Localization Readiness Auditor
Audit an application or feature for localization readiness across extracted messages, interpolation, pluralization, date and number formatting, layout expansion, right-to-left behavior, sorting, search, assets, metadata, and test coverage. Use before adding a locale, reviewing hard-coded UI text, or investigating a feature that breaks outside English.
npx agentscamp add skills/localization-readiness-auditorInstall to ~/.claude/skills/localization-readiness-auditor/SKILL.md
Audits internationalization foundations before translation: message extraction and context, plural and select rules, locale-aware dates and numbers, Unicode input, text expansion, bidirectional layout, sorting and search, localized assets and metadata, fallback behavior, and pseudolocale coverage. It reports concrete blockers by user journey.
Find assumptions that make a feature work only for one language or region.
Workflow
- Define target surfaces. Identify platforms, routes, components, notifications, documents, emails, metadata, accessibility labels, server messages, and locales or writing systems in scope.
- Inventory user-facing text. Find hard-coded strings, concatenation, duplicated messages, image text, backend-provided prose, placeholders, and strings assembled from fragments. Preserve translator context and stable identifiers.
- Check message grammar. Verify interpolation, plural and select rules, gender or grammatical variants where required, markup handling, escaping, and full-sentence translation. Avoid English word-order assumptions.
- Inspect locale-aware data. Review date, time, timezone, calendar, number, currency, percentage, address, name, phone, unit, collation, and case conversion behavior. Keep storage formats separate from presentation.
- Test input and text processing. Exercise Unicode, composed and decomposed characters, non-Latin scripts, emoji, long names, input methods, normalization, validation, truncation, search, slugs, exports, and round trips.
- Stress layout. Use a lengthened pseudolocale and narrow viewport to find fixed widths, clipping, overlapping controls, unsafe truncation, and text embedded in graphics. Verify zoom and dynamic type where supported.
- Inspect bidirectional behavior. Test RTL direction, mirroring, mixed-direction text, icons with directional meaning, number and code isolation, focus order, gestures, and charts. Do not mirror brand marks or inherently fixed symbols.
- Review loading and fallback. Check locale detection, explicit user choice, routing, bundle loading, fallback chains, missing-key telemetry, cached variation, server-client consistency, and SEO metadata.
- Define regression coverage. Add or recommend pseudolocale builds, missing-key checks, representative locale tests, screenshots for critical layouts, and format assertions that avoid machine-specific locale defaults.
WARNING
Translating visible strings does not make a feature localized if dates, plural rules, layout, search, validation, or screen-reader labels still assume English.
Output
Report the audited surfaces and locales, blockers by user journey, hard-coded and structurally unsafe messages, formatting and Unicode defects, layout and RTL findings, fallback gaps, test recommendations, and evidence locations. Separate product copy questions from technical defects.
Frequently asked questions
- What is the difference between internationalization and localization?
- Internationalization prepares software to support languages and regional conventions; localization supplies translated content and locale-specific assets or rules. This skill audits the technical readiness needed before localization succeeds.
- Why use a pseudolocale?
- A pseudolocale expands and decorates text while preserving automation, revealing hard-coded strings, clipping, concatenation, and layout assumptions before real translations are available.
Related
- 9 Best Claude Skills for Frontend DevelopmentCompare Claude skills for accessibility, Web Vitals, React renders, bundles, localization, browser security, test data, tests, and caching.
- Accessibility Regression AuditorAudit a UI change for accessibility regressions by combining automated checks with keyboard, focus, semantic, name-role-value, contrast, zoom, and screen-reader-oriented inspection. Use when reviewing a component or pull request, adding a dialog or form, changing navigation, or investigating an accessibility failure that a linter alone cannot explain.
- Frontend DeveloperUse this agent to build UI — responsive layouts, components, accessibility, and design-system work. Examples — implementing a Figma design, fixing a11y issues, building a reusable component.
- Mobile DeveloperUse this agent to build cross-platform mobile apps with React Native + Expo — screens, navigation, native modules, and shipping via EAS. Examples — adding a tab-based navigation flow, fixing a janky FlatList, shipping a build to TestFlight with EAS.
- Test ScaffolderScaffold a test file with sensible cases for a given module or function. Use when adding tests to untested code and you want a fast, structured starting point.
- Architecture Diagram GeneratorGenerate accurate architecture diagrams as Mermaid — straight from the codebase, not from imagination — by first choosing which view answers the question (container/component, sequence, ER, or state) and then reading the real entry points, module boundaries, service calls, and schema. Use when onboarding to an unfamiliar repo, documenting a system, or visualizing one complex flow.