About this template
"Ship the pricing page" has vanished from your plan four weeks running
Nobody noticed. Meanwhile the fifteen-metric dashboard was green somewhere and red somewhere, no decision followed, and by month two it was a ritual nobody read.
The first section isn't a metric
It's last week's intentions, scored — done, not done, or abandoned, with a running streak count.
Ship pricing page — abandoned, 4 weeks running.
That line is worth more than anything else on the page, and no dashboard surfaces it. An intention quietly dropped three weeks running is a signal about capacity or conviction.
Three numbers, not a dashboard
A review reporting fifteen metrics reports none. So: exactly three.
- Your constraint metric — the one thing currently limiting growth. It asks what that actually is rather than assuming revenue; for most early businesses it's distribution or activation, and defaulting to revenue is how founders optimise the number furthest from what's blocking them.
- Cash — runway in months and the direction it moved.
- The leading indicator — the thing that moves before the constraint does.
Anything else goes in an appendix below the decision, so it can't displace it.
One decision, phrased as a question
"Onboarding completion fell to 41% — do we fix the flow, or change who we let in?"
Not "consider improving onboarding". And when the data supports no decision, it says
no decision needed — keep executing. That refusal is what keeps the review worth
reading in month three — a review that manufactures an action item every week trains
you to ignore it.
Every figure is sourced
No estimating, no carrying last week's number forward, no filling a row so the table
looks complete. Missing metrics show as [MISSING: source] with the decision each
one blocks — which is what actually gets them supplied next week.
What you supply
Your own Claude Code login, plus whatever you track in ~/weekly/exports/ — revenue,
signups, bank balance, pipeline.
Keep past reviews in ~/weekly/reviews/. The intentions loop only closes if last
week's file is there; the first run has nothing to score and says so.
No integrations. Exports are the input, which is also why nothing can be sent.
Where this stops
It drafts. It does not email the review, post it, or commit you to anything in it — next week's intentions are labelled proposals.
It won't read two moving lines as causation, won't forecast from three data points, won't tell you the week was "good" (it compares to intent and lets you judge), and has no industry benchmarks.
Verified on build: the skill, the working tree, both guards, the three-numbers rule, the abandonment tracking and the one-decision rule are present on a fresh fork. Running it on your own week is yours to do.