# structured-extraction

> Claude/Codex skill by [@firecrawl](https://omgskills.com/library/firecrawl/index.md) · 1.2k stars · Updated 2026-04-19

Extract structured data matching a JSON schema from websites. Handles complex nested schemas, arrays, pagination, and validation. Always outputs via formatOutput.

## Install

```sh
git clone https://github.com/firecrawl/web-agent /tmp/web-agent && ln -s /tmp/web-agent/agent-core/src/skills/definitions/structured-extraction ~/.claude/skills/structured-extraction
```

## From README

Structured Extraction Use this skill when extracting data that must match a specific JSON schema. Strategy by task type Simple query (single fact or small object) Search for relevant results. Scrape promising results with a targeted query. Build the result object and call formatOutput immediately. Single target research (one entity, multiple fields) Search for relevant URLs. Scrape to extract data — stay in the orchestrator unless you have many independent sources (roughly 5+) where parallel workers clearly help. Compile findings and call formatOutput. List of items (array in schema) Search/scrape to get the list of items. Are all requested details included in the list? Yes: Build the result and call formatOutput. No: If there are many items (roughly 5+), use spawnAgents so each worker gets the item and fields; otherwise fetch details sequentially in the orchestrator. Aggregate all results and call formatOutput.

## Links

- HTML page: https://omgskills.com/skills/firecrawl/firecrawl-agent/structured-extraction/
- GitHub: https://github.com/firecrawl/web-agent
- Author: [@firecrawl](https://omgskills.com/library/firecrawl/index.md)

## More from this repo

- [competitor-analysis](https://omgskills.com/skills/firecrawl/firecrawl-agent/competitor-analysis/index.md) — Compare two or more companies, products, or platforms across pricing, features, positioning, and docs.
   - [@firecrawl](https://omgskills.com/library/firecrawl/index.md) · 1.2k stars
- [deep-research](https://omgskills.com/skills/firecrawl/firecrawl-agent/deep-research/index.md) — Multi-source research with source triangulation and fact-checking.
   - [@firecrawl](https://omgskills.com/library/firecrawl/index.md) · 1.2k stars
- [e-commerce](https://omgskills.com/skills/firecrawl/firecrawl-agent/e-commerce/index.md) — Navigate e-commerce sites to extract products, pricing, categories, and inventory.
   - [@firecrawl](https://omgskills.com/library/firecrawl/index.md) · 1.2k stars