This skill triages a list of assumptions. Each one is scored on impact (value created and number of customers affected) and risk, defined as (1 - confidence) x effort, then placed into one of four outcomes: defer, proceed, reject or test.
For the assumptions that need testing, the agent proposes an experiment that measures real behavior, with a clear success metric and threshold. The result is a prioritized matrix or table.
What You Get
- Impact and risk scores for every assumption
- A decision for each: defer, proceed to implementation, reject or test
- An experiment design for each high-impact, high-risk assumption
- A prioritized matrix or table, saved as markdown when substantial
Common Use Cases
- Choosing what to test first after an assumption-mapping session
- Cutting a long list of risks down to the few that need experiments
- Documenting why some ideas were rejected or deferred
What Makes It Unique
It turns the assumption prioritization canvas into four explicit decisions, so low-impact high-risk ideas are rejected and high-impact low-risk ones go straight to build. Experiments are required to measure actual behavior and carry a success threshold.
Under The Hood
The skill is a prompt only, with no scripts. It tells the agent to read any assumption lists or research files the user provides and to save substantial output as markdown. It refers to the prioritization-frameworks skill for formulas. It makes no web or API calls and runs no commands.