firecrawl-search

Searches the web and scrapes full page content into JSON files via the Firecrawl CLI.

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-search-leonardoacosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-search
Source: https://github.com/leonardoacosta/agents/tree/main/skills/firecrawl-search
Command: npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-search-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When you don't have a specific URL, finding relevant sources, articles, or news requires manual searching and then visiting each result to read its content. This Skill runs web searches through the Firecrawl CLI and optionally scrapes full page content from results, saving everything as structured JSON files for downstream processing. ## Core Features & Use Cases - Web Search with JSON Output: Run queries and save results to .firecrawl/ files, keeping raw data out of the context window. - Optional Full-Page Scraping: Add --scrape to fetch complete page content from search results in one pass, avoiding redundant fetches. - News and Category Filtering: Restrict results to news sources with time windows (--sources news --tbs qdr:d) or blend in developer-index results via --categories developer. - Use Case: Researching a new library? Search for it, scrape the top results' full content, extract URLs with jq, and send one feedback event to refund a credit. ## Quick Start Ask the agent to search the web for your topic with firecrawl and save the results with full page content to a JSON file under .firecrawl/.

Frequently Asked Questions about firecrawl-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search the web and get full page content with Firecrawl?

Run `firecrawl search "your query" --scrape -o .firecrawl/scraped.json --json`. The `--scrape` flag fetches full page content from each result in the same call, so you avoid re-scraping URLs later and save credits.

How do I search only recent news with the firecrawl CLI?

Use `firecrawl search "your query" --sources news --tbs qdr:d -o .firecrawl/news.json --json`. The `--sources news` flag restricts results to news and `--tbs qdr:d` limits them to the past day.

When should I use firecrawl-search instead of firecrawl-scrape?

Use firecrawl-search when you do not have a specific URL and need to discover sources, articles, or news. Use firecrawl-scrape when you already know the exact URL to extract content from.

Does firecrawl search support academic papers or developer documentation?

Not directly. The `--categories research` flag is only a website filter, not the paper index. Use the dedicated firecrawl-research-index skill for papers and firecrawl-developer-index for library, API, error, or bug questions.

Why did my firecrawl search-feedback call fail or get rejected?

Feedback must be sent within about two minutes of the search and include substantive content: `good` ratings need `--valuable-sources`, while `partial` or `bad` ratings need `--missing-content` or `--query-suggestions`. Zero-result searches write no output file, so verify results exist before reading the search id.

How do I opt out of firecrawl search feedback?

Set `FIRECRAWL_NO_SEARCH_FEEDBACK=1` or `FIRECRAWL_DISABLE_SEARCH_FEEDBACK=1` and the CLI silently skips the feedback call. Team admins can also disable it server-side, in which case the CLI exits 0 without sending anything.