What problem does it solve? React codebases accumulate subtle bugs, performance regressions, accessibility gaps, and security risks that static scanners flag without judgment. This Skill turns React Doctor scan output into a senior-engineer audit: it vets which findings actually matter, prioritizes them by user impact, and writes implementation plans precise enough for any agent or cheaper model to execute without further judgment calls. ## Core Features & Use Cases - Evidence-based audit: Runs React Doctor read-only as JSON, then audits across five categories (bugs & correctness, performance, accessibility, security, maintainability) with parallel subagents. - Leverage-driven prioritization: Severity is judged by hot-path impact, not raw rule severity, and findings are confirmed at their exact file:line before being reported. - Self-contained plans: Each plan inlines the current code, the exact target fix pulled from the canonical per-rule prompt at react.doctor, repo conventions, boundaries, and verification steps including React DevTools Profiler checks. - Use Case: Ask it to audit a Next.js app before a release; it produces a vetted findings table plus a plans/ directory of numbered, commit-stamped plans that a cheaper executor agent can implement one by one. ## Quick Start Ask the assistant to audit this React codebase and produce prioritized improvement plans using the improve-react skill.
