Parse messy files
Find skills for parsing PDFs, extracting tables, running OCR, converting documents, and preparing file content for agent workflows.
Try this task
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Agent should be able to
Resolve
Returns the best skill, alternatives, install handoff, risk summary, and safety gate.
Text plan
Plain text version for Codex, Claude Code, Cursor, and custom agent runtimes.
Browse
Open the filtered registry view for this workflow and compare candidates manually.
Workflow map
Extract tables from PDFs
Convert files to markdown
Run OCR over scans
Normalize document metadata
Best first installs
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Install
Human review before install
Risk
Safe to try
Agent fit
Claude Code + CLI
Updated
Jun 17, 2026
$ npx skills add opendatalab/MinerUGet your documents ready for gen AI
Install
Agent install candidate
Risk
Safe to try
Agent fit
Claude Code + CLI
Updated
Jul 6, 2026
$ npx skills add docling-project/doclingKnowledge Agents and Management in the Cloud
Install
Agent install candidate
Risk
Safe to try
Agent fit
Claude Code + CLI
Updated
May 18, 2026
$ npx skills add run-llama/llama_cloud_servicesSkill shortlist
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
A fast, helpful, and open-source document parser
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
All-in-One Development Tool based on PaddlePaddle
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
Python tool for converting files and office documents to Markdown.
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
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.
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
A Repo For Document AI
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
A markdown parser and compiler. Built for speed.
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
A modern PDF library for TypeScript. Parse, modify, and generate PDFs with a clean, intuitive API.
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
A modern ebook manager and reader with sync and backup capacities for Windows, macOS, Linux, Android, iOS and Web
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
Low metadata risk · Review the audit page, then allow agent install in a sandboxed workflow.
Markdown parser, done right. 100% CommonMark support, extensions, syntax plugins & high speed. Now in Python!
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
Markdown parser, done right. 100% CommonMark support, extensions, syntax plugins & high speed
Low metadata risk · Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
FAQ
These answers are written for both human builders and agents consuming the Registry API.
Start by comparing MinerU, Docling, Llama Cloud Services. OpenAgentSkill ranks them by workflow fit, GitHub adoption, trust score, safety gate, and install readiness.
Yes. Use the linked Registry API prompt to query /api/skills/search with the task: "I need my agent to read PDFs, extract tables, and turn documents into structured data." and retrieve install handoff links for the top results.
No. Start with the highest-fit skill, test it in a sandbox workflow, and add companion skills only when the task needs extra coverage.