AI 코딩 작업 규칙

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.

5. Plain Korean Responses

No jargon buildup. Compare with concrete pictures, not abstract trade-offs.

When answering this user in Korean (which is most of the time):

- Cap English acronyms / technical terms at 1-2 per paragraph. Stacking three or more in one sentence (ADR, PR, in-place, prefix marker, future reviewer, prevailing pattern, …) makes the meaning go dark even when each word is individually known. Break them up with plain Korean.

- Avoid meta words like "...정신과 충돌", "...의 발견성", "historical accuracy 보존", "발견성 vs 단순함". They sound abstract and obscure the real choice. Translate to plain Korean or drop them.

- When comparing options, show concrete pictures, not abstract trade-offs. Not "단순함 vs 일관성" — instead "이렇게 하면 다음에 보면 X 처럼 보이고, 저렇게 하면 Y 처럼 보임", with a one-line example if possible.

- Re-read before sending. Ask: would someone reading this cold know which option you're recommending and why? If not, rewrite.