# llm-intelligent-public-opinion-analytics

This skill sets up an LLM-powered opinion analytics assistant: it crawls hot lists, scores sentiment, clusters topics and sends alerts.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2100 installs · ★ 5
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/data-skills/tree/HEAD/skills/llm-intelligent-public-opinion-analytics/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/llm-intelligent-public-opinion-analytics

## What it does

The skill walks through deploying a public opinion monitoring system built on an LLM. Crawlers pull hot lists from 15 platforms — Weibo, Bilibili, Zhihu, Baidu among them — covering 26 lists in total. The model then reads the content, extracts text from video, scores sentiment and groups related news into topics. You query it in plain language through a web interface.

Alerts go out to email, WeChat Work and Telegram. Crawler control sits on keyboard shortcuts in the web UI, and there is a programmatic API for scripted queries.

Expect a fair amount of setup. You need ChromeDriver or EdgeDriver matching your browser version for detail pages, MySQL 8.0+ with a `hotsearch_db` database, a Python environment with the dependencies from `requirements.txt`, and an LLM API key in OpenAI-compatible format. Database credentials, model keys and channel webhooks live in a `.env` file. Skip the browser driver and detail pages stay empty; skip the database and the crawler has nowhere to write. Worth checking both before the first run.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill llm-intelligent-public-opinion-analytics -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/llm-intelligent-public-opinion-analytics/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/llm-intelligent-public-opinion-analytics/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill llm-intelligent-public-opinion-analytics -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/llm-intelligent-public-opinion-analytics/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill llm-intelligent-public-opinion-analytics -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/llm-intelligent-public-opinion-analytics/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills llm-intelligent-public-opinion-analytics
```

2. **Manually: put the files in place**
- File: `.github/skills/llm-intelligent-public-opinion-analytics/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill llm-intelligent-public-opinion-analytics -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/llm-intelligent-public-opinion-analytics
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/llm-intelligent-public-opinion-analytics/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill llm-intelligent-public-opinion-analytics -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/data-skills/tree/HEAD/skills/llm-intelligent-public-opinion-analytics/SKILL.md

## When to use it
- pull trending topics from 15 platforms into one database
- score sentiment for news around a keyword
- group related storylines into topic clusters
- route spike alerts to email and Telegram
- ask about trends in plain language instead of SQL

## Example prompts
- Set up public opinion monitoring for AI topics
- Compare trending topics on Bilibili and Zhihu over the last day
- Alert me on Telegram if sentiment around electric vehicles turns negative

## Similar
- [llm-evaluation](https://affpapa.org/en/nevibecode/skills/llm-evaluation.md) — skill · 12755 installs
- [cost-aware-llm-pipeline](https://affpapa.org/en/nevibecode/skills/cost-aware-llm-pipeline.md) — skill · 4600 installs
- [llm-context](https://affpapa.org/en/nevibecode/skills/llm-context.md) — skill · 1300 installs
- [llm-council](https://affpapa.org/en/nevibecode/skills/am-will-llm-council.md) — skill · 1200 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 22 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md