Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

firecrawl-build-search — Claude Code skill: what it does, install

A skill that shows an agent how to wire Firecrawl search into a product, so a query finds candidate pages before anything gets read.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add firecrawl/skills --skill firecrawl-build-search -a claude-code
Open on GitHub

What firecrawl-build-search does

The skill covers putting Firecrawl /search into product code and into agent workflows. It fits features that begin with a query rather than a URL, where the app has to find candidate pages first and pick from them.

Search handles discovery and ranking here; pulling page content is a separate step. When cost or latency matters, the advice inside is to hydrate a shortlist selectively instead of every result at once. Decide up front whether the product needs snippets, bare URLs, or full pages, because that choice sets the shape of the call.

You need FIRECRAWL_API_KEY, and self-hosted deployments also set FIRECRAWL_API_URL. The skill then sorts work that looks similar but is not: a known URL belongs to firecrawl-build-scrape, pages that need clicks or form fills to firecrawl-build-interact, published papers to firecrawl-research-index. On that last one it is blunt: categories: ["research"] only narrows an ordinary web search toward research sites such as PubMed, bioRxiv, medRxiv and arXiv, returning page results with no abstract search and no full-text passages.

What it helps with

  • Turn a user question into an answer that cites sources
  • Discover companies or competitors from a topic string
  • Build a shortlist of pages before deeper extraction
  • Feed fresh web results to an agent that starts without a URL
  • Produce query-to-URL pipelines for later /scrape calls

Example prompts for the agent

  • Wire Firecrawl `/search` into the answer endpoint so replies come back with cited sources.
  • Build the query-to-URL pipeline first, we will scrape the shortlist after that.
  • Add competitor discovery by topic — start from a query, not a domain.

How to install firecrawl-build-search

1Skills CLI (Vercel)

npx skills add firecrawl/skills --skill firecrawl-build-search -a claude-code

2Manually: put the files in place

~/.claude/skills/firecrawl-build-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/firecrawl-build-search/

From the same set4

The whole set →
firecrawl-build-scrape firecrawl This skill guides integration of Firecrawl /scrape into product code for single-page extraction. It applies when an app has a known URL and needs markdown, HTML, or metadata. Claude Code CX Codex Cursor +1 61,600installs firecrawl-build-interact firecrawl A coding-agent skill that gets Firecrawl /interact into product code when a page has to be clicked, filled in or paged through before you can read it. Claude Code CX Codex Cursor +1 61,200installs firecrawl-build-onboarding firecrawl Skill fetches Firecrawl credentials and sets up the SDK in your project via built-in browser authentication. Use when your app needs FIRECRAWL_API_KEY or you're adding Firecrawl to .env. Claude Code CX Codex Cursor +1 61,200installs

Similar

omc-doctor Yeachan-Heo A skill that audits an oh-my-claudecode install: compares the plugin version against npm and hunts stale hooks in your settings files. Useful when the plugin looks installed but nothing changes. Claude Code CX Codex Cursor +1 832installs handoff thedotmack Generates a structured HANDOFF.md with goals, failed attempts, and next steps. Use it when context degrades or when starting a fresh session. Claude Code CX Codex Cursor +1 344installs obsidian-canvas-creator axtonliu Turns text into a JSON Canvas file that Obsidian opens as an interactive board. Choose a radial mind map or a freeform layout with grouped zones. Claude Code CX Codex Cursor +1 2,000installs system-info agno A skill with two scripts that tell the agent which host it runs on and what sits in a folder. Useful before you trust any path it prints. Claude Code CX Codex Cursor +1 302installs skill-creator tldraw A guide the agent follows while building a skill: what belongs in SKILL.md, what goes into scripts/, references/ and assets/, and how to keep the whole thing short. Claude Code CX Codex Cursor +1 431installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs

Questions about firecrawl-build-search

How do I install firecrawl-build-search in Claude Code?

Run npx skills add firecrawl/skills --skill firecrawl-build-search -a claude-code. The skill lands at ~/.claude/skills/firecrawl-build-search/SKILL.md.

What does firecrawl-build-search do?

It documents how to call Firecrawl /search from product code, keeping discovery separate from content extraction. It also tells you when a neighbouring skill is the right surface instead.

What does the skill need to work?

A FIRECRAWL_API_KEY, which is required for hosted Firecrawl requests. Point FIRECRAWL_API_URL at your own base URL if you run a self-hosted instance.

Source text

SKILL.md · ISC 
---
name: firecrawl-build-search
description: 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.
license: ISC
metadata:
  author: firecrawl
  version: "0.1.0"
  homepage: https://www.firecrawl.dev
  source: https://github.com/firecrawl/skills
inputs:
  - name: FIRECRAWL_API_KEY
    description: Firecrawl API key for hosted Firecrawl requests.
    required: true
  - name: FIRECRAWL_API_URL
    description: Optional base URL for self-hosted Firecrawl deployments.
    required: false
---

# 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](../firecrawl-build-scrape/SKILL.md).
- If the result page then requires clicks or form interaction, escalate to [firecrawl-build-interact](../firecrawl-build-interact/SKILL.md).
- 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](../firecrawl-research-index/SKILL.md). 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](../firecrawl-developer-index/SKILL.md). 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](https://docs.firecrawl.dev/agent-source-of-truth/node)
- **Python**: [docs.firecrawl.dev/agent-source-of-truth/python](https://docs.firecrawl.dev/agent-source-of-truth/python)
- **Rust**: [docs.firecrawl.dev/agent-source-of-truth/rust](https://docs.firecrawl.dev/agent-source-of-truth/rust)
- **Java**: [docs.firecrawl.dev/agent-source-of-truth/java](https://docs.firecrawl.dev/agent-source-of-truth/java)
- **Elixir**: [docs.firecrawl.dev/agent-source-of-truth/elixir](https://docs.firecrawl.dev/agent-source-of-truth/elixir)
- **cURL / REST**: [docs.firecrawl.dev/agent-source-of-truth/curl](https://docs.firecrawl.dev/agent-source-of-truth/curl)

## See Also

- [firecrawl-build](../firecrawl-build/SKILL.md)
- [firecrawl-build-scrape](../firecrawl-build-scrape/SKILL.md)
- [firecrawl-build-interact](../firecrawl-build-interact/SKILL.md)
- [firecrawl-research-index](../firecrawl-research-index/SKILL.md)
- [firecrawl-developer-index](../firecrawl-developer-index/SKILL.md)

© firecrawl · ISC · firecrawl/skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor