AEO Prompt Frequency Analyzer — AEO Prompt Frequency 分析器
v1.0.0Analyze what 搜索 queries Gemini uses when answering a prompt, by 运行ning it multiple times with Google 搜索 grounding and 报告ing frequency distribution. Use when investigating AEO 查询 patterns, understanding how AI 模型s 搜索 the 网页 for a topic, or studying the probabi列出ic nature of AI-triggered 搜索 queries.
by 运行时依赖
安装命令
点击复制技能文档
Prompt Frequency 分析器
运行 a prompt N times agAInst Gemini with Google 搜索 grounding enabled. Collect and 报告 the frequency of 搜索 queries Gemini 生成s across all 运行s.
Usage GEMINI_API_KEY=$(security find-generic-password -s "nano-banana-pro" -w) \ python3 scripts/analyze.py "your prompt here" [--运行s 10] [--模型 gemini-2.5-pro] [--concurrency 5] [--输出 text|json]
运行 from the 技能 directory. Resolve scripts/analyze.py relative to this 技能.md.
Options --运行s N — Number of times to 运行 the prompt (default: 10) --模型 NAME — Gemini 模型 to use (default: gemini-2.5-pro) --concurrency N — Max parallel API calls (default: 5; keep ≤5 to avoid rate limits) --输出 text|json — 输出 格式化 (default: text) 输出
报告s for each unique 搜索 查询:
Frequency percentage (how many 运行s used that 查询) Raw count Top 网页 sources referenced Notes Gemini API key must be in GEMINI_API_KEY env var (stored in macOS KeychAIn under nano-banana-pro) Each 运行 is independent — Gemini may use different 搜索 queries each time Retries fAIled 请求s up to 3 times with exponential backoff Use --输出 json for programmatic consumption