Skill List
Extracts 50+ fields of wholesale product data from 1688.com offer pages via DOM scripts and network capture, covering pricing tiers, SKU variants, seller scores, promotions, and DSR. Delivers structured JSON for B2B sourcing, resale analysis, and supplier vetting.
Fetches full Airbnb listing details via internal GraphQL API using a numeric ID. Method: run a Python script that calls the public endpoint through browser fetch. Output: title, amenities, photos, rules, ratings, location — for property research and data enrichment without login.
Extracts Airbnb accommodation search results from a destination query via SSR-embedded data, returning listing ID, URL, name, coordinates, rating, price, photos, and badge info. Uses a Python script to parse niobeClientData and supports cursor-based pagination. Value: enables bulk collection of Airbnb rental listings for market research and price monitoring.
Automates submitting questions to Amazon Alexa/Rufus shopping assistant and collecting responses as JSON. Uses browser-act with Python scripts to inject questions and extract answers, supports optional keyword context and batch loops. Value: scaled collection of Amazon AI recommendations for market research.
Extracts structured Amazon product details via ASIN using BrowserAct API and a Python script. Method: configure API key, run script with ASIN, monitor logs, auto-retry on failure. Outputs title, price, ratings, brand, specs, URL — enabling catalog enrichment, price tracking, and market research without manual scraping.
Extracts ranked product cards from any Amazon Best Sellers (zgbs / gp/bestsellers) page across all regional TLDs via browser-act and a Python DOM script. Returns per-item rank, ASIN, title, price, stars, review count plus category and pagination metadata. Enables competitive intelligence, niche discovery, and rank-change tracking by walking paginated top-100 charts.
Scrapes Amazon product data from ASINs via browseract.com automation API and performs surgical competitive analysis. Compares specs, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities. Outputs CSV/Markdown/JSON reports for market strategy.
Analyzes a competitor Amazon listing by ASIN via a two-phase workflow: script-based data extraction then structured diagnosis of content, keyword, visual strategies and review mining. Outputs competitive intelligence and strategic opportunity points for the user's go-to-market. Value: evidence-based market gap discovery without hallucinations or CAPTCHA issues.
Extracts structured Amazon product listings (titles, ASINs, prices, ratings, specs) via BrowserAct API and a Python script. Method: configure keyword/brand/language params and run one CLI command. Value: hallucination-free, captcha-free market research, price tracking, and catalog enrichment from Amazon search results.
Scrapes full product data from any open Amazon detail URL across all regional TLDs via browser-act and a Python DOM script. Extracts 100+ fields including price, rating breakdown, variants, BSR, seller, and sample reviews. Enables bulk ASIN enrichment, competitive research, and price/stock monitoring with structured JSON output.
This skill automates extraction of structured product data from Amazon search results via BrowserAct API. It takes keywords, brand filter, max count, and UI language to run a Python script that returns titles, prices, ratings, reviews, sales, delivery, and best-seller flags. Value: fast, low-cost, captcha-free market research and competitive intelligence without AI hallucinations.
Extracts Amazon product reviews via BrowserAct Reviews API using a product ASIN. Agent runs a Python script with the ASIN to fetch structured reviewer data (name, rating, title, text, country, variant, verified) without login or captcha. Delivers clean review datasets for competitor analysis, sentiment monitoring, and market research at low cost and high speed.
Extracts structured product listings from any Amazon search, keyword, or category page across all regional TLDs via browser-act and Python DOM scripts. Returns per-item cards (ASIN, title, price, stars, badges) plus pagination state. Enables price monitoring, competitor tracking, and ASIN list building at scale.
Forges reusable Agent Skill packages (SKILL.md + Python scripts) from website exploration via browser-act. Method: detect tool, analyze requirements, explore API/DOM paths, generate and verify scripts, deliver tested Skill. Value: explore once, reuse forever — reliable scaled extraction without re-exploration cost.
Automatically extracts official website and social media profiles from a company name or website URL via BrowserAct API. Uses two templates: Google search for company names, site scrape for URLs. Outputs structured JSON of social links. Value: stable, captcha-free, cost-effective lead-gen and outreach data.
