Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    APP Localization i18n QA Auditor

    2

    Audit app localization files for broken placeholders, ICU plural defects, and UI-breaking expansion issues.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    APP Localization i18n QA Auditor

    APP Localization i18n QA Auditor

    Example session with this skill installed

    Audit these two files for a Flutter app. Source: en.arb, Target: es.arb. Check for broken placeholders and ICU plural issues.

    • Read your context and instructions
    • Compiled the app localization i18n

    I have completed the structural audit of the provided .arb files for your Flutter application. The review identified one blocker related to a missing ICU plural category and two warnings regarding placeholder mismatches.

    Localization QA Report

    Summary

    • Scope: 2 locales (en, es), 45 keys.
    • Verdict: Do not ship. Fix blockers in es.arb.
    • Confidence: High (Structural) / High (Spanish Translation).

    Scorecard

    LocaleKeysErrorsWarningsConfidence
    en4500High
    es4512High

    Blockers and Major Findings

    IDLocaleKeyEvidenceFix
    B01esitemsCountMissing other category in ICU plural.Add other category to handle pluralization.
    W01eswelcomeUserPlaceholder {name} is written as {nombre}.Use original {name} key.

    Fix-ready Corrections

    {
  "itemsCount": "{count, plural, one{1 artículo} other{{count} artículos}}",
  "welcomeUser": "¡Bienvenido, {name}!"
}

    Systemic Issues

    Placeholder naming: Translators are attempting to localize placeholder keys (e.g., {name} to {nombre}). This will cause runtime lookup failures in Flutter.

    Plural Logic: The Spanish translation is missing the mandatory other fallback category required by the ICU specification.

    CI Gate Recommendation
    Run the following check in your CI pipeline to prevent these regressions:
    python3 scripts/i18n_check.py --source l10n/app_en.arb --targets l10n/app_es.arb --fail-on error

    Next steps

    1. Replace the broken keys in app_es.arb with the corrections provided above.
    2. Inform the translation team that placeholder keys inside curly braces must not be translated.
    3. Run a pseudo-localization pass to check for layout overflow in the Spanish UI.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manual localization QA is slow and prone to breaking production UIs. This skill audits translation files to find the structural defects that crash apps or corrupt data before they reach your users.

    What it does

    • Structural auditing identifies missing keys, mismatched placeholders, and unbalanced braces across locales.
    • ICU message validation detects broken plural rules, missing categories, and invalid select syntax.
    • RTL support review flags layout mirroring issues and bidirectional text punctuation errors.
    • Expansion analysis predicts UI truncation by checking string length growth in target languages.
    • Glossary building creates terminology maps to ensure consistent register and tone across files.

    How it works

    1. Intake where the agent identifies the file format, source locale, and framework from your provided code or strings.
    2. Automated check using a bundled Python script to find syntax errors and placeholder mismatches.
    3. Judgment layer where a manual review finds terminology conflicts and concatenation traps.
    4. Severity classification categorizing findings into Blockers, Major, and Minor issues.
    5. Report delivery providing a full QA scorecard with fix-ready corrections and a CI gate command.

    Frameworks & tools

    Supports Android strings.xml, iOS .strings, Flutter ARB, i18next JSON, Gettext PO/POT, XLIFF, and Java .properties. Works with ICU MessageFormat and standard printf-style specifiers.

    Why this beats prompting it yourself

    Generic prompts often overlook framework-specific syntax like Android's positional specifiers or complex ICU plural categories. This skill uses a structured check catalog to ensure every placeholder and tag remains code-compliant, preventing runtime crashes that simple text analysis misses.

    Use cases

    • Auditing new translation batches for placeholder parity before a release.
    • Checking RTL support for Arabic or Hebrew localizations.
    • Debugging broken ICU plural logic in React or Flutter apps.
    • Identifying hardcoded strings that were missed during externalization.

    Known limitations

    Does not verify translation accuracy for medical, legal, or financial copy. Cannot guarantee layout fit without access to the actual UI rendering engine.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Cannot verify semantic accuracy for high-risk domains. Does not render UI to check for actual pixel-perfect truncation. Requires developer context for short, ambiguous strings.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed23 days ago

    What's inside

    Frequently Asked Questions

    The skill supports a wide range of industry standards, including Android strings.xml, iOS .strings, Flutter ARB, i18next JSON, XLIFF, Gettext PO/POT, and Java .properties. It also handles both ICU MessageFormat and standard printf-style specifiers.

    Unlike generic AI prompts, this skill uses a specialized Judgment Layer and a structured check catalog to identify framework-specific syntax errors, such as positional specifiers or complex ICU plural categories, that often cause runtime crashes. It doesn't just check text; it audits the code-level integrity of your translation files.

    No complex installation is required; the agent performs an initial intake to identify your file format and framework automatically. It then processes your strings through a multi-step audit and delivers a severity-classified QA scorecard with ready-to-use corrections.

    While the skill identifies structural defects and predicts UI truncation due to string expansion, it cannot guarantee a perfect layout fit without access to your live UI rendering engine. Additionally, it focuses on technical and grammatical integrity rather than specialized legal, medical, or financial accuracy.

    Each purchase includes the full auditing workflow, the bundled validation logic for syntax and ICU checks, and the reporting module that generates fix-ready corrections and CI-gate commands for your development pipeline.