aeo-prompt-frequency-analyzer
Analyze what search queries Gemini uses when answering a prompt, by running it multiple times with Google Search grounding and reporting frequency distribution. Use when investigating AEO query patterns, understanding how AI models search the web for a topic, or studying the probabilistic nature of AI-triggered search queries.
Source facts
- Repository
- modbender/skill-library-mcp
- Last source activity
- March 6, 2026 at 18:33
- Detected SKILL.md language
- English
- Stars
- 12
- Forks
- 3
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- aeo-prompt-frequency-analyzer
- description
- Analyze what search queries Gemini uses when answering a prompt, by running it multiple times with Google Search grounding and reporting frequency distribution. Use when investigating AEO query patterns, understanding how AI models search the web for a topic, or studying the probabilistic nature of AI-triggered search queries.
# Prompt Frequency Analyzer
Run a prompt N times against Gemini with Google Search grounding enabled. Collect and report the frequency of search queries Gemini generates across all runs.
## Usage
```bash
GEMINI_API_KEY=$(security find-generic-password -s "nano-banana-pro" -w) \
python3 scripts/analyze.py "your prompt here" [--runs 10] [--model gemini-2.5-pro] [--concurrency 5] [--output text|json]
```
Run from the skill directory. Resolve `scripts/analyze.py` relative to this SKILL.md.
## Options
- `--runs N` — Number of times to run the prompt (default: 10)
- `--model NAME` — Gemini model to use (default: gemini-2.5-pro)
- `--concurrency N` — Max parallel API calls (default: 5; keep ≤5 to avoid rate limits)
- `--output text|json` — Output format (default: text)
## Output
Reports for each unique search query:
- Frequency percentage (how many runs used that query)
- Raw count
- Top web sources referenced
## Notes
- Gemini API key must be in `GEMINI_API_KEY` env var (stored in macOS Keychain under `nano-banana-pro`)
- Each run is independent — Gemini may use different search queries each time
- Retries failed requests up to 3 times with exponential backoff
- Use `--output json` for programmatic consumption
View on GitHub