Searches Douyin (douyin.com) by keyword via browser-act and a Python script that calls the internal search API. Returns structured video data (author, stats, cover, hashtags, download URL) with date-range and sort filters. Enables KOL research, content mining, and competitive analysis on China's top short-video platform.
Extracts full item detail from any open eBay item URL across all regional TLDs, returning 25+ field JSON (price, seller, condition, brand/MPN/UPC, images, sold/availability, itemSpecifics). Method: validate URL, navigate via browser-act, run Python DOM parser. Value: enables per-item enrichment, price/stock monitoring, competitive research, brand catalog audits.
Extracts product listings from any eBay search or category page URL, returning per-item cards with title, price, seller, image and pagination state across all regional TLDs. Uses browser-act and a Python DOM parser to loop pages via URL pagination. Enables bulk eBay item collection, price comparison, and competitive listing monitoring.
eBay sold-listings scraper for 8 marketplaces. Uses Python URL builder and DOM extractor scripts via browser-act to fetch paginated real-sale records with price, date, condition, seller. Value: pricing intelligence, resale valuation, arbitrage.
Extracts structured product lists from any e-commerce category, search, or keyword page with filters (price/brand/rating/in-stock/sort) and multi-page pagination. Uses browser-act to read public pages and Python scripts to scrape per-item URL, name, price, image, rating. Delivers paginated JSON arrays for catalog building, price monitoring, and competitor research across Amazon, eBay, Walmart, Shopify, and more.
Extracts complete product data from any e-commerce product page via URL, keyword, or identifier using multi-layer extraction (JSON-LD, DOM, OG, microdata). Returns name, price, brand, images, IDs, stock, rating, variants, seller. Value: universal cross-platform product research and monitoring.
Extracts customer reviews from any e-commerce product/reviews page (Amazon, WooCommerce, Shopify, generic) via multi-strategy DOM parsing. Returns reviewer, rating, date, title, body, verified status, helpful votes. Supports pagination for bulk collection, enabling sentiment analysis and competitor feedback mining.
Extracts seller/merchant profile data (name, rating, review count, positive feedback, joined date, return policy) from marketplace seller pages like Amazon and eBay via browser automation and a Python DOM parser. Delivers structured JSON seller intelligence for vendor analysis and due diligence.
Scrapes Etsy public category pages by URL + optional page number, using a Python DOM-extraction script via browser-act stealth session. Returns paginated listings with id, price, rating, shop, badges. Value: bulk category export, trend and competitor research on Etsy niches.
Etsy keyword search scraper that collects paginated product listings from etsy.com search results via a stealth browser session and a Python extraction script. It returns core fields per item (price, rating, shop, badges) for bulk export, competitor research, and trend analysis on handmade or craft niches.
Etsy product detail scraper that takes a listing URL and extracts full data via browser-act and a Python DOM script. It returns price, variations, images, shop, rating, favorites, and description. Value: enables bulk listing enrichment, competitor monitoring, and SEO mining with structured JSON output.
Scrapes an Etsy shop's storefront by URL and returns paginated product listings (listingId, title, price, rating, etc.). Uses browser-act with anti-bot warm-up and Python extraction scripts for serial pagination. Value: bulk competitor shop tracking, supplier catalog collection, and price monitoring.
Searches Meta Ad Library by keyword or Facebook page ID to extract ad details (creatives, copy, CTA, platforms, spend, impressions, page info) via a Python script wrapped as CLI. Value: enables competitor ads analysis and brand monitoring with structured, paginated ad data from Facebook/Instagram/WhatsApp.
Scrapes posts from a Facebook group via group URL, sort order, and count using browser-act and a Python script. Returns structured metadata (post_id, author, timestamp, body, media, reactions, comments, shares). Value: bulk-export group content for monitoring, research, and competitive social listening.
Scrapes posts from any public Facebook Page timeline via browser-act and Python scripts, returning structured data: post text, author, engagement metrics, reaction breakdowns, hashtags/links, media type. Supports date filtering and cursor pagination for bulk collection. Value: enables social media analytics and competitor monitoring with minimal manual effort.
