Set Baseline
A Claude skill that connects to your Databox workspace via MCP and establishes an honest reference point for a metric before you run a campaign or make a change. You pick the data source and name the metric; it pulls the metric's real monthly history, reads its seasonal pattern, and states the baseline as a band — a typical low–high range adjusted for the season.
- ~5 minutes setup
- Runs on demand
- Claude + Databox MCP
- Works with
- Claude
- Requires
- Databox account + Databox MCP
- Data source
- Any source
- Output
- HTML report
- Best for
- Growth teams, agencies, founders
- Setup time
- ~5 minutes
What it does
Most teams judge a campaign or a change against last month. But “last month” is not a baseline — if the metric has any seasonal shape, comparing against a single recent period manufactures false wins and false alarms. A retailer’s December flatters January; a B2B metric’s August understates the year’s normal.
This skill sets an honest reference instead. After the connection check, you pick which connected data source(s) to look at and type the metric you want a baseline for; if the name doesn’t resolve cleanly it shows you the real metric keys to choose from. It then pulls that metric’s monthly history from Databox — ideally 13+ months so a full year-over-year pattern is visible — and reads the seasonal cycle: the recurring peaks and troughs, where the upcoming window sits in that cycle.
From that it sets the baseline as a band, not a number: a typical low–high range adjusted for the season, with the periods that fed it, the seasonal adjustment applied, and a confidence level shown (high with a full history and a clear pattern; provisional when history is thin). Every figure traces to a real Databox metric — it never fabricates a trend to fill a gap, and if the history is too short it says so and labels the baseline provisional.
The deliverable is a self-contained HTML report: per source, the metric’s history charted with the baseline band shaded over it, the band range and central tendency, the seasonality read, and a plain-English note on how to judge a future result against it — a result inside the band is normal, one clearly outside is a genuine signal. Pick multiple sources and each is baselined separately; two sources are never flattened into one band.
No AI hallucinations. Analysis built on a real context layer.
Ask a generic AI to analyse your business performance and it will give you a confident answer. It will also be working from assumptions.
Generic AI doesn't know how your business defines a qualified lead, what your MRR calculation includes, or how you attribute revenue. It fills those gaps with the most plausible interpretation it can find — which is different from the correct one.
The products here run on Databox's data layer — if you choose so. Your metric definitions, your reporting logic, and your live numbers are what the AI reads, pulled straight through Databox MCP instead of uploaded by hand. That's the difference between an output you can share with your team and one you have to verify before you trust it.
Who it's for
What's in the package
Security scanned Reviewed by DataboxHow to use it
Example prompts you can ask Claude
What you need to run this
Claude
Free to download. Required to install and run skills.
Databox account
The skill connects to your data in Databox. The free plan includes all integrations you need to use this skill.
MCP connection
Connector inside your Claude. Takes less than a minute to set up. Full instructions in the setup guide included in the download.
Free to start. Connect your first integration in minutes — no credit card required.
Connect any AI tool to your Databox data with Databox MCP.
Databox MCP is the bridge between your live metrics and any AI — Claude, ChatGPT, Cursor, or any client that speaks MCP. One auth, every workspace, no scraping.
Example output
Common questions
What does Set Baseline do?
It connects to your Databox workspace through MCP and sets an honest, seasonality-aware baseline for a metric before a campaign or change. You pick the data source and metric; it pulls the metric's real history, reads its seasonal pattern, and outputs a typical low–high band with a confidence level as an HTML report — so a later result is judged against a fair reference instead of a misleading last-month number.
What data does it need?
A Databox account with the source whose metric you want to baseline connected (it's data-source-agnostic — GA4, Google Ads, Shopify, Meta, or any other), read through the Databox MCP. It works best with 13+ months of history so a year-over-year seasonal pattern is visible; with less, it still produces a baseline but labels it provisional.
Why a band instead of a single number?
Because a single figure presented as "normal" hides seasonality and manufactures false wins and alarms. A band states a typical range with its confidence, adjusted for where the upcoming window sits in the seasonal cycle — so a result inside the band is normal and one clearly outside it is a real signal.
Do I need a Databox account to use this skill?
Yes, ideally — and here's why it matters. Point a generic AI at a raw data export and it has to guess what your numbers mean: which conversions count, how you define an engaged session, what a "normal" week looks like. It fills those gaps with the most plausible interpretation it can find, which is often not the correct one. The skill avoids that by reading your data live from Databox through MCP, where your metrics are already standardized — one consistent definition for sessions, engagement, and conversions across your setup. The AI reads what's actually true for your business instead of inferring it, so the report is one you can trust rather than verify. You can technically run it against data you've pasted in by hand, but you lose that context layer and the output is only as reliable as the export. If you don't have an account or data source connected yet, the skill walks you through the setup.
Can I use this with the free Databox plan?
Yes — the free Databox plan includes the integration this skill needs, so you can run it at no cost. The skill itself is also free to download.
Does this use live data from my connected source?
Yes — every run reads your live data directly from Databox through the MCP connection. The report reflects your current data at the moment you run it, not a cached or uploaded snapshot.
Do I need to export data manually?
No — there are no CSV exports and no copy-paste. The skill pulls your data straight from Databox through MCP each time it runs, so the report is always built from your live source.
Can agencies run this for multiple clients?
Yes — run it against each client's data connected in Databox, one account at a time, and you get the same structured weekly brief for every client. It's built to give a consistent report you can take to each client review.
Can I customize the report?
Yes. Before it runs, the skill asks a few onboarding questions — what you want to measure, the time frame, and any context that matters for the analysis — so the report is shaped to your goals from the start. After a run, you can give it feedback to adjust focus, sections, or anomaly thresholds, and reinstall the updated version so your changes carry into future runs.
Morning Marketing Summary
Pulls live data from all connected marketing channels via Databox and delivers a performance brief to Slack/email
Content Performance Partner
Every published page sorted into keep, refresh, or retire — a prioritized monthly editorial work queue written from live
Sales Pulse
Pipeline analysis before charts. Reads your CRM through Databox and tells you what's healthy, what's slipping, and where
-
-
-
- +1
