Agent skill · Data & Analytics

insight-driven-event-tracking

Transform raw data into actionable insights by shifting from tracking "what happened" to "why it happened." Use this skill when designing instrumentation specs for new features, auditing analytics dashboards that provide no clear direction, or diagnosing sudden drops in conversion.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill insight-driven-event-tracking --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/analysis/insight-driven-event-tracking/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Insight-Driven Event Tracking Most analytics efforts fail because they track "entertainment" (data that is interesting but doesn't change behavior) rather than "news" (information that forces a change in the real world). This framework shifts instrumentation from simple event logging to capturing the context necessary to explain user intent. ## The Core Principles ### 1. Observation vs. Insight * **Observation:** A raw fact from the database (e.g., "Power users book 4x more than new users"). This has no context and offers no clear action. * **Insight:** An observation plus the "Why" (e.g., "Power users convert at 2x the rate when they see at least 5 drivers on the map"). This tells you exactly what lever to pull (increase supply density). ### 2. The Physics of the Growth Model Before tracking, define the "physics" of your specific universe to identify where levers actually exist: * **Market:** Who are the users and suppliers? * **Product:** What is the core value proposition? * **Model:** How do you charge or capture value? * **Channel:** How do users find you? (e.g., In Southeast Asia, Gojek’s physical drivers in green jackets were a primary growth channel). ## The Instrumentati

What's inside
Steps it walks through
  1. The Core Principles
  2. 1. Observation vs. Insight
  3. 2. The Physics of the Growth Model
  4. The Instrumentation Workflow
  5. Step 1: Identify the "Step Before"
  6. Step 2: Define Contextual Properties
  7. Step 3: Run the "News Test"
  8. Examples
  9. Benchmarks for Success
  10. Common Pitfalls to Avoid
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the insight-driven-event-tracking skill do?

Transform raw data into actionable insights by shifting from tracking "what happened" to "why it happened." Use this skill when designing instrumentation specs for new features, auditing analytics dashboards that provide no clear direction, or diagnosing sudden drops in conversion.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill insight-driven-event-tracking --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going