browser-act

Extracts paginated product lists from e-commerce category or search pages, including details like URL, name, and price. Supports URL, keyword, and site-scoped searches with filters such as price range, brand, and minimum rating on platforms like Amazon, eBay, and Walmart.

A browser automation CLI for AI agents that breaks through anti-bot walls and allows human handoff across platforms when stuck. It supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. It's useful for searching products, finding best-sellers, tracking prices, comparing brands, and extracting data for market research.

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. It should be applied when users need to get reviews, analyze customer feedback, or track sentiment for Amazon products.

This skill extracts structured Amazon product details, including title, price, ratings, reviews count, and availability, using a specific ASIN.

This skill helps users automatically extract channel-level and video detail data from a specific YouTube channel via BrowserAct API. It should be applied when users need to extract channel video data, get latest or popular videos, track competitor content, or extract video metrics like views, likes, comments, and subscribers.

This skill helps users extract GitHub repository project details and contributor contact information using keywords, stars, and update dates. The agent should proactively apply this skill when users express needs like searching for GitHub projects by keywords, finding top open-source contributors in specific domains, extracting developer contacts from GitHub repositories, or discovering trending repositories.

This skill extracts Google Maps reviews using the Google Maps Reviews API. It's applied when users need reviews for local businesses, customer feedback, competitor sentiment analysis, or reviews for store chains.

This skill helps users discover key contacts across industries, roles, and social platforms via the BrowserAct API. It's useful for finding public profiles, decision-makers, and contact details for lead generation.

This skill automatically extracts structured news data from Google News via BrowserAct API. The agent should proactively apply it when users need to search for news on a specific topic, track industry trends, monitor public relations or sentiment, collect competitor updates, get latest reports, or monitor brand exposure.

AI-powered web research assistant that leverages the BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.

Searches the Meta Ad Library by keyword or Facebook page ID, extracting ad details such as creatives, copy, CTA, publisher platforms, spend, impressions, reach estimates, and page transparency information.

Scrapes posts from any public Facebook Page timeline, providing structured data including post text, author info, engagement metrics (likes, comments, shares), detailed reaction breakdowns, hashtags, external links, and media type. It is ideal for extracting Facebook post data and collecting engagement statistics.

Fetches comments from an Instagram post, including text, username, timestamp, like count, and reply count. Use when a user requests to scrape, get, list, or extract comments from an Instagram post.

Scrapes posts from an Instagram user's profile feed, including captions, media URLs, like/comment counts, timestamps, and location tags.

A browser automation CLI built for AI agents. It breaks through anti-bot walls, allows hand-off to humans across platforms when stuck, and supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

This skill automatically extracts structured article details and full content from Zhihu via the BrowserAct API. Agents should proactively apply it for searching articles, tracking industry trends, monitoring public relations or sentiment, and collecting competitor updates or latest reports on Zhihu.

This tool scrapes full metadata for a single TikTok video given its URL, providing details like author profile, engagement stats, music, and hashtags. Use it to extract comprehensive information about any specific TikTok video.

Browser automation CLI built for AI agents. It breaks through anti-bot walls, hands off to humans across platforms when stuck, and supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

A browser automation CLI for AI agents, designed to bypass anti-bot measures and allow human handoff when stuck. It supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

This skill helps users extract YouTube video transcripts and perform deep competitive analysis on the content. It's useful for analyzing content strategy, marketing insights, and competitor value propositions.

This skill creates reusable Skill packages from website exploration via browser-act, avoiding re-exploration. It's used for building reusable skills, understanding site APIs, reproducing scrapers, or performing bulk data extraction.

Extracts complete product information from any e-commerce product page, including name, price, currency, brand, images, description, identifiers (SKU/ASIN/EAN/UPC/GTIN/MPN), stock availability, rating, review count, variants, and seller. Compatible with Shopify, Amazon, WooCommerce, eBay, Walmart, Etsy, AliExpress, Alibaba, Target, Best Buy, Rakuten, Magento, BigCommerce, PrestaShop, and any public e-commerce platform.

