# llm-sentry-geo-marketing

A skill for tracking how AI search engines DeepSeek, Doubao and Bocha mention your brand, and for pulling the citation links out of their answers.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 890 installs · ★ 12
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/marketing-skills/tree/HEAD/skills/llm-sentry-geo-marketing/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/llm-sentry-geo-marketing

## What it does

The skill documents LLM Sentry, a GEO monitoring platform. It runs queries through AI search engines, captures the answers and extracts the reference links inside them. From those it derives Share of Voice — how much of the conversation your brand owns next to competitors. Useful when you want to know what AI search actually says about your product and which domains it cites.

The repo is a monorepo with three parts: a Python monitoring service built on Playwright, a PostgreSQL database, and a desktop client written in Wails, Go and React with local SQLite storage. Queries go through browser automation — a provider opens the search page, flips on search mode, types the query and waits for the answer. Each engine gets its own provider class, so adding a new one means writing a new class. A FastAPI service exposes `POST /mock` to start a task: you pass keywords, the platform list, a repeat count and settings such as `headless` and `timeout`.

You need Python 3.11+ with `uv`, Docker running PostgreSQL 15+, and Chromium installed for Playwright. Skip the Chromium step and the automation will not start. The desktop client adds Go 1.21+, Node.js 18+ and Wails v2 to the list.

## Requirements
- Works with: Sentry

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/llm-sentry-geo-marketing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/llm-sentry-geo-marketing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/marketing-skills llm-sentry-geo-marketing
```

2. **Manually: put the files in place**
- File: `.github/skills/llm-sentry-geo-marketing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/marketing-skills --path skills/llm-sentry-geo-marketing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/llm-sentry-geo-marketing/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -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/marketing-skills/tree/HEAD/skills/llm-sentry-geo-marketing/SKILL.md

## When to use it
- check whether DeepSeek mentions your brand in its answers
- collect the domains AI search engines cite
- measure brand share of voice against competitors
- test answer stability by repeating the same query
- schedule monitoring runs through the REST API

## Example prompts
- Check if our brand shows up in DeepSeek answers for "AI搜索引擎对比"
- Run monitoring for the keyword "generative search optimization" on deepseek and doubao
- Pull the citation links from the answers and calculate our share of voice

## Similar
- [GEO Tracker by DigestSEO](https://affpapa.org/en/nevibecode/mcp/geo-tracker-by-digestseo.md) — MCP server · ★ 38
- [seo-geo](https://affpapa.org/en/nevibecode/skills/agricidaniel-seo-geo.md) — skill · 7200 installs
- [geo-citability](https://affpapa.org/en/nevibecode/skills/geo-citability.md) — skill · 847 installs
- [LLM Optimizer](https://affpapa.org/en/nevibecode/mcp/llm-optimizer.md) — MCP server · ★ 10
- [geo-platform-optimizer](https://affpapa.org/en/nevibecode/skills/geo-platform-optimizer.md) — skill · 830 installs
- [optimize-for-ai](https://affpapa.org/en/nevibecode/skills/optimize-for-ai.md) — skill · 6600 installs

From the same set: [reason-machines/marketing-skills](https://affpapa.org/en/nevibecode/by/reason-machines/marketing-skills.md) — 72 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