Analytics Strategy Creator
A Claude skill that turns a fuzzy "I want to understand X" into a tight, decision-driven analytics strategy - five-or-fewer primary metrics paired with counter-metrics, segmentation, and instrumentation notes. Outputs a markdown doc you can hand to your PM, eng team, or data person. Free to download, free to use.
What's inside
- Pins down the specific decision before recommending any metric
- Researches your product directly from its URL
- Picks 3–5 primary metrics - each paired with a counter-metric and segmentation
- Calls out the vanity metrics worth explicitly skipping
- Chains naturally into the Event Tracking Plan Generator for full instrumentation
- Free - runs entirely inside Claude Pro / Max / Team
Format: Claude Skill (.skill)
Get the Analytics Strategy Creator
Enter your email and we'll start the download immediately.
What is an analytics strategy?
An analytics strategy is a short document that names the specific decision you're trying to make, then picks the few metrics that actually inform it. It's the thing you write before you build a dashboard, set up tracking, or argue about KPIs - so you don't spend the next quarter staring at numbers that don't change anyone's mind.
A good strategy answers four questions:
- What's the decision? (e.g., “invest in onboarding redesign vs. paid acquisition”)
- What 3–5 metrics inform it? (paired with counter-metrics to catch gaming)
- How do we segment each metric? (e.g.,
traffic_source,plan_tier,new_vs_returning) - Which vanity metrics do we explicitly skip? (named, not generic)
Without a strategy, you end up with a 30-metric dashboard nobody looks at, instrumentation work that doesn't map to any decision, and a team that argues about gut feel because the data doesn't resolve anything. A 30-metric dashboard is not a strategy; it's a graveyard.
Why founders skip analytics strategy (and pay for it later)
Most early-stage founders skip the strategy step and jump straight to “let's set up Mixpanel.” Six months in, they have:
- A dashboard with
DAU,MAU,signups, andpage_views- none of which change what they ship next - Metrics that go up while the business goes sideways (no counter-metric to catch it)
- Aggregate numbers that hide the segment where the real problem lives
- Tracking debt built on top of a strategy that was never written down
By the time you realize the numbers aren't actually helping you decide anything, you've already shipped a dashboard the team doesn't trust - and you're back to gut feel.
What this tool does
Once installed in Claude, you tell it the decision you're trying to make and give it your product URL. Then Claude:
- 01Pins down the specific decision before recommending any metric - and pushes back firmly if you answer with a vanity count or a vague category
- 02Researches your product by fetching your marketing site and relevant sub-pages so it understands what you actually do
- 03Asks a few sharp questions about stage, business model, and existing instrumentation
- 04Picks 3–5 primary metrics, each paired with a counter-metric and segmentation dimensions - and names the vanity metrics you're explicitly skipping
- 05Outputs a markdown strategy doc you can hand to your PM, eng team, or data person
What you get
A markdown strategy doc with these sections, ready to share or paste into Notion / Linear / your wiki of choice:
| Section | Description |
|---|---|
| The decision this informs | 1–2 sentences naming the concrete action this strategy enables |
| Product context | One paragraph so any reader can understand what the product does |
| Primary metrics | 3–5 metrics, each with counter-metric, segmentation, computation, cadence, and "what good looks like" |
| Vanity metrics skipped | 2–4 tempting-but-not-useful metrics named explicitly, with a one-line reason |
| Instrumentation notes | Engineer-readable event + property list mapped to the primary metrics |
| What to check first | 2–3 concrete first actions to take this week |
| When to revisit | Specific triggers and cadence for refreshing the strategy |
The doc is intentionally short - roughly 1–2 printed pages. If you want full instrumentation specs to hand to engineering, the output chains naturally into the Event Tracking Plan Generator.
Installation
Steps:
- 01Download the
.skillfile from this page - 02Open Claude → Settings → Capabilities → Skills
- 03Click “Upload skill” and select the file
- 04Open a new conversation. The skill activates automatically when you ask Claude what to measure for a product decision.
How to use it
Start a new chat and say something like:
“I want an analytics strategy for https://app.yourproduct.com - I'm trying to decide [the specific decision].”Claude will then walk you through four short steps:
- 01Decision first - Claude pins down the specific decision you're making. If you answer with a vanity count (“I want to track DAU”) or a vague category (“engagement”), it'll push back until you have a real decision. The single test: what would you do differently if the metric is good vs bad?
- 02Product context - share your URL and a few sentences on what the product does, who uses it, and the core action. Claude fetches your site to fill in the rest, then recaps so you can correct anything off.
- 03Business context - stage (pre-PMF / early growth / scale), existing instrumentation (
nothing yet/GA4/Mixpanel / PostHog / Amplitude/ full stack), and anything else worth knowing. - 04Scope recap - Claude confirms the decision, product, stage, and stack before writing. Then it produces the markdown strategy doc.
The whole run typically takes 10–20 minutes, depending on how sharp your decision is going in. The markdown doc is delivered at the end - short, opinionated, and ready to share.
Analytics strategy vs tracking plan: what's the difference?
| Analytics strategy | Event tracking plan | |
|---|---|---|
| Answers | What should we measure, and why? | What events do we fire, and with what properties? |
| Written | Before instrumentation | After the strategy, before implementation |
| Output | Markdown doc: decision, 3–5 metrics, counter-metrics, segmentation | CSV: event names, properties, types, triggers |
| Audience | Founder, PM, whoever owns the decision | Engineers implementing tracking |
| Tool | This one | Event Tracking Plan Generator |
Do them in that order. A tracking plan without a strategy is instrumentation that maps to no decision.
Questions
What is an analytics strategy?
A short document that names the specific decision you are trying to make, then picks the few metrics that actually inform it. You write it before you build a dashboard or set up tracking.
How is it different from a tracking plan?
The strategy decides what to measure and why; the tracking plan specs which events fire and with what properties. Strategy first, then plan.
What is a counter-metric?
The number you watch to catch your primary metric being gamed. Push signups and you can wreck signup quality - the counter-metric is what catches it. Every primary metric in the strategy is paired with one.
What do I need to run it?
A Claude Pro, Max or Team account - skills aren't available on the free plan. Nothing else.
How long does it take?
A run typically takes 10 to 20 minutes, depending on how sharp your decision is going in.
What if I already have metrics defined?
Run it anyway and compare. The common failure it catches isn't a missing metric - it's a metric with no counter-metric, or a set of metrics that don't map to any decision you're about to make.
Want a custom tool?
Tell us about your analytics workflow and we'll build a custom tool tailored to your team.