agentskills.codes
PD

pdf-to-md

by huangyrcnProductivitySource

Converts PDF documents to Markdown via API.

MarkdownResearchPython

Install

mkdir -p .claude/skills/pdf-to-md && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11558" && unzip -o skill.zip -d .claude/skills/pdf-to-md && rm skill.zip

Installs to .claude/skills/pdf-to-md

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Convert a PDF into high-quality Markdown through the MinerU API VLM pipeline. Use this skill whenever the user wants PDF-to-Markdown conversion, OCR-like extraction, paper text extraction, or Markdown plus extracted images from a PDF. This skill supports the API backend only and always uses the high-quality VLM model configuration.
333 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • →Convert PDF files to Markdown format
  • →Extract text and images from academic PDFs
  • →Generate Markdown output with associated image directories
  • →Support language hints for conversion (en or ch)
  • →Utilize the MinerU API VLM pipeline for high-quality parsing

How it works

The skill uses a Python script to call the MinerU API, which processes the PDF through its VLM pipeline to extract content and convert it into Markdown format, including images.

Inputs & outputs

You give it
A local PDF file path and an optional language hint.
You get back
A Markdown file (`<pdf_stem>.md`) and an image directory (`<pdf_stem>_images/`) next to the original PDF.

When to use pdf-to-md

  • →Converting papers to Markdown
  • →Extracting images and text from PDFs
  • →Digitizing academic documents

About this skill

PDF to Markdown

Converts a PDF to:

<pdf_stem>.md
<pdf_stem>_images/

Prerequisite

Set the MinerU API token:

export MINERU_API_TOKEN="your_token_here"

Usage

python3 "${SKILL_DIR}/scripts/mineru-api.py" <pdf_path> [-l lang]
  • pdf_path: local PDF path
  • -l lang: language hint, en or ch

Backend contract

  • Supported backend: MinerU API only
  • Model: VLM
  • Goal: highest available parsing quality for formulas, tables, and mixed-layout academic PDFs

Output behavior

  • Output files are written next to the PDF
  • Existing Markdown and image directories for the same stem may be overwritten
  • Example: paper.pdf -> paper.md and paper_images/

When not to use it

  • →When the MinerU API token is not set
  • →When a backend other than MinerU API is required
  • →When the goal is not high-quality parsing for academic layouts

Prerequisites

MINERU_API_TOKEN environment variable set

Limitations

  • →Requires the `MINERU_API_TOKEN` environment variable to be set.
  • →Supports only the MinerU API backend.
  • →Output files are written next to the PDF and may overwrite existing Markdown and image directories.

How it compares

This skill provides a specialized PDF to Markdown conversion using the MinerU API's VLM pipeline, optimized for academic layouts and structured content, unlike generic PDF converters.

Compared to similar skills

pdf-to-md side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pdf-to-md (this skill)04moReviewBeginner
biorxiv-database79moReviewBeginner
lecture-transcript-slide-matcher69moReviewAdvanced
arxiv-to-md47moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

biorxiv-database

lifangda

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

780

lecture-transcript-slide-matcher

az9713

Combines YouTube lecture transcripts with PDF slides to create an interactive HTML page. Matches each slide to corresponding transcript segments, organized by key concepts. Use when users want to create synchronized lecture notes from transcript text files and slide PDFs.

669

arxiv-to-md

solatis

Convert arXiv papers to LLM-consumable markdown. Invoke when user provides an arXiv ID or URL, or when syncing academic papers from a PDF folder to a markdown destination.

412

youtube-collector

greatSumini

유튜브 채널을 등록하고 새 컨텐츠를 수집하여 자막 기반 요약을 생성하는 skill. 사용자가 (1) 유튜브 채널 등록/관리를 요청하거나, (2) 등록된 채널의 새 영상 수집을 요청하거나, (3) 유튜브 영상 요약을 요청할 때 사용. 데이터는 .reference/ 폴더에 YAML 형식으로 저장됨.

16

extract-transcript

pamelafox

>-

00

local-deep-research-guide

wentorai

Deep research agent searching 10+ sources with local or cloud LLMs

00

Search skills

Search the agent skills registry