DeepSeek Directory - Reasoning Prompts, Code Tools & Agents
    Neura MarketNeura Market/DeepSeek
    ChatGPTChatGPTClaudeClaudeGeminiGeminiCursorCursorGrokGrokPerplexityPerplexityDeepSeekDeepSeek
    CoPilotCoPilotStable DiffusionStable DiffusionMidjourneyMidjourney
    View All Directories
    OverviewRulesPromptsMCPsAgentsBlogVideosGuidesCoursesCommunityTrendingGenerate
    Join the most active DeepSeek community
    DeepSeek

    The home for DeepSeek enthusiasts

    Explore reasoning prompts, code tools, and agents for DeepSeek.

    Search prompts, reasoning tools, and more...⌘K

    Featured MCPs

    View all →
    F
    Filesystem MCP
    H
    Hugging Face Hub MCP
    S
    Simple MCP Client for DeepSeek
    D
    DeepSeek Terminal MCP Server
    D
    DeepSeek MCP with Mixture of Experts
    D
    DeepSeek MCP in Go (DeepseekMCP)
    D
    DeepSeek MCP Server
    D
    DeepSeek R1 MCP Server for Claude Desktop
    D
    DeepSeek Reasoning MCP Server
    D
    DeepSeek Thinker MCP

    Trending in DeepSeek

    View all →
    4596
    @Nunki08

    Starting next week, DeepSeek will open-source 5 repos

    Starting next week, DeepSeek will open-source 5 repos

    2895
    @ParsaKhaz

    deepseek is a side project

    deepseek is a side project

    2786
    @Optimal_Hamster5789

    Meta panicked by Deepseek

    Meta panicked by Deepseek

    2486
    @SquashFront1303

    Chad Deepseek

    Chad Deepseek

    1990
    @m-gethen

    Qwen wants you to know…

    Seen while walking through Singapore’s Changi airport earlier this week. Alibaba Cloud spending up big on advertising.

    Featured Prompts

    View all →

    Social Network Graph Analysis

    Analyze social network structures for community detection, influence propagation, and information flow patterns.

    164

    Event Sourcing and CQRS Implementation

    Implement event sourcing with command handling, event store, projections, and CQRS read model separation.

    155

    Topology Intuition Builder

    Develop topological intuition through problems about open sets, compactness, connectedness, and homeomorphisms.

    12

    Recursive Thinking Practice

    Develop recursive thinking skills with problems that naturally decompose into smaller self-similar subproblems.

    10

    Game Theory Strategic Analysis

    Apply game theory reasoning to multi-agent strategic scenarios including Nash equilibria and dominant strategies.

    147

    Mechanistic Reasoning in Biology

    Trace biological mechanisms from molecular to organism level, reasoning about cause-effect chains in living systems.

    7

    Combinatorial Puzzle Master

    Solve combinatorial puzzles including bin packing, job scheduling, and traveling salesman variations.

    123

    Causal Reasoning Chain Analysis

    Analyze cause-and-effect relationships in complex scenarios using DeepSeek R1's extended thinking capabilities.

    179

    Academic Paper Translation with Context

    Translate academic papers while preserving technical precision, citation formats, and field-specific conventions.

    12

    Literature Review Synthesizer

    Synthesize multiple research sources into coherent literature reviews with thematic organization and gap identification.

    109
    DeepSeek Directory

    The Daily Hub for Developers Building with DeepSeek

    Get your product in front of the builders defining the future.

    Advertise

    Featured Agents

    View all →
    ragflow

    ragflow

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

    78196
    lobehub

    lobehub

    The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

    75236
    LlamaFactory

    LlamaFactory

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    70147
    unsloth

    unsloth

    Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

    61684
    JeecgBoot

    JeecgBoot

    一款 AI 驱动的低代码平台,提供"零代码"与"代码生成"双模式——零代码模式一句话搭建系统,代码生成模式自动输出前后端代码与建表 SQL,生成即可运行。平台内置 AI 聊天助手、AI大模型、知识库、AI流程编排、MCP 与插件体系,兼容主流大模型,支持一句话生成流程图、设计表单、聊天式业务操作,解决 Java 项目 80% 重复工作,高效且不失灵活。

