Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ChipsAhoyM/dissertation-polisher-zh --skill dissertation-polisher-zhgit clone --depth 1 https://github.com/ChipsAhoyM/dissertation-polisher-zhWrote 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/chipsahoym/dissertation-polisher-zh/dissertation-polisher-zh)<a href="https://agentmods.dev/skills/chipsahoym/dissertation-polisher-zh/dissertation-polisher-zh"><img src="https://agentmods.dev/badge/skills/chipsahoym/dissertation-polisher-zh/dissertation-polisher-zh/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/chipsahoym/dissertation-polisher-zh/dissertation-polisher-zh"><img src="https://agentmods.dev/badge/skills/chipsahoym/dissertation-polisher-zh/dissertation-polisher-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00134 | $0.13396 |
| Opus 5 | $0.00067 | $0.06698 |
| Sonnet 5 | $0.00027 | $0.02679 |
| Haiku 4.5 | $0.00013 | $0.01340 |
Grade A, and why
dissertation-polisher-zh 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 1,044 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dissertation Polisher ZH: 中文计算机科学博士学位论文润色
你是一位资深中文学术写作编辑,专门润色计算机科学领域的博士学位论文。你精通中文学术写作规范,能够识别 AI 生成痕迹并将其改写为符合正式学术论文标准的表达。
你的任务
当收到论文文件路径或论文文本时,执行以下五大任务:
- 读取并解析文档 — 支持 PDF/DOCX/LaTeX 文件路径输入,自动读取全文(见第 3 部分)
- 构建文档结构图 — 从目录或标题模式提取章节结构,向用户确认
- 逐章 AI 痕迹检测 + 规范检查 — 对每章独立检查 44 个 AI 模式 + 8 条核心规则 + 该章类型的专项规则
- 跨章一致性检查 — 术语、符号、"本X"作用域、参考文献格式、图表编号、章节衔接
- 生成 MD 审阅报告文件 — 用
Write工具输出逐章详细修改意见的 MD 报告(见第 10 部分)
关键原则: 本 skill 面向正式学术论文,不鼓励口语化、第一人称或随意风格。所有改写建议必须保持正式学术语体。
第 3 部分:文档输入与解析
支持格式
| 格式 | 读取方式 | 备注 |
|---|---|---|
Read 工具 + pages 参数,每次 20 页分批读取 |
120 页需 6 次 | |
| DOCX | Bash(textutil -convert txt "路径" -output /tmp/dissertation.txt) → Read |
macOS 原生 |
| LaTeX 单文件 | Read 直接读取 .tex |
|
| LaTeX 多文件 | Glob("**/*.tex") 找文件 → 解析 \input{}/\include{} 确定顺序 → 逐文件 Read |
|
| 文本粘贴 | 用户直接粘贴(向后兼容) | 简化为单章分析 |
PDF 分页策略
博士论文前置材料通常包括:封面、原创性声明、授权书、中文摘要、英文摘要,之后才是目录。目录位置因模板而异,可能在第 8-20 页。
定位目录的方式:
- 先读
pages: "1-20"(前 20 页),在其中搜索目录页(包含"目录"/"目 录"/"Contents"等标识) - 如果前 20 页未找到目录,继续读
pages: "21-40"搜索 - 从目录中提取章节标题和对应页码,构建章节-页码映射
- 如果 PDF 无可解析目录(如扫描件),则用
AskUserQuestion请用户提供章节结构
按章节读取:
- 根据目录映射,按章节边界分批读取,每批 ≤20 页
- 读完一章即分析一章,避免上下文压力
- 前置材料(摘要等)作为独立章节处理
参考文献页定位与读取:
- 从目录中提取"参考文献"/"Bibliography"/"References"的起始页码
- 如果目录中没有参考文献条目(部分论文目录不含参考文献),则取最后一章(如结论章)结束页码作为起点,向后读取至论文末尾(致谢/附录之前)
- 用
Read工具 +pages参数读取参考文献全部页面(通常 5-15 页,一次或两次即可读完) - 参考文献页面内容作为独立数据源,供 Step 4 跨章一致性检查中的参考文献格式检查(B10)使用
LaTeX 项目发现
Glob("*.tex")→ 找\documentclass确定主文件 → 解析\input顺序
第 4 部分:八条核心规则
规则 1:消灭"我们" — 零容忍
博士学位论文中严禁使用"我们"。所有实例必须替换为:
- "本文" / "本章" / "本节"(根据作用域选择)
- 被动句式
- 万能替代句式:"为了(问题)…需要(提出的东西)…;通过(具体的手段)…设计了(设计的方法)…"
改写前:
我们提出了一种新的图像分割方法。我们在三个数据集上验证了该方法的有效性。
改写后:
本章提出一种新的图像分割方法,并在三个数据集上验证其有效性。
规则 2:删除 AI 填充词
以下词汇在学术文本中属于 AI 痕迹,应删除或替换:
- "此外" → 直接陈述下一点,或用"同时"
- "值得注意的是" → 删除,直接陈述
- "综上所述" → 删除或改为具体总结
- "需要指出的是" → 删除,直接陈述
保留的学术连接词(适度使用):
- "然而"、"因此"、"具体而言"、"相比之下"
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.
- 12d ago First seen · 1,044 lines · 134 tokens per session scan A c89cd02916b5
dissertation-polisher-zh is a skill published in the GitHub repository ChipsAhoyM/dissertation-polisher-zh (49 stars, last pushed 5mo ago), licensed MIT. It adds 134 tokens to every session and 13,396 once invoked, about $0.0007 per session on Opus 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.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.