44/ 50
＋ Accurately summarizes the core changes in one line
－ feat may fit this newly added security behavior better
Conventional Commit Message Generator
a conventional commit message generator following the Conventional Commits specification.
| Category | Development › Coding |
|---|---|
| Tags | DraftingReformattingDeveloperCode |
I want you to act as a conventional commit message generator following the Conventional Commits specification. I will provide you with git diff output or description of changes, and you will generate a properly formatted commit message. The structure must be: <type>[optional scope]: <description>, followed by optional body and footers. Use these commit types: feat (new features), fix (bug fixes), docs (documentation), style (formatting), refactor (code restructuring), test (adding tests), chore (maintenance), ci (CI changes), perf (performance), build (build system). Include scope in parentheses when relevant (e.g., feat(api):). For breaking changes, add ! after type/scope or include BREAKING CHANGE: footer. The description should be imperative mood, lowercase, no period. Body should explain what and why, not how. Include relevant footers like Refs: #123, Reviewed-by:, etc. (This is just an example, make sure do not use anything from in this example in actual commit message). The output should only contains commit message. Do not include markdown code blocks in output. My first request is: "I need help generating a commit message for my recent changes".
What this prompt does
This is useful for stricter Conventional Commits message generation. It says not to reuse the example and asks for only the message, without Markdown code blocks.
Model comparison
ChatGPT is the most accurate and concise. Gemini is specific but adds inference, while [C] is missing.
41/ 50
＋ Clearly details the threshold and counter behavior
－ The diff lacks timed unlocking and stated rationale
| Criterion | ChatGPT | Gemini | Leader |
|---|---|---|---|
| Instruction following | 9 | 8 | ChatGPT +13% |
| Accuracy | 9 | 7 | ChatGPT +29% |
| Specificity | 9 | 9 | Tie |
| Structure | 8 | 9 | Gemini +13% |
| Right length | 9 | 8 | ChatGPT +13% |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-25). This is an AI review, not a measurement.
Read full answers
We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.
[Pasted material]
다음은 최근 변경사항의 git diff야. 이걸 바탕으로 커밋 메시지를 만들어줘.
diff --git a/src/services/auth.service.ts b/src/services/auth.service.ts
index 3f2a1c9..8b6e2fd 100644
--- a/src/services/auth.service.ts
+++ b/src/services/auth.service.ts
@@ -12,6 +12,14 @@ export class AuthService {
async login(email: string, password: string) {
const user = await this.userRepo.findByEmail(email);
if (!user) throw new UnauthorizedException('사용자를 찾을 수 없습니다.');
+
+ if (user.failedLoginCount >= 5) {
+ throw new ForbiddenException('로그인 시도 횟수를 초과했습니다. 30분 후 다시 시도해주세요.');
+ }
+
const isMatch = await bcrypt.compare(password, user.passwordHash);
if (!isMatch) {
+ await this.userRepo.incrementFailedLoginCount(user.id);
throw new UnauthorizedException('비밀번호가 일치하지 않습니다.');
}
+ await this.userRepo.resetFailedLoginCount(user.id);
return this.generateToken(user);
}
}fix(auth): 로그인 실패 횟수 제한 및 성공 시 카운터 초기화
More in this category
| 12-Month AI and Computer Vision Roadmap for Defense Applications | |
| 2046 Puzzle Game Challenge | |
| 21st.dev component prompt | |
| 3D FACTORY | |
| 3D FPS Game |