Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides a structured approach to designing and implementing product interfaces within existing codebases or new prototypes. It focuses on creating intentional visual hierarchies and responsive states for pages, dashboards, and mobile-shaped web experiences.
Frontend engineers can use these guidelines to refine interaction design, manage empty and loading states, and ensure that UI components remain polished and coherent across a design system.
WHO IT'S FOR
Frontend engineers
building production React web applications
Mobile app developers
shipping React Native apps for iOS and Android
Product designers
implementing deliberate and polished product interfaces
Full-stack developers
prototyping cross-platform web and mobile experiences
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Use the review-interface skill in quick mode to review the primary path of [screen or flow]. Inspect [source path or preview URL], report only evidence-backed high- and medium-impact findings, cap the review at five findings, and do not implement fixes. Clearly state any screens or states you could not inspect.
Use the review-react skill to perform a read-only review of [component, hook, diff, or route path]. Examine enough call sites, types, and tests to substantiate findings, prioritize user-visible correctness and React rule violations, and report only demonstrated issues without implementing fixes.
A specific change, branch, file set, feature, or architecture to review
Relevant repository evidence
Use the review-security skill to conduct a read-only security review of [change, branch, files, feature, or architecture]. Report only reachable, material risks supported by a concrete influence, path, control failure, impact, and scope; omit speculative candidates and do not implement fixes or run intrusive tests.