这是目前 GitHub 前端/AI 圈最火的方向。因为大家都在用 AI 写代码，发现 AI 容易"放飞自我"（写得太复杂、乱改代码），所以大神们总结了一套**"如何让 AI 乖乖写代码"**的知识库。

  • 项目名称：`andrej-karpathy-skills` (或者叫 `CLAUDE.md` 规范)

  • 火爆程度：一周内冲上趋势榜第一，Star 数破 6 万。

  • 核心内容

    这不是代码，而是一份 Markdown 文档。它基于 AI 大神 Andrej Karpathy 的经验，总结了 4 条 AI 必须遵守的铁律：

    1. 编码前思考：遇到歧义先问，别瞎猜。
    2. 简洁优先：能用 50 行写完，绝不写 200 行（拒绝过度抽象）。
    3. 精准修改：只改必须改的地方，别顺手重构别人的代码。
    4. 目标驱动：先写测试复现 Bug，再修复它。

  • 怎么用：
    你可以直接把它的核心内容复制到你 Antigravity 的 `knowledge` 目录里，或者在项目根目录放一个 `CLAUDE.md` 文件。这能极大提升 AI 写前端代码的"听话程度"。

全局添加 Antigravity 的 Knowledge（知识库）非常简单，这相当于给你的 AI 装上一个"永久记忆体"。一旦配置好，无论你打开哪个项目，AI 都会自动读取这些规则，不需要重复配置。

以下是具体的操作步骤：

第一步：找到或创建全局目录

`Antigravity`的全局配置通常存储在用户主目录下的 `.gemini` 文件夹中。

  1. 打开文件资源管理器（Windows）或 访达（Mac）。

  2. 进入以下路径

    • Windows: `C:\\Users\\你的用户名\\.gemini\\antigravity\\`
    • Mac / Linux: `~/.gemini/antigravity/`

  3. 检查目录

    查看是否存在名为 `knowledge` 的文件夹。

    • 如果没有：请手动新建一个文件夹，命名为 `knowledge`。

小贴士：`.gemini` 是隐藏文件夹。

  • Windows: 如果看不到，需要在查看选项中勾选"隐藏的项目"。
  • Mac: 在访达中按 `Command + Shift + .` 可以显示隐藏文件。

把对应的CLAUDE.md放在`knowledge`这个文件夹下面即可

```markdown

CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" -> "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" -> "Write a test that reproduces it, then make it pass"
  • "Refactor X" -> "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

  1. [Step] -> verify: [check]
  2. [Step] -> verify: [check]
  3. [Step] -> verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
```

Trae 的全局配置通常在用户主目录下：
Windows: `C:\\Users\\你的用户名\\.trae\\`
Mac: `~/.trae/`
创建规则文件
在 .trae 目录下，找到或新建一个名为 rules 或 knowledge 的文件夹。