Agent skills that teach your AI, Cursor, and other AI agents to read web analytics like a senior analyst.
Diagnose traffic changes, judge channel quality, and read funnels without the usual rookie mistakes. Works with any analytics source; first-class support for Clamp MCP.
Skills 13 in the Claude listing
Analytics diagnostic method The spine of analytics investigation. Analytics profile setup One-time interview that captures the business context (industry, model, primary conversion, traffic range, ICP, data stack) into a local analytics-profile.md file. Anomaly detection time series Formal time-series methods that augment the hand-coded fingerprint library in traffic-change-diagnosis. Bayesian experiment reader Bayesian counterpart to experiment-result-reader. Causal dag builder Build a refinable causal DAG before answering "did X cause Y" on observational data. Causal evidence checklist Bradford Hill's 9 viewpoints (1965) reframed as a checklist for product analytics. Causal query classifier Pearl's three-rung causal hierarchy as a query classifier. Channel and funnel quality Judge whether traffic is actually valuable and whether funnel drop-off is real or expected. Event schema author Author and maintain an event-schema.yaml file. Experiment result reader Read the result of a running A/B test honestly. Metric context and benchmarks Interpret analytics metrics with correct context. Sequential monitoring Always-valid sequential inference for honest peeking at running A/B tests. Traffic change diagnosis Diagnose why website traffic changed. 