What problem does it solve? After finishing a feature or fix, developers often report work as done based only on unit tests or code review, missing bugs that only appear for real users. This Skill enforces a verification loop that runs the relevant TestSprite tests through the testsprite CLI against the actual change before declaring completion. ## Core Features & Use Cases - Mandatory verification loop: Requires at least one TestSprite run to a terminal verdict (passed/failed/blocked/inconclusive) for every shipped feature, with a narrow skip list for docs-only and config-only edits. - Test authoring guidance: Drafts frontend plan.json files with reliable planSteps wording rules, or backend Python assertion scripts using injected credentials and dependency declarations (--produces/--needs). - Failure triage: Distinguishes plan-quality problems from real product bugs by inspecting step traces, and downloads failure artifact bundles for root-cause analysis. - Use Case: After fixing a checkout coupon bug in a web app, run the existing TestSprite checkout test against the deployed preview URL with --wait, confirm it passes, and report the verdict with the dashboard link. ## Quick Start Verify my just-finished checkout fix by running the relevant TestSprite test against the deployed preview URL and tell me the verdict.