All prompts

Design initial skill tree seed files for self-evolving agents, defining core capability nodes, evolution paths, and trigger conditions, allowing agents to autonomously grow a complete skill system from basic capabilities.

Compare and evaluate the performance, quality, and deployment costs of different Speculative Decoding solutions, generating a selection recommendation report.

Automatically generate a minimal viable skill tree seed file based on your Agent's purpose, including core skill definitions, trigger conditions, and evolution path planning.

Use the Gene Expression Programming paradigm to design autonomous evolution strategies for Agents, automatically discovering optimal tool calling sequences and decision paths through genetic algorithms.

Generates a complete CLAUDE.md configuration file based on your project needs, integrating best practices for LLM coding pitfalls summarized by Andrej Karpathy, ensuring Claude Code outputs more stable and reliable code.

Systematically generates reverse engineering analysis reports for Android APKs, including permission analysis, network request capture, key findings from code decompilation, and security vulnerability assessments, suitable for security research and competitive analysis.

Systematically compare and evaluate multiple AI coding agents (Claude Code, Cursor, Maki, Codex, etc.) on token efficiency, response speed, and code quality in real coding tasks, generating a structured evaluation report.

Uses AI to automatically scan and diagnose Kubernetes cluster issues, generating human-readable fault analysis reports and remediation suggestions.

Enables AI to act as an autonomous task planner, decomposing complex goals into executable sub-tasks, automatically planning dependencies, and executing them step-by-step. Suitable for models like ChatGPT/Claude.

Input your hardware configuration and usage scenario, and the AI will generate a complete local large model deployment decision tree, recommending the most suitable model, quantization scheme, and inference framework.

Systematic comparative analysis of open-source AI clients generates technology selection decision reports

Design Bloomberg's end-level AI financial data analysis workflow, integrating multi-source data, quantitative analysis, and multi-agent decision-making systems

Design an AI-driven public opinion monitoring system that aggregates hotspots across multiple platforms, supporting intelligent filtering and push notifications.

Input the product name and core features to automatically generate complete SaaS Landing Page copy, including Hero section, feature highlights, pricing comparison, FAQ, and CTA, with support for bilingual output.

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.

Transform any topic or article into structured knowledge cards containing core concepts, key data, analogy explanations, and memory anchors, suitable for learning and content creation.

One-click generation of issue templates, label classification systems, and contributor guides for open source projects

Helps you analyze prediction market data, identify arbitrage opportunities, and detect sentiment trends

Input any GitHub open source project information to automatically generate a 5-minute quick start guide for beginners

Enter any GitHub open-source project information and it will automatically generate a 5-minute quick tutorial for beginners

Converts original speech recognition text into clearly structured, highly readable professional documents, automatically adding punctuation, paragraphs, titles, and summaries

A Manus-style Markdown persistent planning approach helps AI Agents break down complex tasks step by step and track execution progress

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.

Imitate Manus's persistent Markdown planning workflow, allowing AI coding assistants to maintain clear plan files during complex tasks, automatically tracking progress and marking completion status to avoid context loss.

Directly convert a single-sentence natural language requirement into a complete MCP Server interface design document, including tool definitions, parameter schemas, error handling, and example calls.

Design a secure Python code execution sandbox solution for AI Agents, based on a minimal Python interpreter implemented in Rust to prevent malicious code escape.

Generates automated fault diagnosis and self-healing runbooks for AI Agent workloads in K8s clusters, covering common scenarios such as Pod anomalies, OOM, and GPU scheduling failures.

Designs a multi-platform public opinion aggregation monitoring system supporting RSS+API data sources, AI intelligent filtering, and multi-channel push notifications, suitable for individuals and teams.

Enter a theme and automatically generate Douyin and Xiaohongshu short video scripts with storyboards, dialogue, and images

Generates a detailed token consumption optimization plan for your AI Agent application, covering context compression, caching strategies, model routing, and more.

Describe your business scenario in natural language to automatically generate multi-model routing strategy configurations, achieving the optimal balance between cost and quality.

Design a comprehensive multi-platform public opinion monitoring system that aggregates hotspots from Weibo, Xiaohongshu, Twitter, etc., with AI-driven analysis and briefing push notifications.

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.

Intelligently reduce noise, deduplicate, and correlate massive operations alerts to generate root cause analysis reports and remediation suggestions.

Helps you systematically analyze and optimize the context window usage efficiency of AI coding agents (such as Claude Code, Cursor, Copilot), generating specific slimming plans and configuration suggestions.

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 ML papers, extract core methods and innovations, and generate experimental reproduction plans

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.

Input the title or abstract of an AI/ML paper to automatically generate a structured quick-read report containing core contributions, methodological innovations, experimental results, and limitation analysis.

Analyze token consumption patterns in your AI Agent workflow, generate intelligent routing rules, and automatically assign simple tasks to smaller models and complex tasks to larger models, reducing API costs by 60-90%.

Evaluate the first-screen effect of your GitHub README using the 3-second rule, receive an attractiveness score, and get an automatic rewrite to help open-source projects boost Star conversion rates.

Generate optimal configuration plans for AI coding IDEs like Cursor, Windsurf, and Kiro, optimizing Agent workflows and context management strategies.

Generates personal identifiable information (PII) detection rules, masking strategies, and compliance reports based on frameworks like Microsoft Presidio.

Input the project tech stack and dependency list to generate a complete dependency security audit report, including vulnerability severity, impact scope, and remediation suggestions.

For Mixture of Experts (MoE) architecture models, generates detailed inference deployment plans, including hardware selection, communication optimization, and cost estimation.

A complete workflow prompt for using AI to read papers, reproduce experiments, and train models, suitable for researchers and ML engineers.