Llm Public Opinion Analytics Assistant

This crawls trending topics from 26 lists across 15 platforms (Weibo, Bilibili, Zhihu, etc.) and runs LLM analysis on top for clustering, sentiment tracking, and conversational queries. You get a web interface where you can ask "show me AI trends from the past week" and it pulls from MySQL storage, plus push notifications via email, WeChat Work, or Telegram when certain keywords spike. The setup is hefty, you'll need MySQL, matching browser drivers for Selenium, and proper API keys for whatever LLM you're using. Once running, it's solid for monitoring Chinese social media at scale. The conversational interface is cleaner than writing SQL queries yourself, though you still have direct database access if you need it.

skills.sh installs: 1.9K
GitHub stars: 2
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/data-skills --skill llm-public-opinion-analytics-assistant --agent claude-code

Installs into .claude/skills of the current project.

Files

LLM-Based Intelligent Public Opinion Analytics Assistant

Skill by ara.so — Data Skills collection.

Overview

This project is an intelligent public opinion analysis assistant that combines real-time data from 26 trending lists across 15 mainstream platforms with large language model (LLM) analysis capabilities. It provides conversational hot search queries, topic-specific searches, topic clustering analysis, and sentiment analysis through a web interface. The system supports keyboard shortcuts for crawler control, multi-platform data retrieval with direct navigation, and multi-channel hot topic push notifications (email, WeChat, Enterprise WeChat, Telegram).