firecrawl-interact
byfirecrawl· 131 skills
Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language prompts or code. Use when the user needs to interact with a webpage beyond simple scraping: logging into a site, submitting forms, clicking through pagination, handling infinite scroll, navigating multi-step checkout or wizard flows, or when a regular scrape failed because content is behind JavaScript interaction. Also useful for authenticated scraping via profiles. Triggers on "interact", "click", "fill out the form", "log in to", "sign in", "submit", "paginated", "next page", "infinite scroll", "interact with the page", "navigate to", "open a session", or "scrape failed".
How to install firecrawl-interact?
firecrawl/cli/firecrawl-interact
$npx -y skills add firecrawl/cli --skill firecrawl-interactInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/firecrawl/cli" --skill "firecrawl/cli/firecrawl-interact"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/firecrawl/cli" that are relevant to the current task. Run `npx skills add "https://github.com/firecrawl/cli"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # firecrawl interact |
| 2 | |
| 3 | Interact with scraped pages in a live browser session. Scrape a page first, then use natural language prompts or code to click, fill forms, navigate, and extract data. |
| 4 | |
| 5 | ## When to use |
| 6 | |
| 7 | - Content requires interaction: clicks, form fills, pagination, login |
| 8 | - `scrape` failed because content is behind JavaScript interaction |
| 9 | - You need to navigate a multi-step flow |
| 10 | - Last resort in the [workflow escalation pattern](firecrawl-cli): search → scrape → map → crawl → **interact** |
| 11 | - **Never use interact for web searches** — use `search` instead |
| 12 | |
| 13 | ## Quick start |
| 14 | |
| 15 | ```bash |
| 16 | # 1. Scrape a page (scrape ID is saved automatically) |
| 17 | firecrawl scrape "<url>" |
| 18 | |
| 19 | # 2. Interact with the page using natural language |
| 20 | firecrawl interact --prompt "Click the login button" |
| 21 | firecrawl interact --prompt "Fill in the email field with test@example.com" |
| 22 | firecrawl interact --prompt "Extract the pricing table" |
| 23 | |
| 24 | # 3. Or use code for precise control |
| 25 | firecrawl interact --code "agent-browser click @e5" --language bash |
| 26 | firecrawl interact --code "agent-browser snapshot -i" --language bash |
| 27 | |
| 28 | # 4. Stop the session when done |
| 29 | firecrawl interact stop |
| 30 | ``` |
| 31 | |
| 32 | ## Options |
| 33 | |
| 34 | | Option | Description | |
| 35 | | --------------------- | ------------------------------------------------- | |
| 36 | | `--prompt <text>` | Natural language instruction (use this OR --code) | |
| 37 | | `--code <code>` | Code to execute in the browser session | |
| 38 | | `--language <lang>` | Language for code: bash, python, node | |
| 39 | | `--timeout <seconds>` | Execution timeout (default: 30, max: 300) | |
| 40 | | `--scrape-id <id>` | Target a specific scrape (default: last scrape) | |
| 41 | | `-o, --output <path>` | Output file path | |
| 42 | |
| 43 | ## Profiles |
| 44 | |
| 45 | Use `--profile` on the scrape to persist browser state (cookies, localStorage) across scrapes: |
| 46 | |
| 47 | ```bash |
| 48 | # Session 1: Login and save state |
| 49 | firecrawl scrape "https://app.example.com/login" --profile my-app |
| 50 | firecrawl interact --prompt "Fill in email with user@example.com and click login" |
| 51 | |
| 52 | # Session 2: Come back authenticated |
| 53 | firecrawl scrape "https://app.example.com/dashboard" --profile my-app |
| 54 | firecrawl interact --prompt "Extract the dashboard data" |
| 55 | ``` |
| 56 | |
| 57 | Read-only reconnect (no writes to profile state): |
| 58 | |
| 59 | ```bash |
| 60 | firecrawl scrape "https://app.example.com" --profile my-app --no-save-changes |
| 61 | ``` |
| 62 | |
| 63 | ## Tips |
| 64 | |
| 65 | - Always scrape first — `interact` requires a scrape ID from a previous `firecrawl scrape` call |
| 66 | - The scrape ID is saved automatically, so you don't need `--scrape-id` for subsequent interact calls |
| 67 | - Use `firecrawl interact stop` to free resources when done |
| 68 | - For parallel work, scrape multiple pages and interact with each using `--scrape-id` |
| 69 | |
| 70 | ## See also |
| 71 | |
| 72 | - [firecrawl-scrape](../firecrawl-scrape/SKILL.md) — try scrape first, escalate to interact only when needed |
| 73 | - [firecrawl-search](../firecrawl-search/SKILL.md) — for web searches (never use interact for searching) |
| 74 | - [firecrawl-agent](../firecrawl-agent/SKILL.md) — AI-powered extraction (less manual control) |
Related
6 picksType
- agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…Jul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI.Jul 2026
- browser-actBrowser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first.Jul 2026
- playwright-cliAutomate browser interactions, test web pages and work with Playwright tests.Jul 2026
- browser-useDirect browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.Jul 2026
- browser-act-skill-forgeForges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later.Jul 2026
