llm-public-opinion-analytics — Claude Code skill: how to install
Monitors hot search rankings across 15 platforms, clusters topics, and runs LLM sentiment analysis with multi-channel alerts. Ideal for tracking trends in real time.
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a claude-codeWhat llm-public-opinion-analytics does
The skill tracks 26 ranking boards across 15 services, including Weibo, Douyin, Bilibili, and Baidu. It stores parsed items in a MySQL database, then relies on language models to cluster topics and evaluate post sentiment.
The repository splits into three core parts: a scraper suite under hotsearchcrawler/, an analysis pipeline in hotsearch_analysis_agent/, and a FastAPI interface in app.py running on port 8000. It sends notifications through Telegram, SMTP email, and WeChat Work bots.
Without ChromeDriver or EdgeDriver placed in your system PATH, the scrapers fail immediately. You also need Python 3.8+, MySQL 5.7+ or 8.0+, and an OpenAI-compatible API key or a local Huawei Pangu model.
What it helps with
- scrape hot search rankings across 15 web platforms
- cluster trending news topics using language models
- evaluate sentiment scores for social media discussions
- dispatch hot topic alerts to Telegram and WeChat Work
Example prompts for the agent
- Analyze sentiment trends for artificial intelligence topics on Weibo over the past 7 days
- Cluster trending search queries from Bilibili and Zhihu into 5 topics
- Set up real-time hot search alerts directed to Telegram
How to install llm-public-opinion-analytics
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a claude-code2Manually: put the files in place
~/.claude/skills/llm-public-opinion-analytics/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-public-opinion-analytics/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a codex2Manually: put the files in place
.agents/skills/llm-public-opinion-analytics/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a cursor2Manually: put the files in place
.cursor/skills/llm-public-opinion-analytics/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/data-skills llm-public-opinion-analytics2Manually: put the files in place
.github/skills/llm-public-opinion-analytics/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/data-skills --path skills/llm-public-opinion-analyticsManually: put the files in place
.devin/skills/llm-public-opinion-analytics/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-public-opinion-analytics
How do I install llm-public-opinion-analytics in Claude Code?
Run npx skills add reason-machines/data-skills --skill llm-public-opinion-analytics -a claude-code in your terminal. You can also place the configuration in ~/.claude/skills/llm-public-opinion-analytics/SKILL.md.
Which models does the analysis engine support?
It accepts OpenAI-compatible endpoints such as gpt-4 and also supports local deployments of the Huawei Pangu model.
What prerequisites are required before scraping?
You must have Python 3.8+, a running MySQL instance, and ChromeDriver or EdgeDriver installed in your system PATH.