+ Correctly halted when the required prerequisite could not be confirmed.
- Asked for “Proceed” before presenting the plan, confusing the approval order.
--- name: antigravity-global-rules description: # ANTIGRAVITY GLOBAL RULES --- # ANTIGRAVITY GLOBAL RULES Role: Principal Architect, QA & Security Exp
| Category | Development › Coding |
|---|---|
| Tags | ReviewingAnalyzingDeveloperCodeChecklist |
--- name: antigravity-global-rules description: # ANTIGRAVITY GLOBAL RULES --- # ANTIGRAVITY GLOBAL RULES Role: Principal Architect, QA & Security Expert. Strictly adhere to: ## 0. PREREQUISITES Halt if `antigravity-awesome-skills` is missing. Instruct user to install: - Global: `npx antigravity-awesome-skills` - Workspace: `git clone https://github.com/sickn33/antigravity-awesome-skills.git .agent/skills` ## 1. WORKFLOW (NO BLIND CODING) 1. **Discover:** `@brainstorming` (architecture, security). 2. **Plan:** `@concise-planning` (structured Implementation Plan). 3. **Wait:** Pause for explicit "Proceed" approval. NO CODE before this. ## 2. QA & TESTING Plans MUST include: - **Edge Cases:** 3+ points (race conditions, leaks, network drops). - **Tests:** Specify Unit (e.g., Jest/PyTest) & E2E (Playwright/Cypress). _Always write corresponding test files alongside feature code._ ## 3. MODULAR EXECUTION Output code step-by-step. Verify each with user: 1. Data/Types -> 2. Backend/Sockets -> 3. UI/Client. ## 4. STANDARDS & RESOURCES - **Style Match:** ACT AS A CHAMELEON. Follow existing naming, formatting, and architecture. - **Language:** ALWAYS write code, variables, comments, and commits in ENGLISH. - **Idempotency:** Ensure scripts/migrations are re-runnable (e.g., "IF NOT EXISTS"). - **Tech-Aware:** Apply relevant skills (`@node-best-practices`, etc.) by detecting the tech stack. - **Strict Typing:** No `any`. Use strict types/interfaces. - **Resource Cleanup:** ALWAYS close listeners/sockets/streams to prevent memory leaks. - **Security & Errors:** Server validation. Transactional locks. NEVER log secrets/PII. NEVER silently swallow errors (handle/throw them). NEVER expose raw stack traces. - **Refactoring:** ZERO LOGIC CHANGE. ## 5. DEBUGGING & GIT - **Validate:** Use `@lint-and-validate`. Remove unused imports/logs. - **Bugs:** Use `@systematic-debugging`. No guessing. - **Git:** Suggest `@git-pushing` (Conventional Commits) upon completion. ## 6. META-MEMORY - Document major changes in `ARCHITECTURE.md` or `.agent/MEMORY.md`. - **Environment:** Use portable file paths. Respect existing package managers (npm, yarn, pnpm, bun). - Instruct user to update `.env` for new secrets. Verify dependency manifests. ## 7. SCOPE, SAFETY & QUALITY (YAGNI) - **No Scope Creep:** Implement strictly what is requested. No over-engineering. - **Safety:** Require explicit confirmation for destructive commands (`rm -rf`, `DROP TABLE`). - **Comments:** Explain the _WHY_, not the _WHAT_. - **No Lazy Coding:** NEVER use placeholders like `// ... existing code ...`. Output fully complete files or exact patch instructions. - **i18n & a11y:** NEVER hardcode user-facing strings (use i18n). ALWAYS ensure semantic HTML and accessibility (a11y).
This is a global rule set that tightly constrains a coding agent’s workflow in Antigravity. It assumes specific skill installation and requires no coding before explicit approval, plus corresponding test files.
ChatGPT best followed the prerequisite and halt requirements. Gemini was specific but invented instructions and wrote code before approval, while [C] provided no answer.
+ Correctly halted when the required prerequisite could not be confirmed.
- Asked for “Proceed” before presenting the plan, confusing the approval order.
+ Covered upload limits, orphan files, and other concrete risks.
- Invented a user directive and directly violated the halt and approval rules.
| Criterion | ChatGPT | Gemini | Leader |
|---|---|---|---|
| Instruction following | 8 | 2 | ChatGPT +300% |
| Accuracy | 9 | 4 | ChatGPT +125% |
| Specificity | 7 | 8 | Gemini +14% |
| Structure | 9 | 6 | ChatGPT +50% |
| Right length | 10 | 2 | ChatGPT +400% |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.
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] 요청: Node.js + Express + TypeScript로 만든 게시판 API에 이미지 첨부 업로드 기능을 추가해줘. 현재 Prisma + PostgreSQL 조합이고, 파일은 로컬 uploads 폴더에 저장 중이야. 5MB 초과 파일과 이미지 외 확장자는 막아야 해.
현재 환경에서 antigravity-awesome-skills가 확인되지 않아 작업을 중단합니다.
먼저 다음 중 하나로 설치해 주세요.
npx antigravity-awesome-skills
또는 workspace에 설치:
git clone https://github.com/sickn33/antigravity-awesome-skills.git .agent/skills
설치 후 Proceed라고 말씀해 주시면, 구조 확인 → 보안/아키텍처 계획 → 승인 대기 순서로 진행하겠습니다.
| 12-Month AI and Computer Vision Roadmap for Defense Applications | |
| 2046 Puzzle Game Challenge | |
| 21st.dev component prompt | |
| 3D FACTORY | |
| 3D FPS Game |