Analytics audit

Skill AtulPurohit/Antigravity-Awesome-Skills/skills/analytics-audit

Audit analytics implementations for tracking gaps and data quality issues.From its SKILL.md

Install

npx -y skills add AtulPurohit/Antigravity-Awesome-Skills --skill analytics-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 401 tokens by cl100k_base, as published. Nobody here has run it

Analytics Auditor

Purpose

Ensure business decisions are based on complete, accurate analytics data.

Audit Checklist

Coverage Audit

// Required events for SaaS product
const REQUIRED_EVENTS = [
  // Acquisition
  'page_view', 'utm_click', 'sign_up', 'sign_in',
  // Activation
  'onboarding_step_started', 'onboarding_step_completed', 'activation_event',
  // Engagement
  'feature_used', 'session_started', 'search_performed',
  // Revenue
  'upgrade_clicked', 'checkout_started', 'payment_completed', 'subscription_cancelled',
  // Retention
  'return_visit', 'notification_clicked',
];

Data Quality SQL

-- Check for event volume anomalies
SELECT
  DATE(created_at) AS date,
  event_name,
  COUNT(*) AS count,
  LAG(COUNT(*)) OVER (PARTITION BY event_name ORDER BY DATE(created_at)) AS prev_day,
  ROUND((COUNT(*) - LAG(COUNT(*)) OVER (PARTITION BY event_name ORDER BY DATE(created_at)))::numeric
        / NULLIF(LAG(COUNT(*)) OVER (PARTITION BY event_name ORDER BY DATE(created_at)), 0) * 100, 1) AS pct_change
FROM analytics_events
WHERE created_at >= NOW() - INTERVAL '30 days'
GROUP BY 1, 2
HAVING ABS(pct_change) > 50  -- Flag 50%+ day-over-day swings
ORDER BY 1 DESC, ABS(pct_change) DESC;

-- Missing user properties
SELECT COUNT(*) FILTER (WHERE user_id IS NULL) / COUNT(*)::float AS pct_anonymous
FROM analytics_events
WHERE event_name = 'purchase_completed';

Outputs

Analytics coverage report
Data quality test queries
Implementation gap priority list
Analytics governance documentation
Data validation CI tests

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.