extract-schema
Turn any webpage into clean, structured JSON matching a TypeScript interface or schema. Use when the user wants to extract products, profiles, articles, or any structured data from a webpage — and get it back as typed, usable JSON.
Install
With your agent
Install OMGSkills skill "olostep/olostep-claude-code-plugin:skills/extract-schema" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/olostep/olostep-claude-code-plugin /tmp/olostep-claude-code-plugin && ln -s /tmp/olostep-claude-code-plugin/skills/extract-schema ~/.claude/skills/extract-schemaFrom README
Olostep Extract Schema Turn any unstructured webpage into perfectly formatted JSON or TypeScript objects. Scrape the site, then parse the data to match the user's exact schema. When to use User provides a URL and a TypeScript interface and says "extract the data to match this shape" User wants to populate a database or create seed data from a real website User is building a directory or aggregator and needs to scrape profiles, pricing, or features into JSON User wants to convert an unstructured blog post or news article into a structured metadata object Instructions When the user provides a URL and a schema (via $ARGUMENTS or in conversation): Review the TypeScript interface, JSON schema, or data shape requested by the user. Scrape the target URL using mcpolostepscrapewebsite (use outputformat: markdown — it's optimized for LLM parsing). If scraping multiple pages (like a list of profiles), use mcpolostepbatchscrapeurls.