Explore

Use when reviewing image assets, markup, and CDN or build transforms related to Serve images at the correct display size. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Use when reviewing article images, cards, galleries, or any component rendered at multiple sizes across breakpoints. Check both the markup and the CSS layout because an incorrect `sizes` attribute can negate a perfectly good `srcset`.

Use when auditing slow page loads, heavy assets, or rendering delays related to Use resource hints for faster loading. 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 a CSS reset or normalize stylesheet. Check the rendered layout across breakpoints and interaction states before proposing a fix.

Use when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Use when reviewing HTTP response headers for privacy hardening on any website that handles authentication, session state, or sensitive URL parameters.

Use when reviewing any process that spans multiple screens, steps, or modal stages. Follow the real user journey and compare fields across steps instead of reviewing screens in isolation.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Respect reduced motion preferences. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when auditing internal link structure after a URL migration, domain change, or site rebuild. Applies to any site that has had redirects in place for more than a month.

Use when auditing site redirects after URL migrations, domain changes, or CMS upgrades. Applies to any site that has had multiple rounds of structural changes over time.

Use when reviewing content pages for user experience and SEO. Applies to blog posts, landing pages, how-to guides, and any long-form content intended for a broad audience.

Use when evaluating content pages for SEO quality. Applies to blog posts, product descriptions, landing pages, or any page expected to receive organic search traffic.

Use when auditing PWA readiness, adding an install prompt, or preparing a web app for submission to Microsoft Store or Google Play via PWA Builder.

Use when reviewing image assets, markup, and CDN or build transforms related to Use progressive JPEG encoding. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Use when auditing e-commerce product pages or implementing structured data for a shop. Applies to any page selling or describing a specific product.

Use when auditing slow page loads, heavy assets, or rendering delays related to Use preconnect for critical third-party origins. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Use when reviewing string concatenation involving counts, translation key lookups, or i18n library configurations to check whether plural forms are handled correctly for all target locales.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Write in plain language. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when auditing local business websites, e-commerce sites, or any site where a physical presence affects trust or local search visibility.

Use when reviewing HTTP response headers for defense-in-depth security hardening on any web application.

Use when auditing slow page loads, heavy assets, or rendering delays related to Use resource hints for faster loading. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Use when reviewing CI configuration, bundle analysis workflows, or pull requests that add dependencies and assets. Distinguish bundle-size budgets from runtime budgets such as Lighthouse or Core Web Vitals so teams can enforce both.

Use when auditing a site that publishes downloadable PDFs (reports, white papers, legal documents, manuals). Applies to any site where PDFs are linked as indexable content resources.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Allow pasting into form inputs. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when reviewing headers, forms, cookies, or third-party integrations related to Secure password input fields. Validate the effective browser and HTTP behavior in a production-like environment.

Use when auditing URL structure or configuring search engine handling of filtered, sorted, or tracked URLs. Applies to e-commerce sites, filtered content directories, and any site appending tracking or session parameters.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Provide alternatives to parallax effects. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when reviewing templates, rendered HTML, or shared components related to Make pagination accessible. Validate the final browser-facing markup, not just the source framework abstraction.

Use when auditing paginated content (blog archives, product category pages, search results). Applies to any site with lists or grids of content split across multiple pages.

Use when auditing slow page loads, heavy assets, or rendering delays related to Keep page weight under 1500KB. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Use when auditing slow page loads, heavy assets, or rendering delays related to Keep page load time under 3 seconds. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Use when auditing site architecture or investigating why specific pages have low organic traffic despite good content. Applies to any site with more than ~20 pages.

Use when reviewing mobile-first layouts, tablet experiences, fullscreen flows, forms, dashboards, or media interfaces. Check rendered behavior in both portrait and landscape and separate genuine layout constraints from unnecessary orientation assumptions.

Use when auditing structured data on a business or brand website homepage. Applies to organisations, companies, non-profits, and publishers that want accurate Knowledge Panel information in Google Search.

Use when reviewing image assets, markup, and CDN or build transforms related to Optimise images for faster loading. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Use when auditing Open Graph tags or investigating why social share counts appear low. Applies to any page with both canonical-url and og:url tags.

Use when auditing a web page's social sharing metadata. Applies to any page users might share on social networks or messaging apps.

Use when auditing Open Graph tags or generating og:image assets. Applies to any page that may be shared on social networks or messaging platforms.

Use when reviewing image assets, markup, and CDN or build transforms related to Lazy load offscreen images. Check encoded size, rendered size, loading strategy, and above-the-fold impact together. Missing `loading='lazy'` is only a valid finding when you can reasonably tell the image is offscreen or non-critical.

Use when adding PWA capabilities, implementing a service worker, or improving the experience for users on unreliable network connections.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Provide alternative text for objects. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when auditing robots meta tags. Applies to any important landing page, article, or product page that should appear with a description in search results.

Use when reviewing templates, rendered HTML, or shared components related to Provide noscript fallback content. Validate the final browser-facing markup, not just the source framework abstraction.

Use when auditing an XML sitemap or diagnosing indexing issues. Applies to any site where noindex meta tags or X-Robots-Tag headers may be applied to URLs also listed in the sitemap.

Use when auditing internal link structure or reviewing link attributes. Applies to any site using rel=nofollow on links pointing to pages within the same domain.

Use when auditing tsconfig.json for missing safety flags, reviewing code that uses array index access in data processing pipelines, or investigating runtime undefined errors that TypeScript did not catch.

Use when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for @typescript-eslint/no-explicit-any.

Use when reviewing HTML or JSX for anchor elements with target='_blank' to verify rel='noopener noreferrer' is present.

Use when reviewing templates, rendered HTML, or shared components related to Use navigation landmark regions. Validate the final browser-facing markup, not just the source framework abstraction.

Use when auditing a local business website for local SEO. Applies to any business that has a physical address and wants to appear in local search results or Google Maps.

Use when reviewing stylesheets, component styles, and responsive behavior related to Use consistent CSS naming conventions. Check the rendered layout across breakpoints and interaction states before proposing a fix.

Use when evaluating test quality on modules containing business logic, calculation utilities, or state machines to determine whether the tests provide genuine defect detection.

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.

Run Semgrep static analysis across a codebase, optionally using Semgrep Pro for cross-file taint analysis. Use when Semgrep or a static-analysis scan is requested; use security-review for a manual audit.

Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging. This is NOT a general code review.

Rewrite AI-generated copy in Spanish and English so it sounds direct, concrete and human while preserving meaning, facts and numbers exactly. Use when drafts feel robotic, verbose or translated and need short active sentences without em-dashes.

Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.

Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.

Use when publishing a Butterbase app as a public template (visibility + listed + repo snapshot), browsing the template gallery, or cloning a template with environment-variable preflight. Templates are public apps with a pushed repo snapshot that other users can fork into their own region.

Use when designing database schemas, creating or modifying tables, choosing column types, adding indexes, or working with the Butterbase declarative schema DSL