A data analyst's job isn't building one dashboard, it's six recurring questions: is this number actually unusual, is it good or bad relative to a real benchmark, are newer customers doing better than older ones, what should the dashboard even show, where's the biggest growth lever, and what are customers actually saying. gtm-skills' Data Analyst pack covers all six in free, open source skills. Links to the skill files and to the Intempt agent that answers these questions continuously against your live event data.
A data analyst gets asked to build dashboards, but the actual job underneath that request is a handful of specific questions asked over and over: is this number normal, is it good, are things trending the right direction, and what should we actually do about it.
Six recurring questions, not one deliverable. That's how this pack is organized.
TL;DR
- gtm-skills' Data Analyst pack is 6 free skills: anomaly detection, benchmark comparison, cohort tracking, KPI dashboard design, growth lever prioritization, and customer research synthesis.
- Install once with npx skills add sidchaudhary/gtm-skills.
- Start with the-kpi-blueprint - decide what to measure and how before analyzing live numbers.
- Intempt's Data Analyst agent detects the right report type from a plain-language question and renders it inline.
How to install these in about 60 seconds
- Run npx skills add sidchaudhary/gtm-skills.
- Create a Claude project per skill - "Anomaly Alert," "Cohort Tracker."
- Paste the skill's SKILL.md into the project instructions.
- Start a chat with your metric data, benchmark source, or research material.
The 6 skills
1. The KPI Blueprint
Designs KPI dashboards with metric formulas, visualization types, alert thresholds, and layout wireframes - for marketing, sales, exec, product, or CS dashboards. Start here: decide what to measure before you measure it. Read the skill.
2. The Anomaly Alert
Takes a time series of one metric and flags which recent points are genuinely outside its normal range, using a stated trailing-average-and-deviation method, not a gut read of a chart. Feeds the metric it flags into your dashboard from the-kpi-blueprint. Read the skill.
3. The Benchmark Check
Takes one of your metrics and checks it against a stated benchmark source, returning a clear over/under read and what the gap actually means. Honest about its limits: it compares against whatever source you supply, or says plainly when it's using general public knowledge instead. Read the skill.
4. The Cohort Tracker
Groups customers by acquisition period and tracks a retention or revenue metric across the periods that follow, returned as a cohort table. Use it to see whether newer customers perform better or worse than older ones, not just a blended average that hides the trend. Read the skill.
5. The Lever Finder
Gets you a prioritized growth strategy with maturity assessment, growth levers, channel priorities, and a quarterly plan - for strategic planning and growth audits, not just a metrics readout. Read the skill.
6. The Theme Miner
Extracts signal from customer research assets - transcripts, reviews, tickets, surveys - and synthesizes it into themes, quote banks, and evidence-based personas. For when you have real customer material and want personas grounded in it, not assumption. Read the skill.
The order to build them in
The-kpi-blueprint comes first - decide what you're measuring and how before you start analyzing numbers. Add the-anomaly-alert once a dashboard is live, so you know when something in it actually needs attention. The-benchmark-check and the-cohort-tracker come next, once you have a baseline worth comparing against or a customer base old enough to track across cohorts. Save the-lever-finder for quarterly planning and the-theme-miner for when you've actually collected customer research worth mining.
What to never hand over
Claims about industry benchmarks you haven't verified - the-benchmark-check discloses its sources plainly, and that discipline should carry into anything you publish externally. And the strategic call on which growth lever to pull first: the-lever-finder prioritizes, a person still decides given constraints the data doesn't capture, like team capacity or a board commitment.
When you outgrow the manual version
Intempt's Data Analyst agent runs this same job continuously: ask it a plain-language question and it detects the right report type - trend, funnel, cohort, path - renders the chart inline, and offers to build the segment, journey, or experiment that addresses what it found, without switching tools. Same six jobs, running against live event data instead of a CSV export.
Frequently asked questions. Answered.
Six free Claude Skills covering the analytics job: anomaly detection, benchmark comparison, cohort tracking, KPI dashboard design, growth lever prioritization, and customer research synthesis. Install with npx skills add sidchaudhary/gtm-skills.