Scrapes posts from any public Facebook Page or personal Profile timeline via browser-act and Python scripts. It resolves page URL to ID, fetches posts with full fields (text, engagement, reaction breakdown, media, ad status), and supports date filter and cursor pagination. Output is structured JSON for social analytics and bulk export.
Extracts GitHub repo details and contributor contacts via BrowserAct API using keywords, stars, and update date. Agent runs a Python script with set params to get repo metrics and contributor profiles (site, Twitter). Value: fast, no-captcha lead gen for recruiting, outreach, and OSS discovery.
Extracts full detail from a single Goofish (闲鱼) second-hand item page via browser automation. Method: navigate to item URL, capture detail API, run Python script to parse DOM. Outputs title, price, seller info, description, images, tags, want-count. Value: enables purchase verification, seller research, and bulk item enrichment.
Scrapes Goofish (闲鱼) second-hand search results by keyword with optional sort/price/date filters. Uses browser navigation plus Python scripts to extract 30 item cards per page (id, title, price, image, location, want-count). Enables price research, competitor monitoring, and bulk used-goods data collection on China's largest second-hand marketplace.
Scrapes Google Maps business data via BrowserAct API using a Python CLI script. Provide keywords, language, and country to extract names, categories, addresses, phones, websites, ratings, and status. Delivers structured lead lists and market insights without captcha or IP issues, lowering data cost.
Extracts business contacts from Google Maps search and place pages, then crawls each website for emails, phones, and social profiles (FB, IG, X, LinkedIn, etc.). Uses Python scripts via browser-act to search, get details, and scrape contacts. Output is a merged lead dataset for local business outreach and competitor research.
Extracts Google Maps reviews via BrowserAct API using a Python script. Agent configures keywords, language, country, then runs the script to get structured review data (author, rating, text, date, likes). Avoids captcha/IP issues, delivers clean data for reputation monitoring, competitor analysis, and market research.
Automatically extracts structured business data from Google Maps search results via the BrowserAct API. By providing keywords, language, and country, it returns clean business lists (name, address, rating, price, etc.) without captcha or IP issues. Value: fast, low-cost local business lead gen, competitor mapping, and CRM-ready market research.
Extracts structured Google News data via BrowserAct API using a Python script. Agent configures keywords, time range, and item count, then runs the script to get headlines, sources, links, and times. Value: hallucination-free, captcha-free news monitoring for PR, trends, and competitor intelligence.
Extracts Google Search SERP data (organic results, paid ads, related searches, People Also Ask, AI Overview, total count) from google.com via browser automation. Uses a Python script to parse rendered HTML after URL-parameter navigation. Delivers structured JSON for SEO ranking checks, keyword research, and competitor search monitoring.
Searches Google to discover social media profiles for a person, brand, or username across X, Instagram, LinkedIn, TikTok, and more. Uses browser-act navigation plus a Python extraction script to return platform, URL, username, bio, and follower count. Value: maps digital footprint and supports influencer or lead research.
Scrapes Indeed.com job listings by keyword, location, and country via browser automation. Uses Python scripts to extract search results and full job details (title, company, salary, rating, description, benefits, apply links). Enables job market analysis, salary benchmarking, and recruitment data collection at scale.
Discovers key industry contacts across roles and social platforms via BrowserAct API. Agent configures industry, site, job title and limit, then runs a Python script to extract structured profiles (URL, name, bio, company). Value: accurate, CAPTCHA-free, low-cost lead gen and talent sourcing.
Scrapes Instagram posts by hashtag from the explore feed via browser-act and a Python GraphQL replay script. Returns media items with captions, like/comment counts, media URLs and user info. Enables marketers and analysts to collect trending hashtag content for social listening and competitive research.
Scrapes Instagram posts tagged at a specific location via internal locations API with cursor pagination. Method: search location name to ID, then fetch ranked/recent posts with Python scripts under logged-in session. Value: returns structured media items (captions, like/comment counts, URLs, user info) for venue marketing and local trend analysis.
