OpenAgentSkill Task
Task: Convert PDFs to markdown
Intent: Extract readable text, tables, and metadata from PDFs for agent workflows.
Agent prompt: Find the best skill for converting PDF files into clean markdown while preserving headings, tables, and metadata.

Success criteria:
- Handles common PDFs
- Keeps headings and tables usable
- Reports extraction limits

Do not use when:
- The PDF is encrypted
- Scanned documents need manual OCR review
- Legal/medical data requires compliance review

Resolve API:
https://www.openagentskill.com/api/agent/resolve?task=Find%20the%20best%20skill%20for%20converting%20PDF%20files%20into%20clean%20markdown%20while%20preserving%20headings%2C%20tables%2C%20and%20metadata.&agent=codex&max_risk=medium

Ranked skills:
1. OCRmyPDF (ocrmypdf-ocrmypdf)
   Match score: 784
   OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
   Trust: 88/100 Production candidate
   Audit: 90/100 Safe to try
   Install: 
   Detail: https://www.openagentskill.com/skills/ocrmypdf-ocrmypdf
   Install API: https://www.openagentskill.com/api/skills/ocrmypdf-ocrmypdf/install
---
2. MinerU (opendatalab-mineru)
   Match score: 775
   Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
   Trust: 86/100 Production candidate
   Audit: 89/100 Safe to try
   Install: 
   Detail: https://www.openagentskill.com/skills/opendatalab-mineru
   Install API: https://www.openagentskill.com/api/skills/opendatalab-mineru/install
---
3. PyMuPDF (pymupdf-pymupdf)
   Match score: 763
   PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
   Trust: 89/100 Production candidate
   Audit: 92/100 Safe to try
   Install: 
   Detail: https://www.openagentskill.com/skills/pymupdf-pymupdf
   Install API: https://www.openagentskill.com/api/skills/pymupdf-pymupdf/install
---
4. Docling (docling-project-docling)
   Match score: 748
   Get your documents ready for gen AI
   Trust: 87/100 Production candidate
   Audit: 91/100 Safe to try
   Install: 
   Detail: https://www.openagentskill.com/skills/docling-project-docling
   Install API: https://www.openagentskill.com/api/skills/docling-project-docling/install
---
5. PaddleOCR (paddlepaddle-paddleocr)
   Match score: 723
   Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
   Trust: 89/100 Production candidate
   Audit: 92/100 Safe to try
   Install: 
   Detail: https://www.openagentskill.com/skills/paddlepaddle-paddleocr
   Install API: https://www.openagentskill.com/api/skills/paddlepaddle-paddleocr/install