    45857
    CowAgent

    CowAgent

    CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。

    43281

    Learn

    View all →

    Top Videos

    27:00

    DeepSeek R1 Prompt Engineering Masterclass

    AI Community

    38:00

    Building a RAG Pipeline with DeepSeek and LangChain

    AI Community

    24:00

    DeepSeek R1 Math Problem Solving: AMC to IMO Level

    AI Community

    Top Guides & Docs

    DeepSeek V3 OpenRouter and Third-Party API Access Guide

    Neura Market

    DeepSeek R1 for Mathematical Olympiad Problem Solving

    Neura Market

    DeepSeek V3 for Content Writing and SEO Optimization

    Neura Market

    Top Courses

    35 hours

    Computer Vision with Deep Learning

    AISchool

    25 hours

    Advanced Python for AI Development

    DevAcademy

    DeepSeek R1 AI: 25 Real World Projects

    Rules

    View all →

    AI/ML

    View all →
    For DeepSeek-R1 (Reasoning Model): - Do NOT use system prompts — place all instructions in the user message - Do NOT use few-shot examples (they confuse the reasoning chain) - Set temperature to 0.6 for optimal reasoning - Let the model reason independently For DeepSeek-V3 (Chat Model): - Use system prompts to define behavior and persona - Few-shot examples work well - Temperature 0.7-1.0 for creative tasks, 0.3-0.5 for precise tasks General Settings: - max_tokens: Set appropriately for your task - top_p: 0.95 recommended - frequency_penalty: 0 (default) - presence_penalty: 0 (default)
    Prompt Engineering Template for DeepSeek: ## Structure 1. ROLE: Define the expert persona 2. CONTEXT: Provide relevant background 3. TASK: Clearly state what you need 4. FORMAT: Specify output format 5. CONSTRAINTS: List any restrictions 6. EXAMPLES: Provide sample input/output (V3 only, not R1) ## R1-Specific Tips - Omit system prompt entirely - Place everything in user message - Let model reason without constraints - Temperature: 0.6 - No few-shot examples ## V3-Specific Tips - Use detailed system prompts - Few-shot examples improve quality - Temperature: task-dependent (0.3-1.0) - Use JSON mode for structured output

    Software Engineering

    View all →
    You are an expert software engineer using DeepSeek V3. Follow these rules: 1. Always provide complete, runnable code — never use placeholder comments 2. Use TypeScript by default unless the user specifies otherwise 3. Follow the project's existing code style and conventions 4. Include error handling for all async operations 5. Write self-documenting code with meaningful variable names 6. When debugging, explain the root cause before providing the fix 7. For refactoring suggestions, explain the tradeoffs 8. Use modern ES2022+ syntax 9. Prefer composition over inheritance 10. Always consider edge cases and null/undefined handling
    Code Review Agent Configuration: 1. Review code for: - Security vulnerabilities (OWASP Top 10) - Performance issues (N+1 queries, memory leaks) - Code style consistency - Error handling completeness - Test coverage gaps - Documentation accuracy 2. Rating scale: Critical / Major / Minor / Suggestion 3. For each issue found: - Line number and file - Issue description - Severity level - Suggested fix with code - Explanation of why it matters 4. End with summary: - Overall code quality score (1-10) - Top 3 improvements needed - What was done well

    Research and Analysis

    View all →
    You are a research analyst powered by DeepSeek R1. Your approach: 1. Break complex questions into sub-questions 2. Analyze each component systematically 3. Consider multiple perspectives and counter-arguments 4. Cite specific data points and sources when available 5. Distinguish between established facts, reasonable inferences, and speculation 6. Present findings in a structured format with clear sections 7. Include a confidence level (High/Medium/Low) for each conclusion 8. Suggest follow-up research questions 9. Flag potential biases in your analysis 10. Provide an executive summary at the top

    Stay up to date

    Get the latest DeepSeek prompts, rules, and resources delivered to your inbox weekly.

    Neura Market LogoNeura Market

    Discover the best AI prompts, plugins, and resources for DeepSeek and more.

    Content Types

    • Rules
    • Prompts
    • MCPs
    • Agents
    • Guides

    Platforms

    • ChatGPT Directory
    • Claude Directory
    • Gemini Directory
    • Cursor Directory
    • Grok Directory
    • Perplexity Directory
    • DeepSeek Directory
    • CoPilot Directory
    • Stable Diffusion Directory
    • Midjourney Directory
    • All Directories

    Resources

    • Blog
    • Documentation
    • Help Center
    • Marketplace

    Legal

    • Privacy Policy
    • Terms of Service

    © 2026 Neura Market. All rights reserved.

    |

    Not affiliated with any AI platform vendors.