实用指南，帮助你用Claude Code、Cursor、Windsurf及其他代理AI编码工具获得有效效果。

基于对1352条真实发展信息的分析，以识别导致高效协作的沟通模式。

向导

• 代理AI工作流程指南 - 主要实用指南，包含逐步方法和全面常见问题解答
• 沟通指南 - 深入解析8种沟通模式和会话动态
• 快速参考 - 一页速查表

技能

skills/ 文件夹包含了 Claude Code 的可重复使用技能定义：

• 链接意图开发- 链接意图开发（LID）——设计前代码的结构化工作流程：HLD → LLD → EARS 规范→实现计划

关键见解

从副驾驶转向智能人工智能：

• 副驾驶：你写代码，AI建议完成
• 代理型AI：AI编写代码，你负责引导和验证

是什么让疗程有效：

1. 详细说明——“我预期Y时看到X”，而不是“坏了”。
2. 闭环——报告结果，哪怕只是“是的”
3. 不断转向——“很好。现在我们…”每隔几次交流
4. 验证假设——“你理解了什么？”工作结束后

How to Work with Agentic AI Coding Assistants

Practical guides for getting effective results with Claude Code, Cursor, Windsurf, and other agentic AI coding tools.

Based on analysis of 1,352 real development messages to identify what communication patterns lead to productive collaboration.

Guides

• Agentic AI Workflow Guide - The main practical guide with step-by-step approach and comprehensive FAQ
• Communication Guide - Deep dive into the 8 communication patterns and session dynamics
• Quick Reference - One-page cheat sheet

Skills

The skills/ folder contains reusable skill definitions for Claude Code:

• linked-intent-dev - Linked-intent development (LID) — structured workflow for design-before-code: HLD → LLD → EARS specs → Implementation plan

Key Insights

The shift from Copilot to agentic AI:

• Copilot: You write code, AI suggests completions
• Agentic AI: AI writes code, you steer and validate

What makes sessions effective:

1. Be detailed - “I see X when I expected Y” not “it’s broken”
2. Close the loop - Report results back, even just “yup”
3. Steer constantly - “Great. Now let’s…” every few exchanges
4. Validate assumptions - “What did you understand?” after work is done

The real anti-pattern isn’t “too many turns” - it’s frustrated circling. Exploration with back-and-forth is fine. Repeating “try again” without new information is the problem.

Data

The analysis_data_index.md file describes the raw data files used in this analysis, with query examples.

License

MIT - See LICENSE