Open source · MIT

Skills that make
your coding agent think
like a product data scientist.

They decide if a question deserves an analysis, pick the method, and check the result before shipping.

Read the method map→
Knowledge layer the ceiling: what each decision taught, and the prior it left writing-reports Measurement framework the floor: the definition of success, and whether the number can be trusted defining-metrics Routing routing-questions one decision, one lookup, three questions, one gate Exploratory analytics forming-hypotheses the question, localised and sized can you randomise? Experimentation designing-experiments reading-experiments Causal inference choosing-causal-designs Statistical modeling building-models the decision, made at volume yes no description hypothesis

Scroll sideways

Eight skills, six positions

A skill is a decision procedure your agent runs with you: the questions in order, the checks that have to pass, and the exit that says this one cannot be answered.

Every name on the map is a link. Causation carries three skills; each other position carries one.

Browse the skills→

See it route

routing-questions

> did the new onboarding lift D7 retention?

decisionwho decides what?onboarding PM: keep or revert
lookupknowledge layer2 prior tests on d7_retention, none on onboarding
gatetrust the metric?d7_retention, registered, one source of truth
q1description, forecast or change?a change
q2once or continuously?once, a ship-or-kill call
q3who assigned it?you: a 50/50 flag, live since 04‑08

-> reading-experiments

srm · exposure log · sequential bound · cuped · shrinkage

> how much does a paywall test usually move trial starts?

decisionwho decides what?growth lead: run the next test?
lookupknowledge layertrial_starts: 6 entries, median +0.9pp, none expired

-> settled

the store already answers it. no query, no traffic, no ticket.

> is activation down since the pricing change?

decisionwho decides what?pricing owner: keep or roll back
lookupknowledge layeractivation: no entry, no prior
gatetrust the metric?two dashboards disagree, no owner, no registry entry

-> defining-metrics

the measurement work is the work. not in the meantime.

Run it on your own question

shell
$ git clone https://github.com/0trm/gallop
$ mkdir -p .claude/skills
$ cp -r gallop/skills/* .claude/skills/

Then ask your agent the question you were about to write a query for. Any agent that reads skills can take the directories; install has the one-skill copy.