Web, Search & Scraping Agent Skills for DeepSeek Harness

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.

Interact with a local Chrome browser session via Chrome DevTools Protocol (only on explicit user approval after being asked to inspect…

Automates legal precedent and legislation searches on the Korean Supreme Court Library website to retrieve structured case data.

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket.

Scrapes Bilibili trending leaderboards, classifies AI, 3C hardware, and AIGC videos, and automatically updates daily reports in Feishu.

Searches Bilibili videos and extracts subtitles into formatted Markdown with timestamps for content analysis and transcription.

Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.

Detect and catalog content blocks on web pages using Puppeteer browser automation with semantic analysis, bounding box capture, and CSS…

Search for books using Kyobo Book Centre's online catalog.

Record polished UI demo videos using Playwright.

Scrape reviews, ratings, and brand mentions from multiple platforms using Apify Actors.

Web search and content extraction via Brave Search API.

Operates the browser via Playwright MCP — navigates, observes, interacts, and reports back based on any instruction.

Install and configure Bright Data SDK/CLI authentication.

Search the web, scrape websites, extract structured data from URLs, and automate browsers using Bright Data's Web MCP.

Implement Bright Data webhook signature validation and event handling.

This skill handles browser automation tasks using subagent architecture to keep the main context window clean.