Retrieve current news articles via DuckDuckGo Lite and RSS with paywall detection.
npx skills add https://github.com/hailingu/llm-prompts --skill news-search-hailingu
Please help me install this Agent Skill. Skill: news-search Source: https://github.com/hailingu/llm-prompts/tree/main/skills/news-search Command: npx skills add https://github.com/hailingu/llm-prompts --skill news-search-hailingu
Distributes up-to-date news by using a browser-first workflow that gracefully handles paywalls, reducing brittle scraping and failed extractions.
Ask the skill to search for a topic and return the top five open results using browser-based retrieval with paywall awareness.
High-intent search queries and answers about installing and using this skill.
Paywall-aware retrieval uses a detector to stop deep extraction when paywalls are encountered, preventing brittle scraping failures. When browser rendering is unavailable, it automatically applies an HTTP fallback to retrieve available content.
Multi-source discovery queries DuckDuckGo Lite and RSS feeds simultaneously for broad news coverage. This browser-first workflow aggregates current articles across platforms before applying retrieval workflows.
Browser-based retrieval uses Playwright to render dynamic pages and detect paywalls during extraction. If Playwright is unavailable, the workflow safely falls back to HTTP retrieval for open content.
Playwright is required for browser-based rendering and paywall detection, but the workflow supports an HTTP fallback when it is unavailable. You can retrieve open articles without it, though paywalled content detection will be limited.
You can search for a topic and request the top open results using browser-based retrieval. The paywall policy filters out restricted content, ensuring you receive accessible articles.
Standard HTTP requests cannot render JavaScript or detect paywalled content, causing extraction failures. Browser-first retrieval uses Playwright to render pages and a paywall detector to gracefully stop extraction on restricted sites.
tiankong0101-byteSearch the web across DuckDuckGo, Tavily, and multi-engine fallbacks.
Pieverse-EngAggregate crypto news, keyword search results, and on-chain market data.
tusososExtract clean article text from URLs and save it as plain text.
zakaroooExtract web page content and metadata via the page_reader function.
