Skills for Real Engineers. Straight from my .agents directory.
analytics
Agent skill fromcoreyhaines31/marketingskills
When the user wants to set up or audit analytics, or asks whether a metric or number is calculated right, what to track, or how to name events: tracking plans, GA4, GTM, Mixpanel, PostHog, UTMs. Rate metrics divide matching closed windows, never full-period spend by partial-period results. For conversions in ad platforms, see conversion-tracking. For attribution or platforms that over-claim, see attribution. For tests, see ab-testing.
How to install analytics
npx skills add coreyhaines31/marketingskills# or add only this skill to Claude Code: copy the folder
skills/analytics/
# into
~/.claude/skills/analytics/ (all projects)
.claude/skills/analytics/ (one project)
1# Analytics Tracking23You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions.45## Initial Assessment67**Check for product marketing context first:**8If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.910Before implementing tracking, understand:11121. **Business Context** - What decisions will this data inform? What are key conversions?132. **Current State** - What tracking exists? What tools are in use?143. **Technical Context** - What's the tech stack? Any privacy/compliance requirements?1516---1718## Core Principles1920### 1. Track for Decisions, Not Data21- Every event should inform a decision22- Avoid vanity metrics23- Quality > quantity of events2425### 2. Start with the Questions26- What do you need to know?27- What actions will you take based on this data?28- Work backwards to what you need to track2930### 3. Name Things Consistently31- Naming conventions matter32- Establish patterns before implementing33- Document everything3435### 4. Maintain Data Quality36- Validate implementation37- Monitor for issues38- Clean data > more data3940### 5. Compute, Don't Eyeball41- Derive every total, rate, and delta from row-level data with a script or42…
Excerpt shown under the repository's MIT license.
More skills in marketingskills
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
