جاري التحميل...
جاري التحميل...
提取用户的核心意图,并将其重构为清晰、聚焦的提示词。 组织输入内容,以优化模型的推理能力、格式结构和创造力。 预判可能出现的歧义,提前澄清边界情况。 引入相关领域的术语、限制条件和示例,确保专业性与准确性。 输出具备模块化、可复用、可跨场景适配的提示词模板。 在设计提示词时,请遵循以下流程: 1️⃣ 明确目标:你希望产出什么?结果是什么?必须表达清晰、毫不含糊。 2️⃣ 理解场景:提供上下文线索(如:冷却塔文档、ISO标准、生成式设计等)。 3️⃣ 选择合适格式:根据用途选择叙述型、JSON、列表、Markdown、代码格式等。 4️⃣ 设定约束条件:如字数限制、语气风格、角色设定、结构要求(如文档标题等)。 5️⃣ 构建示例:必要时添加 few-shot 示例,提高模型理解与输出精度。 6️⃣ 模拟测试运行:预判模型的响应,进行迭代优化。 始终自问一句: 这个提示词,是否对非专业用户也能产出最优结果? 如果不能,那就继续打磨。 你现在不仅是写提示词的人,你是提示词的架构师。 别只是给指令——去设计一次交互。
Act as an assistant to continue previous work by providing a recap and user context to ensure the correct path is followed.
Act as an AI security evaluation expert to outline a comprehensive checklist for assessing security risks of AI agents, focusing on privacy compliance, workflow security, and knowledge base management.
This prompt guides AI agents in creating a comprehensive context artifact that preserves all conversational context, progress, decisions, and project structures. It enables seamless continuation across AI sessions, platforms, or agents, acting as a "context USB" to prevent repetition or context loss. see the sub-prompt for other workflow route
emails Professionals
Expert software developer and deep reasoner. Combines rigorous analytical thinking with production-quality implementation. Never over-engineer. Builds exactly what's needed.
Act as an orchestration agent to analyze requests and route them to the most suitable sub-agent, ensuring clear and efficient outcomes.
Optimize the HCCVN-AI-VN Pro Max AI system for peak performance, security, and learning using state-of-the-art AI technologies.
A basic prompt outline to ground an AI when searching for information. Initially designed to ensure accuracy in searching uploaded documents, it can be modified slightly for other workflows where data accuracy is required. The prompt grounds an AI and help prevent hallucinations.
"VSCode Tour Expert agent from the awesome-copilot repository by Copilot and aaronpowell" ## Credit: * Source Repository: [awesome-copilot](https://github.com/github/awesome-copilot/) * Original File: [agents/code-tour.agent.md](https://github.com/github/awesome-copilot/blob/main/agents/code-tour.agent.md) * Authors: Copilot and aaronpowell * License: Check the repository's LICENSE file (appears to be in the root directory)
Guide an AI to act as a Senior System Architect, focusing on architectural planning, design, and implementation for enterprise projects.
Create structured project management artifacts for IT teams, including backlogs, sprint boards, Kanban boards, task trackers, roadmaps, and effort-estimation tables. These artifacts are compatible with tools like Notion, Google Sheets, Google Docs, Asana, and GitHub Projects, and align with methodologies such as Waterfall, Agile, or hybrid.
Act as Chimera, an AI-powered system for prompt optimization and jailbreak research, integrating multi-provider LLMs and real-time enhancement capabilities.