localizationDeep localization workflow—locale strategy, string extraction, ICU and placeholders, formatting, RTL and layout, translation QA, and continuous delivery with...
Install via ClawdBot CLI:
clawdbot install clawkk/localizationGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 6, 2026
An online retailer expanding into 10+ new markets needs to localize product listings, checkout flows, and customer support. The workflow ensures ICU plurals for cart quantities, Intl formatting for currencies, and RTL support for Arabic, avoiding translation rework.
A B2B SaaS company shipping a major update to 5 languages uses pseudo-localization in CI to catch truncation bugs, defines locale fallback chains, and integrates TMS for translator context, reducing QA time by 30%.
A social media app experiencing broken plurals and date formatting errors in Japanese and German adopts the six-stage workflow. ICU message format replaces concatenated strings, and golden tests prevent regression.
A fintech company entering Latin America needs region-specific legal strings, currency formatting, and RTL for Hebrew. The workflow flags jurisdiction review and enforces ICU for gender agreement in Spanish.
Localize for a tiered locale list (e.g., Tier 1: Western Europe, Tier 2: Asia) with fallback chains. Revenue grows per-market as translation costs scale linearly with string count.
Offer the workflow as a managed service for enterprises: assess, extract, translate, and QA. Revenue via retainer or project fees, with upsells for ICU linting and RTL layout audits.
Integrate pseudo-localization and golden tests into client CI pipelines. Charge per integration plus ongoing maintenance for diff notifications and locale snapshot updates.
💬 Integration Tip
Start by enforcing ICU MessageFormat and Intl APIs in your codebase via linter rules; wire pseudo-localization into your CI pipeline to catch truncation early.
Scored May 6, 2026
Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale.
Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, code >10 lines, reports, proposals, multi-step reasoning, tables, outlines, charts, long writing >3 paragraphs, summarization, long translation. NEVER on Haiku: comparison tables, code >10 lines, multi-step analysis, reports, complex reasoning. STAY on Haiku: factual Q&A, definitions, greetings, reminders, short lookups, casual chat, 1-2 sentence tasks. When in doubt, escalate. Keep Haiku replies concise.
End-user guide for running and configuring the `translate` CLI across text/stdin/file/glob inputs, provider selection, presets, custom prompt templates, and...
Translates articles and documents between languages with three modes - quick (direct), normal (analyze then translate), and refined (analyze, translate, revi...
中文办公自动化 - 专为中文用户设计的办公自动化技能套件。集成中文文档处理、拼音转换、节假日判断、农历支持等功能。
Japanese-English translator and language tutor. Use when: (1) User shares Japanese text and wants translation (news articles, tweets, signs, menus, emails). (2) User asks "what does X mean" for Japanese words/phrases. (3) User wants to learn Japanese grammar, vocabulary, or cultural context. (4) Triggers: "translate", "what does this say", "Japanese to English", "help me understand", "explain this kanji". Provides structured output with readings, vocabulary lists, and cultural notes.