时
5. 输出
- 直接给出润色后的文本
- 标注主要修改点(如用户要求)
- 如果是文件,保存润色版本到同目录(如
introduction-polished.md)
原则
- 保留作者的学术判断:只改表达方式,不改观点和论证逻辑
- 最小修改:能改一个词解决的不改整句
- 保持个人风格:如果原文有作者自己的表达习惯且不影响清晰度,保留
- 不加内容:润色不是扩写,不添加原文没有的论点或引用
示例
用户说:"帮我把这段 Introduction 润色一下,去掉 AI 味" → 检测 AI 模式,替换为自然的学术表达
用户说:"我有一篇 JFM 的范文,帮我按这个风格改写我的 Discussion" → 分析 JFM 范文风格,据此润色 Discussion
用户说:"帮我把这段中文翻译成学术英语" → 翻译并润色,确保符合英文学术写作规范
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 80 lines · 35 tokens per session scan A 24f0f180b9ab
writing-polish is a skill published in the GitHub repository ZimoLiao/scholaraio (584 stars, last pushed 10d ago), licensed MIT. It adds 35 tokens to every session and 938 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
writing-polish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-polishZimoLiao/scholaraio | Skill | 584 | 10d ago | MIT | A | 35 | Claude Code |
| thoughtdagchenxiachan/thoughtdag | Skill | 742 | 5d ago | MIT | B | 39 | Claude Code, Codex |
| autosearch:channel-selection0xmariowu/Autosearch | Skill | 54 | 7d ago | MIT | A | 87 | Claude Code |
| autosearch:context-retention-policy0xmariowu/Autosearch | Skill | 54 | 7d ago | MIT | A | 89 | Claude Code |
| autosearch:delegate-subtask0xmariowu/Autosearch | Skill | 54 | 7d ago | MIT | A | 71 | Claude Code |
| autosearch:experience-compact0xmariowu/Autosearch | Skill | 54 | 7d ago | MIT | A | 69 | Claude Code |
| autosearch:graph-search-plan0xmariowu/Autosearch | Skill | 54 | 7d ago | MIT | A | 72 | Claude Code |