ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

agent-analytics

Run analytics end-to-end from your agent without opening a dashboard. English-first workflow, with Chinese docs and content available. Create projects, ship tracking, query results, and run experiments.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/dannyshmueli/agent-analytics
Or

What This Skill Does

Agent Analytics is a developer-centric web analytics platform designed to be queried directly by AI agents. Unlike traditional heavy-handed analytics tools that require complex dashboard navigation, this skill provides a CLI and MCP-native interface. It focuses on the 'Is this project alive and growing?' philosophy, encouraging developers to track only the most critical 3-5 custom events alongside automatic page view tracking. It supports funnel analysis, retention cohorts, traffic heatmaps, and A/B experiment tracking, allowing your AI to proactively monitor the health of your deployments without human intervention.

Installation

To integrate this skill into your environment, use the OpenClaw command-line interface: clawhub install openclaw/skills/skills/dannyshmueli/agent-analytics

Once installed, initialize your project using the CLI:

  1. Login via npx @agent-analytics/cli login --token aak_YOUR_API_KEY.
  2. Create a project entry using npx @agent-analytics/cli create [PROJECT_NAME] --domain [URL].
  3. Inject the provided tracking snippet into the <body> of your web application.
  4. Verify event flow with npx @agent-analytics/cli events [PROJECT_NAME].

Use Cases

  • Continuous Growth Monitoring: Automatically query retention rates and conversion funnels to assess if a recent update improved user engagement.
  • A/B Testing Optimization: Let the AI agent compare variant performance and suggest the winning strategy based on real-time event data.
  • Error Tracking: Proactively monitor the error event category to catch user-facing issues before support tickets pile up.
  • Feature Adoption Analysis: Track usage of core features to decide which parts of your product to invest more resources in.
  • Cross-Project Management: Use the AI to aggregate data across multiple domains/projects to get a high-level view of your development ecosystem.

Example Prompts

  1. "OpenClaw, check the conversion funnel for 'my-site' and tell me where we are losing the most users between the landing page and signup."
  2. "Compare the cta_click metrics between the last two weeks for our new feature launch to see if the engagement increased."
  3. "Run a property analysis for the feature_used event to identify which specific features are currently most popular among our users."

Tips & Limitations

  • Simplicity is Key: Avoid 'track everything' syndrome. Stick to the suggested standard events (cta_click, signup, login, feature_used, checkout, error) to maintain clean, actionable data.
  • Naming Consistency: Always use npx @agent-analytics/cli properties-received [PROJECT_NAME] before adding new tracking events to ensure property naming remains consistent with existing project data.
  • Security: Keep your API keys and write tokens separate. The write token goes in your frontend snippet, while your personal API key should only be used by your AI agent/CLI for querying data.
Read Full Documentation on GitHub

Metadata

Author@dannyshmueli
Stars3376
Views1
Updated2026-03-24
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-dannyshmueli-agent-analytics": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags

#analytics#tracking#web#events#experiments#live
Safety Score: 4/5

Flags: network-access, external-api

Related Skills

decision-ledger

从纪要、聊天或项目材料中提取决策、负责人、截止时间、前提假设与撤销条件。；use for decision, meeting, governance workflows；do not use for 编造不存在的决策, 替代法律审计.

52yuanchangxing 4473

Spreadsheet & Data Wrangling Master

Complete spreadsheet methodology — data cleanup, transformation, analysis, dashboards, automation, and reporting. Works with CSV, Excel, Google Sheets, or any tabular data. Use when the user needs to clean messy data, build reports, create dashboards, automate recurring spreadsheet tasks, or transform data between formats.

1kalin 4473

candidate-tracker

候选人追踪系统。触发场景：用户要求管理候选人池，记录状态、设置提醒、生成标签。

51mee-com 4473

metric-definition-catalog

把散落指标统一整理成口径、公式、归属、例外情况与常见误用。；use for metrics, catalog, analytics workflows；do not use for 编造指标来源, 替代 BI 平台配置.

52yuanchangxing 4473

insight-brief-generator

把报表和图表转成管理层可读的洞察摘要，区分发现、解释和建议动作。；use for insights, analytics, briefing workflows；do not use for 夸大结论, 把相关性当因果.

52yuanchangxing 4473