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

firecrawl-build-interact — Claude Code skill: /interact

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.

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

What firecrawl-build-interact does

The skill kicks in once /scrape runs out of road: content that shows up only after a click, some typing or a navigation step. It hands the agent the rules for wiring Firecrawl /interact into product code, and the first thing it asks for is the source-of-truth page for your language — Node/TypeScript, Python, Rust, Java, Elixir or cURL/REST — read before any integration code gets written.

The pattern is escalation. Reach for /scrape first and move to /interact only for the smallest browser flow that unlocks the data: a search form, faceted filters, a paginated list, a login-gated dashboard. Persistent profiles earn their keep only when authenticated state has to survive between sessions. If the real job turns out to be open-ended browser automation, the skill says to weigh a browser sandbox instead of stretching this one.

FIRECRAWL_API_KEY is required. FIRECRAWL_API_URL matters for self-hosted Firecrawl deployments. When a page can be read directly, the skill points you back to firecrawl-build-scrape, so a project mixing static and dynamic pages should carry both.

What it helps with

  • fill a search form and apply filters before extraction
  • walk a paginated catalog and collect every page
  • log into a gated dashboard and pull the table
  • click a tab that reveals the content you need
  • decide where /scrape stops and /interact starts

Example prompts for the agent

  • Wire Firecrawl `/interact` into the search page collector — we need to fill the query form and go through every result page.
  • Our `/scrape` call comes back empty because the table renders after a click. Rewrite the collector around `/interact`.
  • Check whether this flow needs a persistent profile at all: the login only matters inside a single run.

How to install firecrawl-build-interact

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

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-search firecrawl A skill that shows an agent how to wire Firecrawl search into a product, so a query finds candidate pages before anything gets read. Claude Code CX Codex Cursor +1 61,500installs 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

tavily-best-practices tavily-ai This skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system. Claude Code CX Codex Cursor +1 20,600installs control-ui cursor Inspects and tests local web, IDE, or Electron interfaces via browser automation and CDP. Captures screenshots, traces, and verifies UI changes without extra dependencies. Claude Code CX Codex Cursor +1 2,400installs external-context Yeachan-Heo This skill breaks down your query into multiple search facets and spawns parallel document-specialist agents to search documentation and web simultaneously. Useful for gathering context on a topic or comparing approaches. Claude Code CX Codex Cursor +1 784installs tavily-extract tavily-ai Extracts clean text or Markdown from specified pages with Tavily CLI. Use it for JavaScript-rendered content or query-focused page chunks. Claude Code CX Codex Cursor +1 18,000installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. Claude Code CX Codex Cursor +1 1,200,000installs webapp-testing official anthropics This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs. Claude Code Claude.ai 186,758installs computer-use stablyai This skill drives a visible app window through orca computer: accessibility tree, clicks, typing, screenshots. Reach for it when the job sits behind a GUI. Claude Code CX Codex Cursor +1 239,000installs browser-use browser-use Hands the agent a real Chrome over CDP: clicks, typing, screenshots, and pages that need JS or your logged-in session. Claude Code CX Codex Cursor +1 98,100installs

Questions about firecrawl-build-interact

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

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

What does firecrawl-build-interact do?

It guides the agent through integrating Firecrawl /interact into product code for pages that need clicks, form fills, pagination or auth-aware flows. It also sets the order of work: /scrape first, escalate only when the page must be manipulated.

How is it different from firecrawl-build-scrape?

firecrawl-build-scrape covers pages you can read as they are. This skill takes over when the page has to be driven. If the data is readable directly, it sends you back to the scrape skill.

Source text

SKILL.md · ISC 
---
name: firecrawl-build-interact
description: Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.
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 Interact

Use this when `/scrape` is not enough because the feature needs to act on the page.

## Use This When

- content appears only after clicks, typing, or navigation
- the feature needs forms, pagination, filters, or multi-step flows
- the product must stay in the same browser context after scraping

## Default Recommendations

- Start with `/scrape`, then escalate to `/interact`.
- Keep `/interact` scoped to the smallest browser workflow that unlocks the data.
- Use persistent profiles only when the feature truly needs authenticated state across sessions.

## Common Product Patterns

- search forms and faceted filters
- paginated result sets
- login-gated dashboards or tools
- flows where the page must be explored before extraction is complete

## Implementation Notes

- `/interact` is the right tool when the page must be manipulated, not just read.
- Keep prompts or action code specific to the product flow.
- If the use case is fully open-ended browser automation, evaluate whether a browser sandbox is a better product fit.

## Escalation Rules

- If the page can be read directly, stay on [firecrawl-build-scrape](../firecrawl-build-scrape/SKILL.md).

## 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-search](../firecrawl-build-search/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