Pdf2md Agent Skill

将 PDF、DOCX、PPTX、XLSX、HTML、CSV 等文档转换为适合 LLM 处理的 Markdown。英文 PDF 使用 md_convert.py；中文论文和中文扫描 PDF 使用 md_convert_zh.py。用户要求阅读、总结、翻译、问答、引用或提取 PDF/Office 文档内容时使用；先转换，再读取生成的 Markdown。

8 starsDocuments & Office Files

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add taotaoboom/pdf2md-agent-skill --skill pdf2md-agent-skill

Manual install

git clone --depth 1 https://github.com/taotaoboom/pdf2md-agent-skill.git /tmp/pdf2md-agent-skill
mkdir -p ~/.claude/skills
cp -r /tmp/pdf2md-agent-skill/. ~/.claude/skills/pdf2md-agent-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# pdf2md-agent-skill - PDF/文档转 Markdown

## 何时触发

需要读取 PDF 内容时，先使用本 skill 转换为 Markdown。

先将 PDF 转换为 Markdown，再用当前 Agent 可用的文本读取工具读取输出文件。

触发场景：

- 用户给了 PDF 路径，要求阅读、总结、分析、翻译、问答
- 需要引用 PDF 中的具体内容
- 需要提取 PDF 中的表格、公式、参考文献

## 标准工作流

先将 `<skill_dir>` 解析为本 `SKILL.md` 所在目录。不要假定 skill 安装在 `~/.claude/skills`，因为 Codex、自定义安装和 Windows 的路径不同。

按固定顺序执行：

```bash
# 步骤 1：根据论文语言选择 PDF 脚本后转换
# 英文论文
python3 "<skill_dir>/scripts/md_convert.py" "<pdf路径>" -o "<工作区临时目录>/<名称>.md"

# 中文论文或中文扫描论文
python3 "<skill_dir>/scripts/md_convert_zh.py" "<pdf路径>" -o "<工作区临时目录>/<名称>.md"

# 步骤 2：用当前 Agent 的文本读取工具读取生成的 .md 文件
```

### PDF 脚本选择规则

1. 用户明确说明论文为中文或英文时，使用对应脚本。
2. 用户未说明时，Agent 根据用户上下文、文件名和第一页可读文本判断正文语言。
3. 无法可靠判断时，先询问用户；不要自行猜测并调用某个脚本。
4. 中英混排但中文正文为主时使用 `md_convert_zh.py`；英文正文为主时使用 `md_convert.py`。
5. Word、PPT、Excel、HTML、CSV 等非 PDF 格式继续使用 `md_convert.py`。

**示例：**

```bash
# 英文论文
python3 "<skill_dir>/scripts/md_convert.py" \
  "/path/to/some-paper.pdf" \
  -o "./some-paper.md"

# 中文论文
python3 "<skill_dir>/scripts/md_convert_zh.py" \
  "/path/to/chinese-paper.pdf" \
  -o "./chinese-paper.md"
```

然后读取 `./some-paper.md`。

## 英文 PDF：`md_convert.py`

英文 PDF 有多类页面，处理策略不同。`md_convert.py` 自动逐页判断：

| 页面类型             | 脚本策略               | 说明                                          |
| -------------------- | ---------------------- | --------------------------------------------- |
| 普通文本页           | PyMuPDF 提取           | 快、免费，段落合并+双栏排序+页眉过滤          |

Read the full skill on GitHub

Details

Skill name: pdf2md-agent-skill
Repository: taotaoboom/pdf2md-agent-skill
License: MIT
Repo updated: 25 July 2026

FAQ

What does the Pdf2md Agent Skill skill do?

How do I install the Pdf2md Agent Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add taotaoboom/pdf2md-agent-skill --skill pdf2md-agent-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Pdf2md Agent Skill popular?

It lives in taotaoboom/pdf2md-agent-skill, which has 8 GitHub stars and 0 forks.

Related skills

Peg Design

v0id-byte/peg-design-system

Use this skill to generate well-branded slides, presentations, and data-driven design artifacts in the Peg visual language. Minimal, type-led, Apple-keynote-inspired. Contains design guidelines, color/type/spacing tokens, React components, and 7 production-ready slide templates.

Documents & Office Files

Moonland Deck

severli93/moonland-deck

Build 16:9 HTML presentation decks (and posters/cards that borrow the same look) in the "Dopamine-Swiss" visual language — a Swiss International grid skeleton crossed with a dopamine 4-color stage system and hand-painted SVG paint-blob highlights. Goes further than styling: it can read a local project, reverse-infer what's worth presenting, write a 演讲大纲.md outline, build a single-file deck from it, and ship a deck the user edits in the browser and syncs back to the outline. Use whenever the user wants a slide deck, talk deck, 演讲 deck, 分享 PPT replacement, keynote, HTML slides, pitch, or a poste

Documents & Office Files

Project Resume Writer

oxygen914/project-resume-writer

Analyze project directories, source code, technical documents, work notes, internships, papers, open-source contributions, platform work, or other career evidence and turn them into evidence-backed Chinese resume material. Use when the user asks to write, polish, quantify, tailor, or evaluate project experience; generate a copy-ready resume project entry; build a detailed project-highlight material library; list technical highlights for later resume selection or interviews; or decide how many project bullets/highlights to write. Also use for 简历项目写法, 项目经历, 项目亮点, 亮点素材库, 技术亮点清单, 投递版, 简历量化, 数据化表达,

Documents & Office Files

Grill My Resume As Manager

letya999/grill-my-resume-as-manager

Hard grill of a Project/Delivery/Tech/Product manager resume: evidence (XYZ), anti-persona flags, role clarity, 10-second recruiter read, optional vacancy-pool match. Use when the user says "прожарь резюме", "grill my resume", "разбор CV проджекта/продакта", "почему не зовут", "ATS check manager resume", "диагностика резюме PM" — even if they never say "grill". Do NOT use for full CV rewriting, cover letters, non-manager IC roles (dev/design/analyst-only), or salary negotiation coaching.

Documents & Office Files

Talisman

jeunecraack/talisman-skill

Generate a polished, on-brand PDF guide/handbook/whitepaper from a codebase or project using LaTeX (.tex -> .pdf) or Markdown->pandoc->pdf, with a designed cover page, the product's real brand colors and logo, a subtle branded page background, and TikZ diagrams (domain models, flows, state machines). Use for any branded PDF derived from a real app: ".tex to pdf", "make a PDF guide", "document how X works", "cover page with our logo", or "in the style of <product>".

Documents & Office Files

Baoyan Resume Writing

meanwhile371/baoyan-resume-writing

Use when 用户提供科研竞赛项目材料（doc/docx/PDF/调查报告/比赛章程/项目报告）要求写入保研简历，或需要将项目经历压缩为学术话语、统一多个项目的表述风格与数据口径，或需要为每条经历生成面试答辩预答、把多条经历串成科研主线叙事。触发词：保研简历、个人陈述、科研竞赛经历、项目包装、简历条目、套磁信经历段、答辩预答、科研主线、夏令营申请表。

Documents & Office Files

Browse the most popular Claude skills, all documents & office files skills, or write your own with the skills generator.