What problem does it solve? Non-trivial code changes often ship without a credible way to prove they work, leaving teams guessing whether a feature, bug fix, or refactor actually behaves as claimed. This Skill structures the upfront thinking needed to connect a behavioral claim to concrete, project-specific evidence before implementation begins. ## Core Features & Use Cases - Evidence Path Design: Derives verification routes from the system itself—controllable inputs, observable effects, state transitions, invariants, and boundaries—rather than defaulting to familiar techniques. - Verification Affordances: Guides creation of minimal capabilities that make relevant state controllable, observable, repeatable, and diagnosable when existing surfaces are too indirect. - Verification Budgeting: Assigns one owner per distinct claim and selects the minimum non-duplicative evidence covering claims and boundaries. - Use Case: Before refactoring a cross-system payment flow, use this Skill to frame the behavioral claim, design an evidence path with a fallback alternative, and close the loop after implementation by reporting what was established versus what remains uncertain. ## Quick Start Ask the agent to build a verification plan for the upcoming feature or bug fix, framing the claim and designing an evidence path before writing any code.
