superpowers
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSuperpowers
核心能力框架
A structured software development framework that transforms how coding agents approach development—preventing the "write code immediately" antipattern.
一个结构化的软件开发框架，能够改变编码Agent的开发方式——避免“立即写代码”的反模式。
When to Use This Skill
何时使用该Skill
- Complex feature development
- Multi-file refactoring
- Test-driven development
- Code review processes
- Systematic debugging
- Team collaboration with AI
- 复杂功能开发
- 多文件重构
- 测试驱动开发
- 代码审查流程
- 系统化调试
- AI团队协作
The Philosophy
核心理念
Traditional AI coding:
User: "Add auth to the app"
AI: *immediately writes 500 lines of code*Superpowers approach:
User: "Add auth to the app"
AI: "Let me understand requirements first..."
→ Questions → Design → Plan → Execute → Review传统AI编码方式：
User: "Add auth to the app"
AI: *immediately writes 500 lines of code*核心能力框架方法：
User: "Add auth to the app"
AI: "Let me understand requirements first..."
→ Questions → Design → Plan → Execute → ReviewCore Workflow
核心工作流
Phase 1: Understanding
阶段1：需求理解
1. Ask clarifying questions
2. Explore existing codebase
3. Understand constraints
4. Validate assumptions1. Ask clarifying questions
2. Explore existing codebase
3. Understand constraints
4. Validate assumptionsPhase 2: Design
阶段2：设计规划
1. Create isolated workspace (git branch)
2. Break work into 2-5 minute tasks
3. Define exact specifications
4. Get approval before coding1. Create isolated workspace (git branch)
2. Break work into 2-5 minute tasks
3. Define exact specifications
4. Get approval before codingPhase 3: Execution
阶段3：执行开发
1. RED: Write failing test
2. GREEN: Minimum code to pass
3. REFACTOR: Clean up
4. Review before next task1. RED: Write failing test
2. GREEN: Minimum code to pass
3. REFACTOR: Clean up
4. Review before next taskPhase 4: Review
阶段4：审查验证
1. Specification compliance check
2. Code quality review
3. Integration verification
4. Branch completion decision1. Specification compliance check
2. Code quality review
3. Integration verification
4. Branch completion decisionKey Principles
核心原则
1. Design Before Code
1. 先设计后编码
Never write code without understanding:
- What problem are we solving?
- What are the constraints?
- How does it fit existing code?
- What are the edge cases?
在未明确以下内容前，绝不编写代码：
- 我们要解决什么问题？
- 有哪些约束条件？
- 如何适配现有代码？
- 存在哪些边缘情况？
2. Small, Focused Tasks
2. 小而聚焦的任务
Each task should be:
- Completable in 2-5 minutes
- Single responsibility
- Independently testable
- Clear success criteria
每个任务应满足：
- 可在2-5分钟内完成
- 单一职责
- 可独立测试
- 明确的成功标准
3. Test-First Development
3. 测试优先开发
RED → GREEN → REFACTOR- Write test first
- Minimum code to pass
- Clean up afterward
- Never skip this cycle
RED → GREEN → REFACTOR- 先编写测试用例
- 编写最少代码以通过测试
- 事后优化代码
- 绝不跳过该循环
4. Systematic, Not Ad-hoc
4. 系统化而非随意化
┌─────────────────────────────────────┐
│ Systematic vs. Ad-hoc │
├─────────────────────────────────────┤
│ Plan then execute │ Jump in │
│ Verify with tests │ Hope it works│
│ Review each step │ Review at end│
│ Evidence-based │ Assumption │
└─────────────────────────────────────┘┌─────────────────────────────────────┐
│ Systematic vs. Ad-hoc │
├─────────────────────────────────────┤
│ Plan then execute │ Jump in │
│ Verify with tests │ Hope it works│
│ Review each step │ Review at end│
│ Evidence-based │ Assumption │
└─────────────────────────────────────┘5. Evidence Over Assumption
5. 基于证据而非假设
- Don't assume code works—verify
- Don't assume understanding—validate
- Don't assume completion—prove
- 绝不假设代码可行——需验证
- 绝不假设已理解需求——需确认
- 绝不假设任务完成——需证明
Skills Library
技能库
Testing
测试技能
- Unit test patterns
- Integration testing
- Test coverage analysis
- Mocking strategies
- 单元测试模式
- 集成测试
- 测试覆盖率分析
- 模拟策略
Debugging
调试技能
1. Reproduce the issue
2. Isolate the cause
3. Root cause analysis
4. Verify the fix
5. Prevent regression1. Reproduce the issue
2. Isolate the cause
3. Root cause analysis
4. Verify the fix
5. Prevent regressionCollaboration
协作技能
- Brainstorming: Explore options
- Planning: Structure approach
- Parallel execution: Multiple agents
- Review: Quality gates
- 头脑风暴：探索多种方案
- 规划：构建结构化方法
- 并行执行：多Agent协作
- 审查：质量管控关卡
Meta-Skills
元技能
- Extending the framework
- Custom skill creation
- Workflow optimization
- 扩展框架
- 自定义技能创建
- 工作流优化
How to Use
使用方法
Starting a Feature
启动新功能开发
I want to add user authentication.
