AI Agent Skills

Computer vision assisted tool to extract numerical data from plot images.

Crawl a website starting from a URL, find relevant pages, and extract data – all guided by your natural language prompt.

The headless Chrome/Chromium driver on top of Puppeteer. Take screenshots, generate PDFs, extract text and HTML with a production-ready API.

Python scripts for ETL (extract, transform and load) jobs for Ethereum blocks, transactions, ERC20 / ERC721 tokens, transfers, receipts, logs, contracts, internal transa…

Learn step-by-step how to scrape Google Trends data and make a result comparison using Python and Oxylabs SERP API. Extract keywords, their popularity, breakdown by regi…

GitHub Action to extract metadata (tags, labels) from Git reference and GitHub events for Docker

What's in your data? Extract schema, statistics and entities from datasets

Read, create, or edit Microsoft Word .docx files — extract/summarize

Read, extract (text/tables), create, merge/split/rotate, watermark, encrypt,

AI Map is an AI-powered website mapping tool by Oxylabs AI Studio that uses natural language prompts to intelligently discover and extract relevant URLs from any website.

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, he

Gmail: Read a message and extract its body or headers.

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selecto…

Procedure for extracting structured data from PDFs with opendataloader-pdf (ODL) correctly: read the installed tool's own help to discover its current options, build the…

Build a source-grounded deep-reading Paper Card for one scientific paper, preprint, PDF, DOI, arXiv page, publisher article, or pasted paper text. Use when the user asks…

对学术文献逐条执行多源交叉验证，逐字段对比作者、标题、年份、卷期、页码， 标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题，输出结构化验证报告。 可批量处理整篇论文/开题报告的参考文献列表，也可单条校验，支持与 Zotero 同步修正。