Agent skill · data analytics · aradotso
adspy-analytics-intelligence
Analytics platform for tracking and analyzing sponsored advertisements across multiple networks with competitor insights
Why this skill is useful
Adds executable commands for tracking and analyzing competitor ad campaigns across multiple networks that aren't widely known.
What it needs
Requires git installed locally. Requires adspy account access. About 5k tokens when loaded. Last updated 2026-08-05. 5 stars on the source repository.
What this skill does
AdSpy Analytics Intelligence Skill by ara.so — Data Skills collection AdSpy is an analytics platform for tracking and analyzing sponsored advertisements across multiple advertising networks. It provides real-time monitoring of competitor ad campaigns, ad spend trends, creative performance metrics, and actionable insights on advertising strategies. Installation Windows (PowerShell) Manual Installation Core Concepts AdSpy operates on several key components: Network Monitors: Track ads across different advertising platforms Campaign Analyzers: Process and categorize ad campaigns Intelligence Reports: Generate insights on competitor strategies Creative Trackers: Monitor ad creative performance and variations Spend Estimators: Estimate advertising budget allocation Configuration Configuration is typically managed through environment variables or a configuration file: Configuration file (config.yaml): Key Commands Starting the Analytics Platform Campaign Tracking Analytics and Reporting Data Management API Usage Patterns Python Library Usage Searching for Ads Analyzing Competitor Strategies Monitoring Ad Spend Trends Tracking Creative Performance Exporting Data Real-time Monitoring Advanced Patterns Batch Processing Multiple Advertisers Custom Analytics Pipeline Competitor Comparison Dashboard Troubleshooting Rate Limiting Issues Connection Issues Data Synchronization Performance Optimization Debugging Best Practices 1. Use environment variables for API keys and sensitive configuration 2. Enable caching for frequently accessed data to reduce API calls 3. Implement retry logic for production environments 4. Use batch operations when processing multiple advertisers 5. Set appropriate monitoring intervals to balance freshness and rate limits 6. Archive old data regularly to maintain performance 7. Use filters early in pipelines to reduce data processing overhead
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/adspy-analytics-intelligence