Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides tools for AI agents to interact with the web via remote browsers and residential proxies. It allows automation builders to bypass bot protections like Cloudflare and DataDome by connecting through the Chrome DevTools Protocol using Playwright or Puppeteer.
The skills facilitate structured data extraction from JavaScript-heavy sites and support geo-targeting, persistent sessions, and live VNC inspection for debugging agent behavior in real-time.
WHO IT'S FOR
AI agent / automation builders
integrating anti-detection browser capabilities into agents
Data engineers
extracting structured data from protected websites
Market intelligence analysts
collecting geo-targeted e-commerce and search data
Content researchers
extracting structured metadata and subtitles from YouTube
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Claude Code plugin marketplace
Installs: Oxylabs plugin bundle for proxies, Web Scraper API, Web Unblocker, headless browsers, and YouTube video data extraction; the positively mapped supplied paths are listed below. · Claude Code
Before you start
Claude Code
Inside a Claude Code agent session, enter these commands in order to add the Oxylabs marketplace and install the Oxylabs plugin.
A target URL replacing <replace with the URL to test>
OXYLABS_USERNAME environment variable
OXYLABS_PASSWORD environment variable
Use the web-unblocker skill to make one basic request to my target URL and report the response status and whether useful content was returned. Use OXYLABS_USERNAME and OXYLABS_PASSWORD from my environment, preserve the required TLS flag, and do not crawl additional pages. Target URL: <replace with the URL to test>.
Use the web-scraper-api skill to scrape one URL with the universal source and summarize the returned status, final URL, and main content. Use OXY_WSA_USERNAME and OXY_WSA_PASSWORD from my environment and make only one Realtime API request. URL: <replace with the page URL>.
A YouTube video ID replacing <replace with the YouTube video ID>
OXY_WSA_USERNAME environment variable
OXY_WSA_PASSWORD environment variable
Use the video-data skill and its Video Data API to retrieve structured metadata for one YouTube video. Use OXY_WSA_USERNAME and OXY_WSA_PASSWORD from my environment, request youtube_metadata with parsing enabled, and summarize the title, views, likes, and description when present. Video ID: <replace with the YouTube video ID>.
Claude