Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when auditing public documentation portals, API references, help centers, SDK docs, or large knowledge bases. Check the final file served at `/llms.txt` and verify that the linked pages are stable, high-value, and accessible without relying on a JavaScript-only interface.
Use when auditing slow page loads, heavy assets, or rendering delays related to Show loading indicators. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.
Use when reviewing stylesheets, component styles, and responsive behavior related to Use CSS logical properties for i18n and RTL support. Check the rendered layout across breakpoints and interaction states before proposing a fix.
Use when reviewing scripts, client components, bundles, or runtime behavior related to Prevent common memory leak patterns. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.
Use when auditing HTML document structure. Applies to any page where meta tags (noindex, canonical-url, description, viewport, OG tags) may have been injected into the body by CMS plugins, widgets, or JavaScript rendering.
Use when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid meta refresh redirects. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
Use when reviewing CI coverage, automated checks, or test strategy related to Test on real mobile devices and viewports. Focus on whether the rule is continuously verified, not just documented.
Use when reviewing CI coverage, automated checks, or test strategy related to Follow mocking best practices. Focus on whether the rule is continuously verified, not just documented.
Use when reviewing image assets, markup, and CDN or build transforms related to Use modern image formats (WebP, AVIF). Check encoded size, rendered size, loading strategy, and above-the-fold impact together.
Use when evaluating test quality on modules containing business logic, calculation utilities, or state machines to determine whether the tests provide genuine defect detection.