Agent Analytics
An AI agent product analytics tool supporting funnel, retention, and experiment analysis.
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 agent product analytics tool supporting funnel, retention, and experiment analysis. Full Skill content: https://321skill.com/skills/agent-analytics-x/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 lack of a unified tool for AI agents to conduct product analysis. In practical development, AI agents need to analyze user behavior, conversion funnels, retention rates, A/B test results, and more. However, traditional analytics tools require manual operation and cannot be deeply integrated with AI agents. Agent Analytics enables agents to directly read product data via CLI commands and automatically recommends minimal growth actions, significantly improving data analysis efficiency.
Usage is straightforward: you simply install the CLI tool via the npx command, then authorize login through a browser. After that, you can use natural language instructions to query project data, create sites, analyze events, view funnels and retention, etc. It supports fixed commands like projects, stats, insights, funnel, retention, experiments, and the agent will automatically execute them and return results. For scenarios requiring an upgrade, the CLI will automatically guide you through the payment process.
It is well-suited for teams or individuals needing automated product analysis, especially those already using AI agents for development and operations who want their agents to directly read product data and provide growth suggestions. Product managers, data analysts, and marketing specialists can all use this Skill to quickly gain user behavior insights without manually logging into analytics platforms.
It is recommended to use this tool uniformly whenever you need AI agents to autonomously analyze product data. Note that it primarily relies on CLI execution, does not support direct API or curl calls, and requires browser authorization for login. The free version has read limits; upgrades require browser authorization. The CLI version is fixed at 0.5.34—do not use other versions.
Key Features
Unlike traditional analytics tools like Google Analytics, Agent Analytics is designed specifically for AI agents. It supports CLI commands that allow agents to directly read funnel, retention, and experiment data and automatically recommend minimal growth actions, eliminating the need for manual human operation. While tools like Mixpanel offer APIs, they require developers to write code for integration and do not support direct natural language interaction.
Limitations
Requires an npx environment; CLI version is fixed at 0.5.34; does not support direct API calls or curl; free version has read limits; upgrades require the browser authorization process.
FAQ
How do I install Agent Analytics?
Run `npx --yes @agent-analytics/cli@0.5.34 login`. The first run will guide you through browser login authorization.
Is an API key required?
No. Normal setup uses browser authorization login; no manual API key entry is needed.
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/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/raw/index.md