agentleFS
jeftekharijeftekhari/google-analytics/skills/check-analytics/SKILL.md

check-analytics

Skill2 starsChanged 9 months agoMITView on GitHub

Audit existing Google Analytics implementation. Checks for common issues, missing configurations, and optimization opportunities.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search for analytics code:

    line 12
  2. Distinctive:

    Create a report with these sections:

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analytics Audit Skill

You are auditing the Google Analytics implementation in this project.

Step 1: Find Existing Analytics

Search for analytics code:

  • gtag or dataLayer references
  • Google Tag Manager (GTM-)
  • Universal Analytics (UA-) - deprecated
  • GA4 Measurement IDs (G-)
  • Third-party analytics (Mixpanel, Amplitude, Plausible, etc.)

Step 2: Generate Audit Report

Create a report with these sections:

Current Setup

  • Framework detected
  • Analytics provider(s) found
  • Measurement ID(s) found (redact last 6 chars for security: G-XXXX******)
  • Implementation method (gtag.js, GTM, npm package)

Issues Found

Check for:

  1. Deprecated UA properties - Universal Analytics sunset July 2024
  2. Missing pageview tracking for SPAs
  3. Hardcoded Measurement IDs (should use env vars)
  4. Missing TypeScript types for gtag
  5. No consent mode implementation
  6. Debug mode in production (check for debug_mode: true)
  7. Duplicate script loading
  8. Missing error boundaries around analytics code
  9. Blocking script loading (should be async)
  10. No fallback for ad-blocker scenarios

Recommendations

Provide actionable fixes ranked by priority:

  • 🔴 Critical (breaking/deprecated)
  • 🟡 Warning (best practice violations)
  • 🟢 Suggestion (optimizations)

Event Coverage Analysis

List custom events being tracked and suggest missing ones:

  • Sign up / Login events
  • Purchase/conversion events
  • Form submissions
  • Error tracking
  • Key user interactions

Output Format

# Analytics Audit Report

## Summary
- **Status**: [Healthy / Needs Attention / Critical Issues]
- **Provider**: [GA4 / GTM / Other]
- **Framework**: [detected framework]

## Current Implementation
[describe what was found]

## Issues

### 🔴 Critical
[list critical issues]

### 🟡 Warnings
[list warnings]

### 🟢 Suggestions
[list suggestions]

## Event Coverage
| Event Type | Status | Recommendation |
|------------|--------|----------------|
| Page Views | ✅ | - |
| Sign Up | ❌ | Add sign_up event |
| ... | ... | ... |

## Next Steps
1. [ordered action items]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.