Show HN: Crit – Visual QA for iOS apps and AI coding agents (natethegreat.github.io)

Crit is a new tool designed for improving iOS app development by enabling visual quality assurance (QA) through structured feedback for coding agents. By capturing screenshots from the iOS Simulator on macOS, users can easily pinpoint issues within the app interface and compile detailed feedback in a structured JSON format. This streamlined process allows developers to efficiently communicate problems with popular coding agents like Claude Code, Codex, Gemini, and Cursor, enhancing the coding workflow without any plugins or vendor lock-in. Users can initiate the feedback cycle with simple commands, and all data is saved in the project's .crit/ directory. This announcement is significant for the AI/ML community as it showcases innovation in integrating visual QA with coding agents, thereby facilitating more intelligent and responsive app development. The tool's dependency-free design enhances accessibility for developers, while its ability to work with any agent capable of processing images and JSON further broadens its applicability. Although currently limited to iOS apps, the potential for future Android support indicates a strategic direction for expanding its use in cross-platform development environments.