Productivity
news-briefing avatar

news-briefing

Real-time AI news briefing tool. Instantly search the web for any topic, get summarized insights in Chinese, and receive professional briefing cards via Feishu.

Introduction

News Briefing is a high-efficiency AI agent skill designed for professionals who need to stay informed without information overload. By integrating Perplexity for real-time web search and PPIO for advanced AI analysis, this tool transforms raw search results into structured, intelligent digests. It is built to serve as a private intelligence officer, allowing users to trigger updates via simple natural language commands like 'briefing on Tesla' or 'AI news today'. The skill handles multi-topic aggregation, filtering out noise, and delivering actionable insights, backgrounds, and logical analysis directly to your Feishu workspace via high-fidelity, mobile-optimized cards.

  • Real-time intelligent search across global sources using Perplexity API.

  • Deep AI-powered insights, including contextual background, logical drivers, industry impact, and key signal tracking.

  • Native Feishu integration, delivering rich-text cards that collapse for clean mobile viewing.

  • Flexible deployment options ranging from simple ad-hoc chat triggers to automated daily scheduled reports.

  • Customizable output categories including AI, GEO, SPORT, BIZ, and CUSTOM.

  • Requires API keys for Feishu (APP_ID/SECRET) and Perplexity sonar.

  • The output is fully localized to Chinese, ideal for regional market monitoring.

  • Optimized for scenarios like daily competitive intelligence, trend tracking, sports updates, and macroeconomic research.

  • Designed for command-line usage or agentic integration, supporting parameters like --topics, --counts, and --target-user for automated scheduling.

  • Use the --no-insight flag to improve latency for quick news scanning without deep analysis.

Repository Stats

Stars
4,456
Forks
1,217
Open Issues
7
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
Apr 30, 2026, 04:12 PM
View on GitHub