Help me think through:
1. What auth mechanism?
2. Session vs JWT?
3. Where to store credentials?
4. What existing code to modify?I want to add user authentication.
Help me think through:
1. What auth mechanism?
2. Session vs JWT?
3. Where to store credentials?
4. What existing code to modify?During Development
开发过程中
I'm implementing the login endpoint.
Current state:
- User model exists
- Password hashing ready
Next: Create POST /login endpoint
Tests first, then implementation.I'm implementing the login endpoint.
Current state:
- User model exists
- Password hashing ready
Next: Create POST /login endpoint
Tests first, then implementation.Code Review
代码审查
Review my changes:
[paste diff]
Check against:
- Original spec
- Test coverage
- Code quality
- Security concernsReview my changes:
[paste diff]
Check against:
- Original spec
- Test coverage
- Code quality
- Security concernsExample: Adding a Feature
示例：添加新功能
1. Discovery
1. 需求探索
User: "Add forgot password feature"
Agent: "Before we start, let me understand:
1. How should the reset link be delivered? (email?)
2. What's the token expiry? (1 hour?)
3. Should we rate limit attempts?
4. Any existing email infrastructure?"User: "Add forgot password feature"
Agent: "Before we start, let me understand:
1. How should the reset link be delivered? (email?)
2. What's the token expiry? (1 hour?)
3. Should we rate limit attempts?
4. Any existing email infrastructure?"2. Planning
2. 任务规划
Tasks:
1. Create password_reset_tokens table
2. Add POST /forgot-password endpoint
3. Add POST /reset-password endpoint
4. Create email template
5. Add rate limiting middlewareTasks:
1. Create password_reset_tokens table
2. Add POST /forgot-password endpoint
3. Add POST /reset-password endpoint
4. Create email template
5. Add rate limiting middleware3. Execution (Task 1)
3. 执行开发（任务1）
undefinedundefinedTask: Create password_reset_tokens table
Task: Create password_reset_tokens table
Test (RED)
Test (RED)
- Test migration creates table
- Test table has correct columns
- Test migration creates table
- Test table has correct columns
Implementation (GREEN)
Implementation (GREEN)
- Create migration file
- Define schema
- Create migration file
- Define schema
Verify
Verify
- Run migration
- Check table exists
undefined- Run migration
- Check table exists
undefined4. Review
4. 审查验证
undefinedundefinedTask 1 Complete
Task 1 Complete
✓ Migration runs successfully
✓ Table has: id, user_id, token, expires_at
✓ Foreign key constraint works
Ready for Task 2?
undefined✓ Migration runs successfully
✓ Table has: id, user_id, token, expires_at
✓ Foreign key constraint works
Ready for Task 2?
undefinedBest Practices
最佳实践
- Don't Rush: Speed comes from fewer mistakes
- Ask Questions: Clarify before implementing
- Small Steps: Easier to verify and debug
- Test Everything: Trust comes from evidence
- Review Often: Catch issues early
- 勿急于求成：速度源于更少的错误
- 积极提问：在实现前先明确需求
- 小步迭代：更易于验证和调试
- 全面测试：信任源于证据
- 频繁审查：尽早发现问题
Integration
集成支持
Available for:
- Claude Code: Via marketplace
- Codex: Plugin installation
- OpenCode: Direct integration
目前支持以下平台：
- Claude Code：通过应用市场
- Codex：插件安装
- OpenCode：直接集成
Anti-Patterns to Avoid
需避免的反模式
- Writing code without understanding requirements
- Skipping tests "to save time"
- Large PRs with multiple concerns
- Assuming code works without verification
- Declaring done without evidence
- 未理解需求就编写代码
- 为“节省时间”跳过测试
- 包含多个关注点的大型PR
- 未验证就假设代码可行
- 无证据就宣称任务完成