Firecrawl Build Search

From the author

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.

— the description by firecrawl

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides guidance on integrating the Firecrawl search functionality into product code and agent workflows. It is designed for scenarios where an application must discover relevant web sources based on a query rather than a known URL. The skill emphasizes using search as a discovery and ranking mechanism, separating the initial search phase from subsequent scraping or interaction tasks to maintain predictable and efficient data pipelines.

What it does

Enables web discovery based on user queries.
Provides a foundation for building query-to-URL pipelines.
Supports selective hydration of search result content.
Offers guidance on integrating search with downstream scraping or interaction tasks.
Defines clear escalation paths for specialized search needs like research papers or developer documentation.

When to use it

When your application needs to find information before it can extract data.
When the user input is a search query rather than a direct URL.
When you need to generate a shortlist of web pages for further processing.
When you require current web results for answer generation or topic discovery.

Advantages

Separates discovery from extraction for cleaner, more modular code.
Reduces unnecessary scraping by allowing selective follow-up.
Provides a predictable contract for downstream automation logic.
Integrates seamlessly with other Firecrawl capabilities for end-to-end workflows.

Usage examples

“I need to find the latest news on a specific industry topic to generate a summary.”: The agent uses the search skill to query the web, retrieves a list of relevant URLs, and then proceeds to extract content from the most pertinent pages.
“Build a pipeline that finds competitor websites based on a list of keywords.”: The system executes search queries for the provided keywords, filters the results, and compiles a shortlist of target URLs for future scraping.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/firecrawl/firecrawl-build-search/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip firecrawl-build-search.zip -d .agents/skills

Documentation by firecrawl

Use this when the application starts with a query, not a URL.

Use This When

the user asks a question and the product must discover sources first
the feature needs current web results
you want to turn a search query into a shortlist of pages for later scraping

Default Recommendations

Use /search first when URL discovery is part of the product behavior.
Keep search and extraction conceptually separate unless scraping search results is clearly required.
Prefer selective follow-up extraction over broad hydration when cost or latency matters.

Common Product Patterns

answer generation with cited sources
company, competitor, or topic discovery
research workflows that produce a shortlist of web pages before deeper extraction
query-to-URL pipelines for later /scrape or /interact

Note that "research workflow" here means discovering web pages. If the product is searching published papers, that is a different surface — see the escalation rules below.

Escalation Rules

If you already have the URL, use firecrawl-build-scrape.
If the result page then requires clicks or form interaction, escalate to firecrawl-build-interact.
If the feature searches published research papers — biomedical, clinical, and life-science literature (PubMed, bioRxiv, medRxiv) or arXiv preprints — /search is the wrong surface. Use the research paper index instead: firecrawl-research-index. Passing categories: ["research"] to /search does not query that index; it filters an ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them — no abstract search, related-paper expansion, or full-text passages.
If the feature answers developer questions from issues, pull requests, READMEs, or documentation pages, use the developer index instead: firecrawl-developer-index. The same caveat applies to categories: ["developer"].

Implementation Notes

Treat /search as discovery, ranking, and source selection.
Be explicit about whether the product needs snippets, URLs, or full result content.
Keep the query contract stable so downstream scraping logic stays predictable.

Docs (Source of Truth)

Read the source-of-truth page for your project language before writing integration code:

Node / TypeScript: docs.firecrawl.dev/agent-source-of-truth/node
Python: docs.firecrawl.dev/agent-source-of-truth/python
Rust: docs.firecrawl.dev/agent-source-of-truth/rust
Java: docs.firecrawl.dev/agent-source-of-truth/java
Elixir: docs.firecrawl.dev/agent-source-of-truth/elixir
cURL / REST: docs.firecrawl.dev/agent-source-of-truth/curl

Files

ATTRIBUTION.mdAdded by AutoGineer923 B
LICENSELicence file added by AutoGineer735 B
SKILL.md4.2 KiB

SKILL.md