All prompts

Used to evaluate AI Agent conversation quality, scoring from multiple dimensions such as accuracy, relevance, security, and formatting standards, generating structured evaluation reports suitable for quality control before Agent products go live.

Simulate a professional Bloomberg Terminal style, using AI to analyze stocks, futures, and macroeconomic data, generating professional-grade investment research reports and visualization chart recommendations.

Helps you quickly determine whether an AI Agent skill is worth installing by generating a structured evaluation decision tree.

Input natural language requirements to automatically generate an MCP protocol-compliant Server interface design document, including tool definitions, parameter schemas, and example calls.

Compresses multiple news/social media items into a structured one-page briefing, suitable for quickly understanding the full picture of a topic.

Input a topic to automatically generate a complete workflow prompt for short video production, including script, storyboard, voiceover copy, subtitles, and publishing plan.

Automatically generate deployment plans for multi-model hybrid inference clusters based on business scenarios and hardware conditions, including model allocation, routing strategies, and cost estimates.

Batch converts multimodal documents such as PDFs, images, and web pages into structured Markdown knowledge bases, supporting direct integration with RAG systems.

Evaluates the maturity of an AI Agent's self-evolution capabilities and provides evolution asset design proposals based on the GEP (Gene Expression Programming) framework, including implementation suggestions for a three-layer architecture of Genes, Capsules, and Events.

Input a list of pending tasks to the AI, which will automatically sort them based on urgency, dependencies, and estimated duration, outputting an execution plan with time suggestions.

Decompose complex project requirements into multiple Agent subtasks, assign them to different platforms (Web/Desktop/Terminal) for coordinated execution, and generate a Kanban board and dependency graph.

Generate a complete technical selection, architecture design, and deployment plan for an open-source NotebookLM alternative based on requirements, supporting local/private deployment.

Automatically design a speculative decoding acceleration scheme based on your model deployment scenario, including draft model selection, verification strategies, and performance estimates.

Automatically generate complete Python data processing pipeline code based on natural language descriptions of data cleaning needs, supporting frameworks like Pandas and Polars.

Input a GitHub repository link to quickly analyze the project's technical architecture, outputting an architecture description and a Mermaid visualization diagram, suitable for technology selection and code reading.

Based on historical project data, community activity, and external events, predict the Star growth trend of open-source projects, generating community operation growth models and strategic recommendations.

Generates comprehensive desktop operation test scenarios for Computer-Use Agents (CUAs), including multi-step UI interactions, exception handling, and evaluation metrics, suitable for macOS/Linux/Windows sandbox environments.

Uses LLMs to extract structured entities from unstructured text, supporting custom schemas and few-shot examples, suitable for document parsing, report analysis, and other scenarios.

Describe your microservice deployment needs in natural language; the AI automatically generates a complete Helm Chart, including values.yaml, templates, and NOTES.txt.

Generate comprehensive metadata governance solutions for enterprises, including data lineage tracking, data quality monitoring, automatic classification and annotation, and data catalog construction, helping AI teams build trusted data infrastructure.

Generate secure sandbox code execution environment configurations for AI Agents, supporting various isolation solutions such as Docker and microVMs to ensure the safety of AI code execution.

Based on your mood, scene, or theme, generate a complete song creative plan, including style, lyric outline, arrangement suggestions, and prompts for AI music tools.

Converts natural language descriptions of desktop operation tasks into structured automation execution steps, suitable for AI desktop Agent scenarios.

Design a local-first scientific writing environment integrating LaTeX formatting, Python data analysis, and AI assistance, ensuring data privacy.

Helps developers plan and manage multiple coding agent parallel sessions, reasonably allocating tasks, avoiding file conflicts, and coordinating merge strategies.

Transform repetitive terminal operations described in natural language into reusable automated scripts supporting Bash/Zsh/Fish, including error handling and logging.

Help you plan how to collect and prepare personal data to train an AI digital avatar that mimics your style

Analyze your current development toolchain configuration to identify efficiency bottlenecks and recommend the optimal AI-enhanced solution

Converts obscure API error messages into easy-to-understand Chinese explanations, along with specific repair suggestions and code examples

Analyzes command safety, rates risks, and assesses potential impacts before execution to prevent accidental data loss or system damage.

Automatically generates comparative evaluation scripts for multiple LLMs based on requirements, supporting custom test sets, scoring metrics, and result visualization.

Design a complete closed-loop AI Agent autonomous project delivery process, from task receipt to PR merging, without step-by-step human supervision. Suitable for team-level AI coding agent deployment scenarios.

For CI/CD systems like GitHub Actions, a comprehensive security hardening checklist is automatically generated, covering key security areas such as supply chain attack protection, key management, and permission minimization.

Helps review React code generated by AI coding agents, detects common anti-patterns (unnecessary re-renders, closure traps, state management errors, etc.), and provides fixing suggestions.

Analyze contributor structure, community activity, and health metrics of GitHub open-source projects to generate visual reports.

Help developers evaluate and select full-duplex voice AI tech stacks, and design low-latency real-time voice interaction system architectures.

Automatically generate multi-LLM model routing strategies based on task type, cost budget, and latency requirements to help developers intelligently distribute requests across different models.

Input a repository link to automatically analyze project architecture and generate Mermaid dependency diagrams, complexity heatmaps, and onboarding reading routes.

Design standardized communication protocols and message formats for multi-agent systems, supporting task distribution, state synchronization, error propagation, and result aggregation.

Help developers evaluate and select the most suitable LLM inference acceleration technologies, including speculative decoding, quantization, and KV Cache optimization.

Design multilingual speech synthesis and cloning solutions based on the latest open-source TTS technologies, covering voice design, emotion control, and streaming output.

Systematically evaluate the strategy logic, risk control mechanisms, and drawdown tolerance of your AI autonomous trading system, generating a structured pre-launch checklist.

Describe your document types and scale to generate a complete local semantic search system deployment plan, including embedding model selection, vector database configuration, and search API code.

Design a rigorous A/B test experiment plan for your LLM application, including sample size calculation, evaluation metric definition, statistical significance testing, and result visualization code.

Design the task workflow for an automation agent, including deployment, monitoring, fault recovery, and scaling strategies.

Decompose complex development requirements into independently executable sub-tasks and generate detailed agent instructions for each, compatible with multi-agent coding platforms like Multica and Claude Code.

Generate personalized learning paths and weekly plans based on the user's knowledge base, goals, and available time.

Instruct the AI Agent to automatically loop through and execute all items in the PRD until completion. Suitable for autonomous development scenarios with coding agents like Claude Code or Codex.