Fetches comments from an Instagram post via internal comments API with cursor pagination. Provides scripts to resolve shortcode to media ID and pull comment pages. Outputs structured comment data (text, user, likes, replies) for social listening, audience analysis, and marketing research.
Fetches Instagram user profile metadata (bio, follower/following/post counts, verification status) via internal REST API using a Python script wrapper. Key method: run get-profile-meta.py with username through browser-act session. Value: quickly obtain structured account intelligence without login or manual browsing.
Scrapes an Instagram user's profile feed via internal feed API with cursor pagination. Uses Python scripts to resolve username to ID then fetch posts (caption, media URL, like/comment counts, timestamp, location). Outputs a merged structured post list for archiving, analysis, or outreach.
Searches LinkedIn job listings via the user's logged-in browser and extracts full job details with filters for work type, contract, experience, and date. Outputs structured JSON with title, company, location, description, salary, and URLs. Value: enables job market research, lead collection, and hiring analysis at scale.
Scrapes Product Hunt daily/weekly/monthly/yearly leaderboard launches with full product details, maker profiles, and website contact info via browser DOM extraction scripts. Key method: navigate leaderboard URLs and run Python extractors for list, detail, maker, website. Value: structured launch data for startup monitoring, new product discovery, and maker lead generation.
Automatically discovers social media profiles across platforms (Facebook, Twitter, Instagram, LinkedIn, etc.) for a given person or brand name via the BrowserAct API. It runs a Python script that returns a CSV of profile URLs, usernames, follower counts, and bios. Value: fast, cost-effective, hallucination-free lead gen and background research.
Searches Taobao and Tmall product listings by keyword via browser-act and a Python DOM extractor, returning paginated cards with title, price, shop, image, sales, tags. Enables bulk keyword collection, price monitoring, and competitive research on Chinese e-commerce.
Fetches full product detail from a Taobao/Tmall page by itemId via browser-act and a Python DOM extractor. Returns title, price, shop, images, SKU variants, attributes as JSON. Enables product DB building, price tracking, and comparison research at scale.
Fetches Taobao/Tmall product reviews by itemId via browser automation. Uses Python scripts to extract reviewer name, date, purchased variant, text, and photos from lazy-loaded review sections with pagination. Enables sentiment analysis and review dataset building.
A workflow skill that browses a Taobao/Tmall shop catalog by shopId and extracts paginated product listings (itemId, title, imageUrl). It uses browser-act with a Python extraction script and batch pagination. Value: enables shop inventory monitoring, competitor store analysis, and bulk itemId collection from a specific seller.
Searches Threads posts by keyword or hashtag via browser-act and extracts SSR-embedded JSON with engagement metrics. Method: navigate search URL, run Python script to parse results. Value: delivers structured post lists (text, user, likes, replies) for social listening, trend monitoring, and KOL discovery without login.
Discovers Threads user accounts by keyword and extracts profile data (username, display name, verification, bio, follower count). Uses browser-act with Python scripts to read SSR JSON and enrich via profile API. Value: quick influencer/competitor discovery on Threads without login.
Fetches public posts from a Threads user profile via SSR JSON and scroll pagination using browser-act and Python scripts. Outputs structured post data with engagement metrics and media info for creator monitoring or content research.
Scrapes TikTok videos by hashtag name via browser navigation and network capture, outputting paginated video lists with author, engagement, music and video metadata. Uses a Python script to resolve challenge ID then scrolls to paginate. Enables bulk hashtag video collection for trend research, influencer discovery and content monitoring.
Scrapes a TikTok user's profile and paginated video list via browser-act network capture of the signed item_list API. Outputs profile metadata and full video stats for influencer research, competitor analysis, and content archiving.
Scrapes TikTok search results by keyword via browser navigation and network capture of the signed `/api/search/item/full/` endpoint. Returns paginated video lists with author, stats, music, and metadata. Enables market research, competitor monitoring, and topic-based creator discovery on TikTok.
