Skill Detail
Extract schema-shaped JSON from JavaScript-rendered pages with llm-scraper
Open a rendered page, describe the fields you want, and return structured data without hand-maintaining brittle selectors.
Research & ScrapingMulti-Framework
Research & Scraping
Multi-Framework
Security Reviewed
⭐ 6.3k GitHub stars
⬇ 3.8k/wk npm
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill extract-schema-shaped-json-from-javascript-rendered-pages-with-llm-scraper
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Node.js, Playwright-compatible browser runtime, llm-scraper package, supported LLM provider credentials, target URLs
Install & setup
Install llm-scraper together with Playwright and the schema dependencies shown in the README, configure a supported model provider, then run it against rendered pages with a defined output schema.
Author
mishushakov
Publisher
Individual
Last updated
Apr 15, 2026
Quick brief
Use llm-scraper when an agent needs to turn a rendered web page into structured output for a known schema, especially when the page depends on client-side rendering. The user is not invoking a general browser automation product here. The workflow is bounded extraction: open the page, map content into a schema, and return structured JSON. That boundary keeps it distinct from generic browser control and from broader crawling platforms.