awesome-ai-coding-techniques — AI Agent 工作流中文教程

Requirements & Planning

Generate Code, Not Dependencies

Write custom code rather than pulling in more libraries when working with assistants.

Community adoption: 27% situational • Vote on coding-with-ai.dev (n=30)

"Be even more conservative about upgrades than before... I strongly prefer more code generation over using more dependencies." — Armin Ronacher

Build a Prototype First

Start every project with a quick generated prototype to prove it can work.

Community adoption: 44% situational • Vote on coding-with-ai.dev (n=34)

"The best way to start any project is with a prototype that proves that the key requirements of that project can be met. I often find that an LLM can get me to that working prototype within a few minutes of me sitting down with my laptop—or sometimes even while working on my phone." — Simon Willison

Build Fast, Foolproof Tools

Create tools that respond quickly, provide clear error messages, and protect against misuse by agents.

Community adoption: 17% essential • Vote on coding-with-ai.dev (n=12)

"Tools need to be fast. The quicker they respond (and the less useless output they produce) the better. Crashes are tolerable; hangs are problematic. Tools need to be user friendly! Tools must clearly inform agents of misuse or errors to ensure forward progress. Tools need to be protected against an LLM chaos monkey using them completely wrong. There is no such thing as user error or undefined behavior!" — Armin Ronacher

Show Screenshots

Drop in screenshots and iterate - take a screenshot of the result, compare, repeat.

Community adoption: 38% situational • Vote on coding-with-ai.dev (n=29)

"Give Claude a visual mock by copying / pasting or drag-dropping an image... take screenshots of the result, and iterate until its result matches the mock." — Anthropic

Get Multiple Options

Ask LLM to present several approaches with pros/cons so you can choose the best option.

Community adoption: 57% essential • Vote on coding-with-ai.dev (n=51)

"I'll use prompts like what are options for HTTP libraries in Rust? Include usage examples" — Simon Willison

Testing & QA

Ask Open Questions, Not Leading Ones

Avoid 'Am I right that...' questions - instead ask for pros/cons, alternatives, and 'What am I missing?' to counteract LLM's tendency to agree.

"My best current technique for avoiding this is a bit of role-play that gives the coding agent a reason not to blindly trust the code review... 'A reviewer did some analysis of this PR. They're external, so reading the codebase cold... 1) should we hire this reviewer 2) which of the issues they've flagged should be fixed?'" — Jesse Vincent