This skill automatically extracts product data from Amazon search results. The Agent proactively applies it for tasks such as searching products by keywords, finding best-selling items, monitoring prices, and collecting ratings for market research.

Browser automation CLI built for AI agents. It breaks through anti-bot walls, allows handover to humans across platforms when stuck, and supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

This skill helps users analyze Amazon competitor listings by ASIN, producing structured competitive intelligence and strategic opportunity points for their go-to-market. It should be applied to understand what top-ranked products do right in content or visuals, and to find market gaps and unmet buyer needs.

A browser automation CLI built for AI agents, designed to break through anti-bot walls and hand off to humans across platforms when stuck. It supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

Extracts YouTube video transcripts and reformats content into summaries, chapter outlines, Twitter/X threads, blog posts, or quotes. Use when the user shares a YouTube URL and asks to summarize or extract content.

A browser automation CLI designed for AI agents, it breaks through anti-bot walls and allows hand-off to humans across platforms when stuck. It supports parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

Extracts seller profile data like name, rating, review count, and return policy from marketplace pages such as Amazon and eBay, or any e-commerce site with seller profiles.

Extracts customer reviews from e-commerce product pages, including reviewer name, star rating, date, title, body, verified purchase status, and helpful votes. It supports Amazon, WooCommerce, Shopify, and other sites with standard review markup, including pagination.

This skill helps users automatically scrape business data from Google Maps using the BrowserAct Google Maps API. The agent should proactively trigger this skill for needs such as finding restaurants, extracting contact info, researching competitors, collecting addresses, generating lead lists, and monitoring business ratings.

This skill helps users automatically extract official website and social media profiles. The agent should apply it when users need to find a company's website or social media contacts, like YouTube, LinkedIn, X, and Facebook profiles, or extract links from a URL.

This skill helps users automatically extract business data from Google Maps search results. The Agent should proactively apply it when users search for businesses like coffee shops or clinics, track competitors, or extract business leads.

Searches LinkedIn job listings and extracts full job details. Supports filtering by work type, contract type, experience level, date posted, and company, returning comprehensive job information including description, salary, and direct URLs.

This skill helps users automatically find social media profiles across platforms like Facebook, Twitter, Instagram, LinkedIn, etc., using the BrowserAct API.

A browser automation CLI designed for AI agents, it bypasses anti-bot defenses and allows human handoff across platforms when stuck. It features parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

A browser automation CLI for AI agents, designed to bypass anti-bot walls and enable human hand-off when stuck. It features parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

Extracts Google Search results page (SERP) data including organic results, paid ads, related searches, People Also Ask questions, AI Overview text, and total result count from google.com.

A browser automation CLI built for AI agents, designed to break through anti-bot walls and allow handoff to humans across platforms when stuck. It features parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.

Scrapes posts from a Facebook group given a group URL, sort order, and desired count, returning structured post metadata like ID, permalink, author, timestamp, body, media, and various counts. Use to extract or collect Facebook group content and data.

Scrapes Instagram posts by hashtag, returning media items with captions, like/comment counts, media URLs and user info from the hashtag explore feed.

Scrapes posts from public Facebook Pages or personal profiles, providing structured data such as post text, author info, engagement metrics, full reaction breakdowns, hashtags, external links, media assets with URLs, and page ad library status.

Scrapes Instagram posts tagged at a specific location or place, returning media items with captions, like/comment counts, media URLs and user info.

Fetches Instagram user profile metadata including bio, follower count, following count, post count, and verification status.

This skill scrapes TikTok videos by keyword, providing a paginated list with full metadata such as author, engagement stats, music, and video details. It's ideal for extracting TikTok search data or collecting search results based on specific keywords.

Scrapes tweets from X (Twitter) by search query, user handle, or direct URL, returning full tweet data including text, author info, engagement metrics, media, and hashtags.