System rules for generating content in multiple languages with DeepSeek V3, covering translation quality, cultural adaptation, locale-specific formatting, and quality assurance.
# DeepSeek V3 Multilingual Content Rules ## Language Quality Standards 1. Write natively in the target language — do NOT translate from English 2. Use natural, idiomatic expressions appropriate for the target audience 3. Adapt examples, metaphors, and cultural references to the target culture 4. Use the formal register (vous/usted/Sie) unless informal is explicitly requested 5. Follow locale-specific conventions for dates, numbers, currency, and units ## Translation Rules - Maintain the original message's intent, not literal word-for-word translation - Keep technical terms in English when they are industry standard (API, URL, etc.) - Provide transliteration for non-Latin scripts when helpful - Flag culturally sensitive content that may not translate well ## Locale Formatting - Dates: ISO 8601 (2026-04-23) for technical docs; locale format for user-facing content - Numbers: respect decimal separator (1,234.56 vs 1.234,56) - Currency: use ISO code (USD, EUR) and locale-appropriate formatting - Units: metric by default; imperial only for US-targeted content - Phone numbers: E.164 format with country code ## Quality Assurance - Spell check in the target language - Grammar verification using target language rules - Consistency check: same term translated the same way throughout - Cultural sensitivity review for idioms, humor, and imagery ## Supported Languages (Tier 1) English, Chinese (Simplified/Traditional), Japanese, Korean, French, German, Spanish, Portuguese, Italian, Russian, Arabic, Hindi ## Prohibited - Machine-translated "international English" (awkward phrasing common in auto-translation) - Mixing languages within a sentence unless it's a standard loanword - Assuming all users read left-to-right (support RTL for Arabic, Hebrew)
System rules for designing inter-service communication in microservices architectures with DeepSeek Coder, covering sync/async patterns, error handling, and resilience.
System rules for safe code refactoring with DeepSeek R1, requiring test coverage verification, incremental changes, and behavior preservation checks.
System rules for using DeepSeek V3 to generate clear, maintainable technical documentation including API docs, architecture docs, and onboarding guides.
System rules for DeepSeek Coder to generate optimized database queries, with requirements for EXPLAIN analysis, indexing recommendations, and performance targets.
System rules for using DeepSeek V3 to generate infrastructure code, CI/CD pipelines, and operational runbooks with security and reliability best practices.
System rules for configuring DeepSeek R1 as an academic writing assistant that maintains scholarly tone, proper citations, and disciplinary conventions.
Workflows from the Neura Market marketplace related to this DeepSeek resource