llm-sentry-geo-marketing — Claude Code skill
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.
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a claude-codeWhat llm-sentry-geo-marketing 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.
What it helps with
- 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 for the agent
- 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
How to install llm-sentry-geo-marketing
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a claude-code2Manually: put the files in place
~/.claude/skills/llm-sentry-geo-marketing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-sentry-geo-marketing/
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a codex2Manually: put the files in place
.agents/skills/llm-sentry-geo-marketing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a cursor2Manually: put the files in place
.cursor/skills/llm-sentry-geo-marketing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/marketing-skills llm-sentry-geo-marketing2Manually: put the files in place
.github/skills/llm-sentry-geo-marketing/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/marketing-skills --path skills/llm-sentry-geo-marketingManually: put the files in place
.devin/skills/llm-sentry-geo-marketing/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -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-sentry-geo-marketing
How do I install llm-sentry-geo-marketing in Claude Code?
Run npx skills add reason-machines/marketing-skills --skill llm-sentry-geo-marketing -a claude-code. The skill lands at ~/.claude/skills/llm-sentry-geo-marketing/SKILL.md.
What does llm-sentry-geo-marketing do?
It covers the LLM Sentry platform: queries go through AI search engines, citation links are parsed from the answers, and brand share of voice is calculated.
What do I need before using this skill?
Python 3.11+ with uv, Docker with PostgreSQL 15+, and Chromium installed for Playwright. The desktop client also needs Go 1.21+, Node.js 18+ and Wails v2.
