据 AlphaMoat 统计,截至 2026-09,Ocr Document 累计下载 4,245 次、获 2 个星标,在全部 5,078 个 AI 技能中排名第 2,342 位,在「办公效率」分类(435 个)中排名第 197 位。

累计安装

398

累计下载

4,245

星标

全站排名

#2,342

全站前 47% · 「办公效率」前 46%

平台	累计安装	累计下载	星标	评论
ClawHub ↗	44	4,245	-	-
SkillHub ↗	398	3,596	2	—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

mineru-open-api可接收本地文件或URL，并设置识别语言和输出目录。flash-extract会上传云端，文档称无需账户，限制为10MB及20页；完整布局OCR另需认证。识别结果应核对，不能据文档保证数据留存政策。

资料发布于 2026-10-27

可以用来做什么

从扫描PDF或页面照片提取文字

什么时候用

原始内容是扫描图像且需可编辑文本时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

说明这份扫描件的云端处理和大小限制，确认后再提取并标注模糊文字。

月度数据趋势

累计下载4,245

星标2

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份	累计下载	环比	星标
2026-09	4,245	—	2
2026-08	4,085	+24.8%	2
2026-07	3,272	+98.9%	2
2026-06	1,645	+13.8%	2
2026-05	1,446	—	1
2026-03	658	—	-

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

2.6 KB · ClawHub v1.0.0

---
name: ocr_document
description: "OCR document extraction - extract text from scanned documents, photos, and images using OCR. Use when reading scanned PDFs, photographed pages, handwritten notes, or any document that needs optical character recognition."
homepage: https://mineru.net
metadata: {"openclaw":{"emoji":"🔍","requires":{"bins":["mineru-open-api"]},"install":[{"id":"npm","kind":"node","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via npm"},{"id":"uv","kind":"uv","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via uv"},{"id":"go","kind":"go","package":"github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api","bins":["mineru-open-api"],"label":"Install via go install","os":["darwin","linux"]}]}}
---

# OCR Document - Extract Text from Scanned Documents and Images

Extract text from scanned documents and images using OCR via MinerU Open API. No API key required.

展开全部(共 66 行)


## Quick Start

```bash
# OCR a scanned PDF
mineru-open-api flash-extract scanned.pdf

# OCR an image of a document
mineru-open-api flash-extract page-photo.jpg

# OCR from URL (no download needed)
mineru-open-api flash-extract https://example.com/scanned.pdf

# Specify language for better accuracy
mineru-open-api flash-extract scanned.pdf --language en

# Save OCR result to file
mineru-open-api flash-extract scanned.pdf -o ./output/
```

## Language Rule

You MUST reply to the user in the SAME language they use. This is non-negotiable.

## Capabilities

- OCR for scanned PDFs, photographed documents, images
- Supports PDF, PNG, JPG, WebP, BMP, TIFF
- Supports both local files and URLs directly
- Language hint with `--language` (default: `ch`, use `en` for English)
- No API key, no signup, no authentication
- Max 10MB / 20 pages per document

## When to Use

- User asks to "OCR" a document or image
- User has a scanned PDF that needs text extraction
- User shares a photo of a page and wants the text
- User mentions "scan", "handwriting", or "recognize text"

## CLI Reference

Run `mineru-open-api flash-extract --help` for all available options.

## Data Privacy

- `flash-extract` uploads the document to MinerU's cloud API for processing and returns the result. No account or API key is required.
- Documents are processed in real-time and are not stored after extraction.
- For details, see https://mineru.net

## Notes

- Best results with clear, high-resolution scans
- For higher precision OCR with full layout preservation, use `mineru-open-api extract --ocr` (requires auth via `mineru-open-api auth`)
- If the CLI cannot be installed via npm/uv/go, download it from https://mineru.net/ecosystem?tab=cli