Agent Analytics
An AI-powered product analytics tool that supports funnel, retention, experiment, and other analyses.
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: Agent Analytics. It is used for: An AI-powered product analytics tool that supports funnel, retention, experiment, and other analyses. Full Skill content: https://321skill.com/skills/agent-analytics-x-2/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the challenge product teams face in quickly gaining user behavior insights. In practice, product managers and data analysts often need to query databases manually or wait for BI reports. Agent Analytics allows AI to directly execute product analysis commands via the CLI, fetching real-time data for funnels, retention, user paths, experiments, and more, while automatically recommending minimal growth actions.
Usage is straightforward: you simply run CLI commands via npx in your terminal, or let an AI agent automatically invoke the corresponding command based on natural language instructions. For example, tell the AI "Analyze the registration conversion funnel for the last 7 days," and it will automatically execute the funnel command and return the conversion rate for each step. It supports browser login authorization, eliminating the need for manual API key configuration.
It's ideal for teams or individuals who need to iterate products quickly and optimize user growth and retention strategies. Particularly for teams already using tools like Amplitude or Mixpanel but wanting to embed analytics capabilities into AI workflows, Agent Analytics enables a closed loop from data querying to actionable recommendations.
It's recommended to maintain consistent versions when using the npx command to avoid compatibility issues due to version discrepancies. Note that the free tier has read limits, and some advanced features (such as experiment analysis and contextual analysis) require a Pro subscription, accessible via the upgrade-link command.
Key Features
Unlike traditional product analytics tools such as Amplitude or Mixpanel, Agent Analytics interacts entirely through the CLI with AI agents, eliminating the need for manual dashboard configuration or SQL writing. The AI can directly execute analysis commands and recommend growth actions based on the results, automating the journey from data to decision.
Limitations
Requires an npx environment (Node.js), relies on browser login authorization, the free tier has read limits, and some advanced features (e.g., experiment analysis, contextual analysis) require a Pro subscription.
FAQ
How do I install Agent Analytics?
No installation is required; you can use it directly with the npx command: `npx --yes @agent-analytics/cli@0.5.34 <command>`. You can also install it globally: `npm install -g @agent-analytics/cli`.
Is an API key required?
No. Normal setup uses browser login authorization, so manual API key configuration is unnecessary. The detached login mode is only used in environments without browser callbacks, such as Paperclip or OpenClaw.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-analytics-x-2/raw/index.md to read the original Skill definition (Markdown format) for Agent Analytics, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-analytics-x-2/raw/index.md