35 rules available in the DeepSeek directory
System rules for designing inter-service communication in microservices architectures with DeepSeek Coder, covering sync/async patterns, error handling, and resilience.
System rules for generating content in multiple languages with DeepSeek V3, covering translation quality, cultural adaptation, locale-specific formatting, and quality assurance.
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.
System rules for using DeepSeek V3 to develop backend APIs with Node.js/Express or Python/FastAPI, covering security, validation, error handling, and documentation.
Comprehensive system rules for configuring DeepSeek V3 as a frontend development assistant with React, TypeScript, CSS, and accessibility standards.
System rules for forcing DeepSeek R1 to output structured JSON, YAML, or XML responses while still leveraging chain-of-thought reasoning in think tags.
Rules for deploying and optimizing DeepSeek models locally using Ollama, including hardware requirements, configuration, and performance tuning.
Rules for implementing content moderation when using DeepSeek models in user-facing applications, covering input screening, output filtering, and escalation.
Rules for organizing, versioning, and testing prompt templates in production applications that use DeepSeek models.
Rules for building TypeScript/Node.js applications with DeepSeek API, including client patterns, streaming, error handling, and deployment.
Comprehensive development rules for building Python applications with DeepSeek API integration, covering project structure, type hints, testing, and async patterns.
Rules for optimizing context window usage across DeepSeek models including chunking strategies, summarization, and conversation management.
Security-focused rules for deploying DeepSeek models in production, covering API key management, input sanitization, output filtering, and compliance.
Rules for building an intelligent router that selects the optimal DeepSeek model (V3, R1, Coder) based on task type, complexity, and cost constraints.
Production rules for handling DeepSeek API rate limits, errors, retries, and cost optimization in application code.
Guidelines for maximizing DeepSeek R1 reasoning quality through proper prompting structure, thinking tag management, and multi-step problem decomposition.
Rules for configuring DeepSeek to produce structured JSON output reliably, with schema validation and error handling patterns.
Configuration rules for using DeepSeek models within Cursor IDE, including agent mode setup, file handling, and code generation guidelines.
Comprehensive rules for configuring DeepSeek V3 as a production-quality coding assistant with planning, code quality, and output formatting guidelines.
The standard system instructions used by DeepSeek Coder models, defining the AI programming assistant role and behavioral boundaries.