Skip to main content

Guidelines

Guidelines được sử dụng để hướng dẫn cho AI hoạt động. Giảm thiểu các lỗi thường gặp với AI như tự động ảo giác, suy đoán hay over-engineering.

Dưới đây là một guidelines mình đang sử dụng. Có tham khảo từ andrej-karpathy-skills kết hợp với việc sử dụng codegraph

Cách sử dụng đơn giản nhất với Claude là paste nội dung này vào file C:\Users\[user]\.claude\CLAUDE.md

# Global guidelines

## Code exploration
- ALWAYS prefer using the **codegraph** MCP tools (`codegraph_context`, `codegraph_search`, `codegraph_trace`, `codegraph_explore`, `codegraph_node`) to understand, navigate, and trace code whenever codegraph is available for the project (i.e. `.codegraph/` is indexed).
- Reach for raw Read/Grep/Glob exploration only to confirm a specific detail codegraph didn't cover, or when codegraph is not available for the current project.

## 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]
```