According to AlphaMoat, as of 2026-09, Mineru Pdf Parser has 1,558 downloads and 1 stars — ranked #4,730 of 5,078 AI skills overall, and #385 of 435 in Office.

Installs

156

Downloads

1.6K

Stars

Overall Rank

#4,730

Top 94% overall · Top 89% in Office

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	32	1.2K	1	1
SkillHub ↗	156	1.6K	1	—

Platforms count differently and update at different times.

What this skill does

It accepts local files or online URLs and can extract formulas and tables or OCR scanned PDFs; results are saved locally. PDF contents and MINERU_TOKEN are sent to MinerU, so submit documents only when confidentiality requirements and service terms allow it. Treat downloaded or parsed results as untrusted and inspect them before reuse. Requires Python and requests. Choose a supported engine and language; the documented defaults are vlm and Chinese. Parsing is asynchronous unless waiting is requested, and results are stored under ~/.openclaw/MinerU_Results/. Validate remote archives safely, including member paths and size/time limits, before extraction. Review the implementation rather than assuming downloaded ZIP contents are safe.

Profile published 2026-10-27

What you can do with it

Convert a PDF to Markdown for analysis
Extract text, tables or formulas from a scanned PDF

When to use it

When the document may be sent to MinerU and the token is provided securely through an environment variable

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Explain the parsing workflow and external-transfer boundary for this approved PDF.

List security checks before reusing remote parsing results.

Monthly Trend

Downloads1.6K

Stars1

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	1.6K	—	1
2026-08	1.3K	+15.2%	1
2026-07	1.1K	+24.1%	1
2026-06	879	+15.2%	1
2026-05	763	—	1
2026-03	514	—	1

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.3 KB · ClawHub v3.0.3

---
name: pdf-parser
description: 使用 MinerU API 将 PDF 解析为 Markdown，支持公式、表格、OCR。提供本地文件和在线 URL 两种解析方式。触发条件：(1) 用户说"解析 PDF [路径]"，(2) 用户说"将 PDF 转为 Markdown"，(3) 在 paper-workflow 中自动调用。使用场景：学术论文解析、文档提取、知识库构建。
homepage: https://mineru.net
metadata: {"clawdbot":{"emoji":"📄","requires":{"env":["MINERU_TOKEN"]},"primaryCredential":"MINERU_TOKEN"}}
---

# PDF Parser Skill

基于 [MinerU](https://github.com/opendatalab/MinerU) 提供 PDF 解析能力。

Show all (96 lines)


## 功能

- **PDF 解析**: 将 PDF 转换为 Markdown 格式
- **公式识别**: 支持 LaTeX 公式提取
- **表格识别**: 自动识别并转换表格结构
- **OCR**: 支持图片型 PDF 文字识别
- **多语言**: 支持中文、英文，日文、韩文等

## ⚠️ 安装前必读

**使用本技能即表示：**
1. 你愿意提供你的 MinerU API Token (`MINERU_TOKEN`)
2. Token 会被发送给 https://mineru.net/
3. 确认 MinerU 服务可信，接受其隐私政策
4. 已在本地源码中确认无额外意外行为

## 前提条件

### 1. 安装依赖

```bash
pip install requests
```

### 2. 获取 MinerU Token

访问 <https://mineru.net/> 注册并获取 API Token。

### 3. 设置环境变量

**Windows (PowerShell):**
```powershell
$env:MINERU_TOKEN = "your-token-here"
```

**macOS / Linux:**
```bash
export MINERU_TOKEN=your-token-here
```

## 支持的引擎

| 引擎 | 说明 |
|------|------|
| vlm | VLM 引擎（默认） |
| pipeline | 管道引擎 |
| MinerU-HTML | HTML 输出 |

## 快速开始

```bash
# 解析 PDF (默认 vlm 引擎)
python scripts/mineru_api.py -f <pdf路径> --wait

# 指定引擎
python scripts/mineru_api.py -f <pdf路径> --engine pipeline --wait
```

## 选项

| 参数 | 说明 | 默认值 |
|------|------|--------|
| -f, --files | 本地 PDF 文件 | - |
| --engine | 解析引擎 | vlm |
| --lang | 语言 (ch/en/ja/ko) | ch |
| --wait | 等待解析完成 | 否 |

## 环境变量

| 变量 | 必填 | 说明 |
|------|------|------|
| MINERU_TOKEN | 是 | MinerU API Token |

## 输出

解析结果保存在 `~/.openclaw/MinerU_Results/` 目录下。

## 工作流

1. 设置 `MINERU_TOKEN` 环境变量
2. 执行解析命令
3. 等待解析完成
4. 读取 full.md 分析内容
5. 根据内容重命名目录