Agent skill · marketing growth · aradotso
llm-sentry-geo-marketing
GEO (Generative Engine Optimization) monitoring platform for tracking brand mentions in AI search engines like DeepSeek and Doubao
Why this skill is useful
Provides specific commands and workflows for monitoring brand mentions in AI search engines that the AI wouldn't generate on its own.
What it needs
Requires docker, docker-compose, go, node, python installed locally. About 7k tokens when loaded. Last updated 2026-08-05. 8 stars on the source repository.
What this skill does
LLM Sentry GEO Marketing Skill Skill by ara.so — Marketing Skills collection. What This Project Does LLM Sentry is an automated monitoring and analysis platform for GEO (Generative Engine Optimization). It tracks how AI search engines (DeepSeek, Doubao, Bocha) mention brands and analyze citation sources in their responses. The platform uses browser automation (Playwright) to simulate real user queries, extract AI responses, parse reference links, and calculate Share of Voice (SoV) metrics. Core capabilities: Real-time brand exposure monitoring in AI search results Citation source extraction and domain analysis Multi-round query execution for stability testing Desktop client (Wails + Go + React) with local SQLite storage RESTful API for task automation PostgreSQL-based data persistence Project Structure This is a monorepo with three main components: Installation Prerequisites Python 3.11+ with uv package manager Docker and Docker Compose PostgreSQL 15+ (via Docker) For desktop client: Go 1.21+, Node.js 18+, Wails v2 Quick Setup with Makefile Manual Setup Desktop Client Setup Database Schema The system uses two main tables: Records table (monitoring results): Citations table (extracted references): API Usage Start API Server Start server: Create Monitoring Task POST /mock Python example: Provider Implementation Pattern Each AI platform has a dedicated provider class: Example DeepSeek provider: Core Domain Extraction Logic Database Operations Running Monitoring Tasks Single Query Example Multi-Round Query Example Desktop Client (Wails) Backend Configuration Environment Variables Create .env file in llmsentrymonitor/: Settings File Common Patterns Pattern 1: Batch Keyword Monitoring Pattern 2: Citation Analysis Pipeline Pattern 3: Share of Voice Calculation Troubleshooting Issue: Playwright Browser Not Found Issue: Database Connection Failed Issue: Login Required During Headless Mode First run in non-headless mode to complete login: After successful login, browser will …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/llm-sentry-geo-marketing