Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account. Use this to design or fix signup and onboarding, diagnose why signups do not convert to active use, reduce time-to-value, or decide what a new user must accomplish first.
npx skills add https://github.com/cbrock84/headcount --skill activation
Acquisition spend is wasted downstream of a weak activation. This is usually the cheapest place to
improve revenue and the least worked on.
Name the specific thing a new user does that predicts they will stay — not "logged in twice," but
the action that delivers the value they came for. Find it in the data: compare what retained users
did in week one against what churned users did.
Everything in onboarding exists to get people to that moment faster. Without it defined, onboarding
becomes a feature tour.
Every field costs conversion, and each one must earn its place. Ask for what is needed to deliver
value now; collect the rest later, in context, when the reason is obvious.
people leave.
The goal is the first real outcome, not a completed tour.
is the moment it becomes real.
differs from the assumed one.
least designed.
Checklists work when the items lead to real value and the list can be dismissed. They fail when they
are busywork.
Instrument each step and find the largest drop. Then watch session recordings of people who dropped
there — the quantitative data says where, and only observation says why.
Common causes, in rough order: asked for too much too early, value not visible before effort
required, an empty product with no path out of it, and a required integration nobody has permissions
for.
Percentage reaching the activation moment, and time to reach it. Signup conversion alone will
happily improve while activation falls.
Take cbrock84/activation from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.