version: "3.0.1" name: PDF to Markdown description: "Convert PDF files to Markdown with table recognition. Use when extracting text, converting tables, summarizing documents, fixing formatting issues." author: BytesAgain homepage: https://bytesagain.com source: https://github.com/bytesagain/ai-skills

pdf-to-markdown

CLI tool for pdf to markdown

Commands

md

scripts/script.sh md

txt

scripts/script.sh txt

json

scripts/script.sh json

convert

scripts/script.sh convert

batch

scripts/script.sh batch

extract

scripts/script.sh extract

headers

scripts/script.sh headers

table

scripts/script.sh table

info

scripts/script.sh info

list

scripts/script.sh list

export

scripts/script.sh export

config

scripts/script.sh config

help

scripts/script.sh help

version

scripts/script.sh version

Examples

scripts/script.sh help
scripts/script.sh md

Configuration

Data Storage

All data saved in ~/.pdf-to-markdown/. Runs on your machine without external calls.

Requirements

• bash 4.0+

Powered by BytesAgain | bytesagain.com | hello@bytesagain.com

这个工具质量中等偏上，文档说明详细、使用方法清晰，适合需要将 PDF 文本转为 Markdown 的用户。纯标准库实现是亮点，配置简单。优点是提供了离线自检和预览功能，错误提示规范。但需要注意它只能处理文字型 PDF，遇到扫描件、加密文件或复杂表格就会失效，标题识别也容易出错，实际使用时建议对输出结果进行人工检查。总体而言，作为基础文本提取工具够用，但不要期待它能完美保留复杂排版。