Extracts full metadata from a single TikTok video URL by parsing SSR-embedded data via a Python script, returning author profile, engagement stats, music, video meta, hashtags, mentions and slideshow images. Supports batch URL processing. Value: quick, login-free archival and verification of TikTok posts with structured data.
Looks up a company's Trustpilot profile by domain and extracts metadata (TrustScore, review counts, verification, contact, reply metrics). Method: navigate review page, parse SSR JSON via Python script. Value: fast reputation checks and bulk domain enrichment for vetting and lead generation.
A Trustpilot customer reviews scraper that takes a company domain plus optional filters (star, language, date, verified, reply, keyword, country) and extracts paginated reviews with 20+ fields each via browser-act and a Python SSR parser. It enables brand monitoring, sentiment analysis, competitor review comparison, and BI dashboard exports from public Trustpilot data.
Scrapes Walmart category/browse pages by URL + page number, extracting paginated product listings (itemId, title, brand, price, rating, seller, etc.) via a Python DOM script. Value: builds Walmart category datasets, monitors prices, and supports filtered bulk collection with resume-on-error batch orchestration.
Scrapes Walmart keyword search results via browser-act and a Python script, extracting paginated product listings with price, rating, availability, and seller info. Delivers structured JSON for bulk Walmart product data, price comparison, and search ranking monitoring.
Extracts full structured product data from a Walmart product detail page (walmart.com/ip/...) via browser automation and a Python DOM script. Method: navigate with browser-act, run extract-product-detail.py to pull JSON with price, specs, variants, fulfillment, and review summary. Value: enables catalog building, price/stock monitoring, and competitive research on Walmart with minimal manual effort.
Scrapes paginated Walmart customer reviews by product item ID via browser-act and a Python extraction script. It captures rating, text, author, verified purchase, votes, variant, seller and photo count per review. Value: enables bulk review collection, sentiment analysis, and competitor benchmarking on Walmart.
AI web research assistant using BrowserAct API to bypass restricted web access and search for info. Method: run research.py with query params to call BrowserAct, extract and validate multi-source data. Value: produces structured reports with citations, no hallucinations, global access for OpenClaw/Claude Code.
Deep-crawls any website from start URLs via BFS, stripping boilerplate to emit per-page LLM-ready text/markdown/HTML with metadata and in-scope links. Uses browser-act and Python scripts for discovery and extraction. Value: builds clean RAG corpora, vector DBs, or chatbot knowledge bases from entire sites or docs hubs.
X (Twitter) DM end-to-end automation skill that scans inbox for pending replies, reads history, and sends persona-based replies; also supports user search and outreach. Uses browser-act with Python scripts and built-in passcode unlock and rate control. Value: scales DM handling, saves manual effort, enables campaign outreach.
X keyword-comment automates searching X by keyword, reading tweets, generating persona-based contextual replies, and posting them via a browser-act session. It drives traffic and engagement through batch keyword reply campaigns on X/Twitter.
Collects every tweet in an X conversation thread from a conversation id (root tweet id), including focal tweet, replies, sub-replies via browser network capture and Python parsing scripts. Outputs normalized per-tweet JSON with author, engagement, media, and pagination cursors for thread analysis or export.
Scrapes an X (Twitter) user's profile timeline by handle with selectable mode (tweets / replies / media). Uses browser-act network capture plus Python scripts to build URLs and parse GraphQL responses. Outputs normalized per-tweet data with engagement, media, and pagination cursors for KOL research and competitor tracking.
Scrapes tweets from any X/Twitter URL (search, profile, tweet detail, list) by auto-detecting the timeline endpoint, navigating via browser with network capture, and parsing responses with Python scripts. Outputs normalized per-tweet data with engagement, media, and pagination cursors for batch KOL monitoring and research.
Scrapes X (Twitter) tweets by search query, user handle, or direct URL using browser-act and a React Fiber DOM script. Returns full structured tweet data (text, author, metrics, media, hashtags) with pagination and filters. Value: enables large-scale tweet collection for monitoring, analysis, and export without official API.
