메뉴
Code quality enforcement, linting, type checking, and best practices. Use after every code change to ensure production-grade quality. Integrates with ruff, mypy, pylint, and other quality tools.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
DEEP multi-step research harness. Decomposes queries into sub-questions, executes parallel web searches via Pieces MCP, iteratively refines with gap detection, and synthesizes cited reports. Architecture inspired by GPT Researcher (27.6k stars), Vane/Perplexica (35.2k stars), and Gemini Deep Research. Use when user asks for deep research, investigation, analysis, comparison, or any task requiring exhaustive web research.
DEFAULT THINKING MODE — not a feature, but how the agent operates. Every task gets innovation-overdrive thinking: research, ground, reflect on contradictions, propose, then build. This is the agent's identity, not a command. Integrates MiMo-Code's 6-phase memory consolidation.
Chain execution manager: validates dependencies, enforces order, tracks violations. Use to verify that all required skill chains were executed and to get the correct execution order.
API design patterns, REST conventions, and endpoint standards. Use when creating or modifying API endpoints. Covers routing, request/response patterns, error handling, and versioning.
Architectural design, system patterns, and dependency management. Use when designing new modules, refactoring existing systems, or making architectural decisions. Covers layering, coupling, cohesion, and design patterns.
Trigger-driven automation definitions and runner management. Use when creating, running, or managing skill-based automation pipelines.
| name | quality |
| description | Code quality enforcement, linting, type checking, and best practices. Use after every code change to ensure production-grade quality. Integrates with ruff, mypy, pylint, and other quality tools. |
| chains_with | ["lint-fixer","automated-learning"] |
Every file that touches the codebase must pass the quality gate. No exceptions.
Fire this skill ALWAYS after completing implementation. Must be the final step before presenting results to the user.
# Python
ruff check src/ tests/ benchmarks/
ruff check --fix src/ tests/ benchmarks/
ruff format --check src/ tests/
# Type checking
mypy src/
# Import sorting
ruff check --select I src/ tests/
# Run all tests
python -m pytest tests/ -x -q
# Run with coverage
python -m pytest tests/ --cov=src/ --cov-report=term
# Run benchmarks (smoke)
python -m pytest benchmarks/ --benchmark-min-rounds=1 -x -q
| Check | Tool | What to fix |
|---|---|---|
| Unused imports | ruff F401 | Remove or use |
| Unused variables | ruff F841 | Remove or prefix with _ |
| Bare except | ruff E722 | Specify exception type |
| Mutable defaults | ruff B006 | Use None + if x is None |
| Line too long | ruff E501 | Break lines |
| Missing type hints | mypy | Add annotations |
| Any return type | mypy | Be specific |
| Untyped dict/list | mypy | Use dict[str, Any] |
# ESLint
npx eslint --fix src/
# TypeScript
npx tsc --noEmit
# Prettier
npx prettier --write src/
For quick quality checks during development:
# Fastest: just static analysis
ruff check src/
# Medium: static + types
ruff check src/ && mypy src/
# Full: everything
ruff check src/ && mypy src/ && pytest tests/ -x -q
| Issue Count | Action |
|---|---|
| 0 | Ship it |
| 1-3 | Fix all, recheck |
| 4-10 | Flag to user, discuss priority |
| 10+ | STOP. Major quality issue. |