自撰作品《AI精准操作手册:从Prompt工程到认知导航》(AI Precision Operations Manual: From Prompt Engineering to Cognitive Navigation)
# AI精准操作手册:从Prompt工程到认知导航<br>AI Precision Operations Manual: From Prompt Engineering to Cognitive Navigation 👇在线阅读全书 ## [📖目录](https://github.com/1Haschwalth/prompt-engineering/tree/MAIN/%E4%B9%A6) - [0. 序篇](https://github.com/1Haschwalth/prompt-engineering/tree/MAIN/%E4%B9%A6/0.%20%E5%BA%8F%E7%AF%87) - [笔者按:写给每一个即将成为超级个体的你](https://github.com/1Haschwalth/prompt-engineering/blob/MAIN/%E4%B9%A6/0.%20%E5%BA%8F%E7%AF%87/0.%20%E7%AC%94%E8%80%85%E6%8C%89.md) - [导论——精准时代的认知杠杆](https://github.com/1Haschwalth/prompt-engineering/blob/MAIN/%E4%B9%A6/0.%20%E5%BA%8F%E7%AF%87/1.%20%E5%AF%BC%E8%AE%BA%E2%80%94%E2%80%94%E7%B2%BE%E5%87%86%E6%97%B6%E4%BB%A3%E7%9A%84%E8%AE%A4%E7%9F%A5%E6%9D%A0%E6%9D%86.md) - [1. 理论基础篇——解构Prompt的哲学与科学](https://github.com/1Haschwalth/prompt-engineering/tree/MAIN/%E4%B9%A6/1.%20%E7%90%86%E8%AE%BA%E5%9F%BA%E7%A1%80%E7%AF%87%E2%80%94%E2%80%94%E8%A7%A3%E6%9E%84Prompt%E7%9A%84%E5%93%B2%E5%AD%A6%E4%B8%8E%E7%A7%91%E5%AD%A6) - [第二章:Prompt的本质与第一性原理](https://github.com/1Haschwalth/prompt-engineering/blob/MAIN/%E4%B9%A6/1.%20%E7%90%86%E8%AE%BA%E5%9F%BA%E7%A1%80%E7%AF%87%E2%80%94%E2%80%94%E8%A7%A3%E6%9E%84Prompt%E7%9A%84%E5%93%B2%E5%AD%A6%E4%B8%8E%E7%A7%91%E5%AD%A6/2.%20Prompt%E7%9A%84%E6%9C%AC%E8%B4%A8%E4%B8%8E%E7%AC%AC%E4%B8%80%E6%80%A7%E5%8E%9F%E7%90%86%E2%80%8B%E2%80%8B.md) - [第三章:大模型如何“思考”与回应Prompt](https://github.com/1Haschwalth/prompt-engineering/blob/MAIN/%E4%B9%A6/1.%20%E7%90%86%E8%AE%BA%E5%9F%BA%E7%A1%80%E7%AF%87%E2%80%94%E2%80%94%E8%A7%A3%E6%9E%84Prompt%E7%9A%84%E5%93%B2%E5%AD%A6%E4%B8%8E%E7%A7%91%E5%AD%A6/3.%20%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%A6%82%E4%BD%95%E2%80%9C%E6%80%9D%E8%80%83%E2%80%9D%E4%B8%8E%E5%9B%9E%E5%BA%94Prompt.md) - [2. 核心技法篇——精准操作的四大支柱](https://github.com/1Haschwalth/prompt-engineering/tree/MAIN/%E4%B9%A6/2.%20%E6%A0%B8%E5%BF%83%E6%8A%80%E6%B3%95%E7%AF%87%E2%80%94%E2%80%94%E7%B2%BE%E5%87%86%E6%93%8D%E4%BD%9C%E7%9A%84%E5%9B%9B%E5%A4%A7%E6%94%AF%E6%9F%B1%E2%80%8B%E2%80%8B) - [第四章:第一支柱——明确认知坐标系(Define the Frame of Reference)](h
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型