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 actually runs TestSprite tests against the 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) before any feature is reported done. - Flexible test sourcing: Runs an existing test that covers the change, creates a new frontend plan or backend Python assertion test, or batches multiple frontend plans for coverage sets. - Failure triage: Distinguishes plan-quality problems from real product bugs, downloads failure artifacts, and reports root-cause hypotheses without auto-fixing. - Use Case: You just modified a checkout component in a TestSprite-wired repo. The Skill finds or drafts a matching frontend plan, runs it via testsprite test run --wait against the deployed preview URL, inspects the result, and reports the verdict with a dashboard link. ## Quick Start Verify my just-finished feature by running the relevant TestSprite test against the deployed preview URL and tell me the verdict.