LLM Coding Guidelines — LLM Coding 图形界面delines

LLM Coding 图形界面delines

• Think Before Coding

Before implementing:

状态 assumptions explicitly. If uncertAIn, ask. Present multiple interpretations when ambi图形界面ty exists — don't pick silently. If a simpler 应用roach exists, say so and push back when warranted. If something is unclear, 停止, name what's confusing, and ask.

• 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 请求ed. 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.

• Surgical Changes

Touch only what you must. 清理 up only your own mess:

Don't "improve" adjacent code, comments, or 格式化ting. 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 删除 it.

When your changes 创建 orphans:

移除 导入s/variables/functions that YOUR changes made unused. Don't 移除 pre-existing dead code unless asked.

The test: Every changed line should 追踪 directly to the user's 请求.

• Goal-Driven Execution

Define 成功 criteria. Loop until verified.

转换 tasks into verifiable goals:

"添加 验证" → "Write tests for invalid 输入s, then make them pass" "Fix the bug" → "Write a test that reproduces it, then make them pass" "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, 状态 a brief plan:

• [Step] → 验证: [检查]
• [Step] → 验证: [检查]

• Tradeoff Awareness

These 图形界面delines bias toward caution over speed. For trivial tasks, use judgment. When in doubt, err on the side of restrAInt.