Searches X (Twitter) via free-form advanced query and returns normalized tweet lists with author, engagement, media, hashtags. Uses browser-act network capture and Python scripts to build URLs and parse GraphQL responses. Enables bulk tweet collection for brand monitoring, sentiment analysis, and KOL harvesting.
Automates the full Xiaohongshu content operation workflow from pain-point topic collection, style case analysis, topic selection, content writing, publishing with approval, to performance tracking. Uses browser-act CLI on a stealth browser to post and monitor. Delivers end-to-end XHS marketing automation with account safety controls and data-driven optimization.
Fetches Xiaohongshu note detail and comments by note ID using browser-act and Python scripts to read Vue SSR state. Returns title, description, author, engagement stats, tags, and paginated comments. Enables marketers to analyze RedNote content and audience feedback efficiently.
Searches Xiaohongshu (RedNote) notes by keyword via browser automation, extracting a paginated list with title, author, engagement stats, cover URL and xsecToken. Method: navigate to search page, apply optional filters, run Python extraction script on Vue SSR state, paginate by scrolling. Value: enables KOL discovery, topic monitoring and bulk XHS post collection for marketing research.
Searches Xiaohongshu notes by keyword with full field extraction (body, tags, images, video, stats) and all filter options. Uses DOM extraction scripts via browser-act to get rendered feeds and note details. Outputs structured note lists with engagement metrics for content monitoring and KOL research.
Fetches Xiaohongshu user profile and published notes by user ID via browser-act automation and Python scripts that read Vue SSR state. Returns nickname, bio, follower counts, tags, and paginated notes with engagement stats. Enables efficient KOL discovery and influencer research without manual browsing.
Automatically extracts YouTube video metrics and channel info by keyword via BrowserAct API. Method: run a Python script with keywords and date filter to call the API and parse structured data. Value: stable, CAPTCHA-free, cost-effective data for competitor scanning, campaign tracking, and market research.
Extracts structured YouTube channel data from search results via BrowserAct API using a Python script. Method: configure keyword and date filter, run script, get verified channels with subscriber counts. Value: stable, CAPTCHA-free, cost-effective channel discovery for influencer/competitor research and CRM enrichment.
Extracts a YouTube channel's business email and About metadata from a channel id, handle, or URL. It navigates the About view, reads description emails, and if absent follows non-social outbound links to recover emails from the creator's own site. Outputs structured JSON with contact and channel stats for influencer marketing and lead generation.
Extracts YouTube video lists and comments via BrowserAct API using a Python script. Provides keyword search, comment limit and scroll config to get structured video and viewer comment data. Value: zero-hallucination, no CAPTCHA, cost-efficient audience insight and market research.
Extracts structured YouTube search result data (videos, shorts, channels, playlists) via BrowserAct API using a Python script. Method: configure keyword, type, limit and run one command; handles API key check and retry. Value: stable, CAPTCHA-free, cost-effective data for market research and competitor analysis.
Extracts timestamped transcripts from a YouTube video's built-in panel and reformats them into summaries, chapter outlines, X threads, blog posts, or quotes. Uses Python scripts to read page DOM via browser-act. Value: turns video content into structured, reusable text assets for research, content repurposing, and quick consumption.
Extracts YouTube video transcripts via BrowserAct API and performs structured 8-dimension competitive content analysis. Method: run Python script to fetch transcripts, then Agent analyzes hook, messaging, audience, pain points, virality, credibility, business model, gaps. Value: reveals competitor strategy and content opportunities without manual viewing.
Extracts channel-level and video detail data from a specific YouTube channel via BrowserAct API using a Python script. Input channel URL and video type (Latest/Popular/Earliest) to get structured metrics like subscribers, views, likes, comments. Value: stable, CAPTCHA-free, cost-effective YouTube data for competitor tracking and content strategy.
Extracts structured Zhihu article data and full content via BrowserAct API using a Python script. Provides keyword search with date filters and automated retry. Outputs title, body, author, date, and URL for market research, PR monitoring, and trend tracking.
Installation
Copy and run in your terminal to add browser-act/skills to your Agent environment.
npx skills add browser-act/skills