firecrawl-build-search

Turns a search query into a shortlist of ranked web pages, for product features that start from a question instead of a known URL.

WHEN TO USE

SCOPE

USE FOR

Generate an answer with cited sources by discovering pages before reading them.
Discover competitor or company pages on a given topic before extracting details.
Turn a user's question into a shortlist of web pages worth reading further.
Build a query-to-URL pipeline that feeds a later page-scraping step.

NOT FOR

Don't use this once you already have the URL; go straight to firecrawl-build-scrape instead.
Don't use this for published research papers, biomedical, clinical, or arXiv literature; use the research paper index instead.
Don't use this to answer developer questions from issues, PRs, READMEs, or docs; use the developer index instead.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (8)

Firecrawl Build Search

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

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add firecrawl/skills --skill "firecrawl-build-search" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

What's inside

Files included with this skill.

View on GitHub

Firecrawl Build Search

Use This When

Default Recommendations

Common Product Patterns

Escalation Rules

Implementation Notes

Docs (Source of Truth)

See Also

Account or credentials required

What's inside

firecrawl-build-search

Firecrawl Build Search

Use This When

Default Recommendations

Common Product Patterns

Escalation Rules

Implementation Notes

Docs (Source of Truth)

See Also

Account or credentials required

What's inside

More skills

MCP keyword matches