菜单
Code smell detection and safe incremental refactoring patterns. Use when improving code structure, reducing technical debt, or cleaning up after a TDD cycle. Covers SOLID principles, smell catalog, and the propose-apply workflow.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Workflow for investigating and reproducing bugs before fixing via TDD. Use when a bug report or GitHub issue is received. Covers issue fetching, root cause analysis, reproduction planning, and handoff to TDD cycle.
CRAP score quality gate for code complexity and test coverage. Use when reviewing methods for complexity risk, deciding whether to split methods, or determining minimum test coverage requirements.
Five independent analysis perspectives for code review: correctness, architecture, security, conventions, and complexity. Use when reviewing PRs, commits, or local changes. Includes severity model and output format.
Index of Architecture Decision Records (ADRs) for cross-cutting technical decisions. Use when making design choices, reviewing proposals for consistency with prior decisions, or onboarding to understand why specific tools or patterns were chosen. Covers test tooling, SDK architecture, code quality, and acceptance test infrastructure.
Git commit messages, PR workflow, and branching strategy using Conventional Commits and Semantic Versioning. Use when creating commits, pull requests, or managing Git workflow.
Security guardrails for Envilder (CLI, GitHub Action, SDKs, CDK, website). Covers secret handling, credential hygiene, supply chain safety, input validation, and CI/CD security. Use when reviewing code for security, handling secrets, validating CLI input, or reviewing GitHub Actions workflows.
| name | code-refactoring |
| description | Code smell detection and safe incremental refactoring patterns. Use when improving code structure, reducing technical debt, or cleaning up after a TDD cycle. Covers SOLID principles, smell catalog, and the propose-apply workflow. |
Detect code smells and apply safe, incremental refactoring while preserving all existing behavior.
| Smell | Indicator |
|---|---|
| Long method | > 20 lines or doing multiple things |
| Large class | Multiple responsibilities |
| Duplicated logic | Same pattern in 2+ places |
| Tight coupling | Direct dependency on concrete implementations |
| Mixed abstraction levels | High/low-level operations in same method |
| SRP violation | Class/method has multiple reasons to change |
| Architecture boundary violation | Domain importing infrastructure |
| Feature envy | Method uses another class's data more than its own |
Present opportunities before applying:
## Refactoring Opportunities
| # | Smell | Location | Proposed Change | Risk |
|---|-------|----------|-----------------|------|
| 1 | {smell} | {file:line} | {what to do} | Low/Med |
Wait for confirmation before applying.
For each approved refactoring:
pnpm test after each changepnpm lint to verify formatting## Refactoring Complete
**Applied:** {N} of {M} proposed changes
**Tests:** all passing ✓
**Formatter:** ran ✓
### Changes
1. {file}: {what changed}
| Principle | Quick check |
|---|---|
| Single Responsibility | Does this class/method have one reason to change? |
| Open/Closed | Can I extend without modifying existing code? |
| Liskov Substitution | Can subtypes replace base without breaking behavior? |
| Interface Segregation | Are interfaces focused (no unused methods)? |
| Dependency Inversion | Do high-level modules depend on abstractions? |