firecrawl-search_skill
- TypeScript
147
GitHub Stars
1
Bundled Files
3 weeks ago
Catalog Refreshed
1 month ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstart where the catalogue uses aiagentskills.
npx veilstart add skill firecrawl/cli --skill firecrawl-search- SKILL.md2.9 KB
Overview
This skill provides web search with optional full-page content extraction, returning real search results as structured JSON and, when requested, complete page content in Markdown. It is designed to find articles, news, and sources and to feed downstream scraping or crawling workflows without relying on short snippets. Use it whenever you need thorough, machine-readable search output rather than brief summaries.
How this skill works
The skill runs a web search query and returns ranked results as JSON, including metadata like title, URL, snippet, and source type. With the --scrape option it fetches and converts each result page into a Markdown representation (or other formats), embedding full text so an agent can read or index entire pages. It supports filters for sources, categories, time ranges, location, and result limits.
When to use it
- You need to find articles, recent news, or authoritative sources for research.
- You want full-page content for downstream extraction, summarization, or indexing.
- You don’t have a specific URL and need discovery across the web.
- You need search results exported as JSON for automation or pipelines.
- You want time- or region-filtered search (recent news, local results).
Best practices
- Use --scrape only when you need full content to avoid redundant fetches and save credits.
- Write results to a dedicated .firecrawl/ output file to keep agent context small.
- Start broad, then refine with categories, sources, or time filters to focus results.
- Limit results (--limit) to what you will actually process to conserve resources.
- Combine with downstream scrape/crawl skills for deeper extraction or site mapping.
Example use cases
- Gather the latest news about a product launch from the past day using news source and time filters.
- Discover academic or GitHub resources on a research topic and scrape the top pages for full text.
- Build a JSON feed of URLs and Markdown page content to feed a custom search index or summarizer.
- Find and export primary sources for fact-checking or evidence collection in an investigation.
- Locate region-specific coverage by setting country or location parameters.
FAQ
Yes — enable the --scrape flag to fetch and convert each result page into full-page Markdown or specified scrape formats.
How do I avoid bloating the agent context with long pages?
Output results to a file (e.g., .firecrawl/search.json or .firecrawl/scraped.json) and reference that file in downstream steps instead of pasting content into the agent chat.
