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 verification planning so every change has a concrete, project-specific evidence path before implementation begins. ## Core Features & Use Cases - Evidence Path Design: Frames the claim being made, derives candidate evidence paths from the system's inputs, outputs, state transitions, and boundaries, then selects a proportionate path with known limitations. - Verification Affordances: Defines the smallest capability needed to make behavior controllable, observable, repeatable, and diagnosable when the existing system cannot reveal the truth directly. - Verification Budgeting: Assigns one owner per distinct claim and chooses the minimum non-duplicative evidence covering claims and important boundaries. - Use Case: Before refactoring a payment retry flow, use this Skill to define the claim (retries are idempotent), design a repeatable test scenario from a known state, and close the loop by interpreting the resulting evidence after implementation. ## Quick Start Ask the agent to build a verification plan for the upcoming feature or bug fix before writing any implementation code.
