All prompts

Generates a complete local LLM fine-tuning plan based on hardware conditions and task requirements, including data preparation, training configuration, and deployment.

Automatically plans the skill modules, toolchains, and execution flows required by an AI Agent based on task descriptions.

Design an automated code review pipeline with multi-agent collaboration, including role division for security auditing, performance analysis, and code style checking.

Help developers quickly configure MCP Server to connect to databases, providing structured data access capabilities for AI Agents.

Enter project information and automatically generate a README in Chinese, English, and Japanese, including badges, installation instructions, usage examples, and other complete structures.

Designs multi-agent collaboration systems for robot hardware platforms, supporting natural language control of humanoid robots, quadrupeds, and drones.

Breaks down penetration testing targets into automated sub-task chains, supporting the full process from information gathering and vulnerability scanning to exploitation and report generation.

Transforms basic READMEs into professional, visually appealing versions that attract stars, supporting bilingual (Chinese/English) output.

Diagnose your efficiency in using AI coding assistants (Cursor/Copilot/Claude Code, etc.) and provide optimization suggestions.

A prompt for local deployment and debugging of Vision Language Models (VLMs) designed specifically for Apple Silicon Mac users, based on the MLX framework.

Uses AI to analyze time series data, generating forecasting reports and visualization suggestions

Design robust error handling, automatic retry, and graceful degradation strategies for AI Agent systems.

Design the optimal local RAG/semantic search architecture based on your data type and scale.

Helps you design task scheduling strategies for multi-agent parallel coding, resolving code conflicts, resource competition, and other issues.

Describe the automation process you want in natural language, and AI helps break it down into executable Agent workflow steps.

Generate Compound Engineering best practice configurations for coding Agent projects to improve multi-Agent collaborative code quality.

Design multi-tool parallel scheduling strategies for AI Agents, including task decomposition, tool selection, result aggregation, and exception fallback mechanisms.

Generate performance benchmark reports for LLM inference on edge devices, covering latency, throughput, memory usage, and quantization strategy comparisons.

Expert consultant for designing and building full-stack serverless applications using Cloudflare Workers, D1, R2, KV, and other edge computing services.

Generate a comprehensive performance tuning checklist and optimization suggestions for locally deployed on-device large language models.

Help researchers systematically reproduce experiments from AI papers, providing end-to-end guidance from environment setup to result verification.

Design AI chatbot architectures supporting multiple platforms like WeChat, Telegram, and Discord, including message routing, context management, and plugin systems.

Input your service description to automatically generate a complete code framework for a Model Context Protocol Server.

Analyze your AI Agent workflow to identify token waste points, generate context compression plans, and help you save money and improve efficiency.

Design robust error handling mechanisms for AI Agents, including retry strategies, fallback chains, timeout management, and graceful degradation plans to ensure valuable output even in abnormal scenarios.

Generate local LLM deployment plans for Mac users, including model selection, quantization strategies, MLX/llama.cpp configurations, and performance tuning suggestions.

Helps design voice AI product solutions, covering the entire process from requirement analysis to technology selection to user experience

Analyzes system prompts of any AI product, extracting design patterns, security mechanisms, and functional architecture to help you understand how top-tier AI products design their prompts.

Analyze issues in open-source project READMEs and generate optimized versions to improve discoverability and developer conversion rates.

Help you describe multi-agent collaboration scenarios in natural language, automatically generating a complete workflow orchestration plan, including agent role definitions, message routing, fault tolerance strategies, and human-in-the-loop nodes.

Help compress long conversations/documents to fit within the LLM context window, preserving key information and reducing token consumption.

Input basic information about an open-source project to automatically generate a high-quality bilingual (Chinese + English) README, suitable for international promotion.

Describe a scene to generate detailed anime-style prompts suitable for tools like Midjourney/SD.

Generate a comprehensive performance optimization checklist for deploying AI models on edge/on-device scenarios, covering model compression, inference acceleration, and resource management.

Rapidly designs computer vision solutions based on business requirements, including model selection and deployment architecture.

Paste agent runtime logs to AI to automatically identify failure reasons, provide fix suggestions, and retry strategies

Automatically generates best practice configurations for Claude Code based on your project type, including CLAUDE.md, sub-Agent definitions, custom commands, and skill modules.

Input a GitHub project link, and the AI will summarize its core value, applicable scenarios, and potential risks in one sentence.

Design AI data pipelines for processing images, audio, video, and structured data, suitable for large-scale data engineering scenarios.

Automatically analyze invoices, receipts, and bank statements, archive them by category, and generate expense reports.

Analyze problems with an open-source project's README and rewrite it to make the project easier to discover and use.

Design a fully local document semantic search system for you, combining BM25 keyword search and vector semantic search, suitable for notes, meeting minutes, and knowledge bases.

Analyze the system prompts of any AI product, identify security vulnerabilities and optimization opportunities, and generate a hardened version. Suitable for AI product developers conducting security audits.

Input a GitHub repository link to generate a 30-second elevator pitch script, social media copy, and target audience analysis. Ideal for technical sharing and content creation.

Quickly evaluates the value, tech stack, and applicable scenarios of trending open-source projects on GitHub.

Architectural guidance, concurrency patterns, and performance optimization advice for building AI Agents and LLM applications in Go.

Design role assignment, communication protocols, and task orchestration schemes for multi-agent collaboration systems.

Design and build a local-first document semantic search system supporting intelligent retrieval of meeting minutes, notes, and knowledge bases.