0trm
UserProduct data science as agent skills: route question to the right method, run checks before shipping.
Categories
Indexed Skills (3)
routing-questions
Routes an incoming product question to the method it deserves before any analysis starts. Checks what the team already knows, whether the metric can be trusted, whether the question is description or causation, whether the decision is made once or continuously, and who assigned the treatment. Use when a product, analytics, or experimentation request first arrives, when someone asks for a deep dive or a dashboard, or before opening a query editor on any question about impact, lift, or whether something worked.
defining-metrics
Turns a metric name into a computation, a source of truth, a registry entry, and a written statement of how it will be gamed, then decides whether it is trustworthy enough to promote. Use when defining a north-star or guardrail metric, when two dashboards disagree on the same number, when arbitrating between conflicting metric definitions, or when a readout depends on a metric nobody has validated.
writing-readouts
Writes an experiment or analysis readout with the decision rule first and the result last, converts the finding into a durable belief rather than a number, and files both the knowledge-repo entry and the prior-store record before the ticket closes. Use when a test finishes, when documenting a shipped or killed decision, when writing up a null result or a rollback, or when a question needs an entry someone can find in a year.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.