Firecrawl Interact
技能 已验证 活跃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".
To enable users to perform complex interactions with web pages that go beyond simple scraping, by controlling a live browser session for tasks like logging in, form submission, and navigating dynamic content.
功能
- Control live browser sessions
- Fill forms and click buttons via prompts/code
- Navigate multi-step web flows
- Extract data from interacted pages
- Persist browser state with profiles
使用场景
- Logging into websites and authenticated scraping
- Submitting forms and completing wizard-like flows
- Handling pagination and infinite scroll
- Interacting with JavaScript-heavy content
- Recovering when standard scraping fails
非目标
- Performing general web searches (use 'search' command)
- Crawling entire websites (use 'crawl' command)
- Performing bulk site downloads (use 'experimental download')
- Simple static content scraping (use 'scrape' command)
工作流
- Scrape a target URL using `firecrawl scrape`.
- Initiate interaction with the scraped page using `firecrawl interact`.
- Provide natural language prompts or executable code to control browser actions.
- Extract desired data from the interacted page.
- Optionally use profiles to persist browser state across sessions.
- Stop the interaction session using `firecrawl interact stop` when done.
实践
- Browser automation
- Web interaction
- Data extraction
先决条件
- Node.js installed
- Firecrawl CLI installed (`npm install -g firecrawl-cli`)
- A previous 'firecrawl scrape' command must have been run
安装
请先添加 Marketplace
/plugin marketplace add firecrawl/cli/plugin install cli@firecrawl质量评分
已验证类似扩展
Agent Browser
100AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。
Chatgpt Search
100Search ChatGPT and extract the full response + hydration JSON that powers the UI. Attaches to a running Chrome instance (port 9222 by default), opens ChatGPT, submits a query, waits for the streamed response, and returns structured data: messages, product cards, hydration JSON, and API calls. Use when asked to "search chatgpt", "ask chatgpt", "chatgpt search", "get chatgpt response", or "scrape chatgpt".
AutoBrowse
100Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
Github
100Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.
Cli Creator
100Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
Browser Extract
99Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model