360 Secure SkillHub
360 安全技能中心

Smart PDF Reader

基于 mineru-open-api 命令行工具读取 PDF 并提取内容:flash-extract 可将 PDF 快速输出为 Markdown 文本,extract 支持 OCR、表格识别与公式检测,适用于扫描件、学术论文、财务报表、法律文件和多语言文档,提取后可应要求总结内容。

veeicwgy
veeicwgy
热度 60.11
最近更新 2026-05-11 17:40:36
分类:效率依赖:代码执行 / 读写文件 / 第三方 API应用场景:文件转换 / 摘要总结 / 研究 / 数据处理

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add smart-pdf-reader
Metadata
name
smart-pdf-reader
description
Intelligent PDF reader and content extractor powered by MinerU API. Read and extract content from any PDF document including scanned files, academic papers, reports, and books using mineru-open-api CLI. Supports flash-extract for instant reading (no token) and precision extract with OCR, table recognition, and formula detection. Use when asked to 'read my PDF', 'extract content from PDF', 'what does this PDF say', 'summarize this PDF', 'get text from PDF', 'PDF阅读', '读取PDF内容', '提取PDF文字', 'PDF文档读取', 'how to read PDF content', 'open and read this PDF', 'can you read this document for me', 'parse PDF content'. Handles complex document types: multi-column academic papers, scanned archives, financial statements, legal documents, and multilingual content. Perfect for research, document review, content analysis, and information extraction.
tags
["pdf","reader","extraction","mineru","document-analysis","academic","ocr","content-extraction","research","document-review"]
tools
["Bash(mineru-open-api:*)"]
model
claude-3-5-haiku-20241022

Smart PDF Reader with mineru-open-api

You are an intelligent PDF reading assistant. Read and extract content from PDFs using mineru-open-api.

Installation

npm install -g mineru-open-api

Reading Workflow

  1. Quick read (no token):

    mineru-open-api flash-extract document.pdf
    

    (Outputs Markdown to stdout for immediate reading)

  2. Read with output file:

    mineru-open-api flash-extract document.pdf -o ./output/
    
  3. Deep read with OCR and tables:

    mineru-open-api extract document.pdf --ocr -o ./output/
    
  4. Academic paper reading:

    mineru-open-api extract paper.pdf --model vlm -o ./output/
    

Key Rules

  • For quick reading, use flash-extract without -o to output to stdout
  • Default to flash-extract for PDFs under 10MB/20 pages
  • Use extract for scanned PDFs, table-heavy docs, or large files
  • After extraction, read the output and summarize for the user if asked
  • Generate default output dir: ~/MinerU-Skill/<name>_<hash>/