algorithm-design

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Algorithm Design

算法设计

Formalize methods into algorithm pseudocode and system architecture diagrams.

将方法形式化为算法伪代码和系统架构图。

Input

输入

```
$0
```
— Method description or implementation to formalize

```
$0$
```
— 待形式化的方法描述或实现代码

References

参考资料

Algorithm and diagram templates:

~/.claude/skills/algorithm-design/references/algorithm-templates.md

算法与图表模板：

~/.claude/skills/algorithm-design/references/algorithm-templates.md

Workflow

工作流程

Step 1: Formalize the Algorithm

步骤1：形式化算法

Define clear inputs and outputs
Identify the main loop / recursive structure
Specify all parameters and their types
Write step-by-step pseudocode

定义明确的输入和输出
识别主循环/递归结构
明确所有参数及其类型
编写分步伪代码

Step 2: Generate LaTeX Pseudocode

步骤2：生成LaTeX伪代码

Use

algorithm

algpseudocode

environments:

latex

\begin{algorithm}[t]
\caption{Method Name}
\label{alg:method}
\begin{algorithmic}[1]
\Require Input $x$, parameters $\theta$
\Ensure Output $y$
\State Initialize ...
\For{$t = 1$ to $T$}
    \State $z_t \gets f(x_t; \theta)$
    \If{convergence criterion met}
        \State \textbf{break}
    \EndIf
\EndFor
\State \Return $y$
\end{algorithmic}
\end{algorithm}

使用

algorithm

algpseudocode

环境：

latex

\begin{algorithm}[t]
\caption{Method Name}
\label{alg:method}
\begin{algorithmic}[1]
\Require Input $x$, parameters $\theta$
\Ensure Output $y$
\State Initialize ...
\For{$t = 1$ to $T$}
    \State $z_t \gets f(x_t; \theta)$
    \If{convergence criterion met}
        \State \textbf{break}
    \EndIf
\EndFor
\State \Return $y$
\end{algorithmic}
\end{algorithm}

Step 3: Generate UML Diagrams (Mermaid)

步骤3：生成UML图（Mermaid）

Class Diagram

类图

mermaid

classDiagram
    class Model {
        +forward(x: Tensor) Tensor
        +train_step(batch) float
    }

mermaid

classDiagram
    class Model {
        +forward(x: Tensor) Tensor
        +train_step(batch) float
    }

Sequence Diagram

序列图

mermaid

sequenceDiagram
    participant M as Main
    participant D as DataLoader
    M->>D: load_data()
    D-->>M: batches

mermaid

sequenceDiagram
    participant M as Main
    participant D as DataLoader
    M->>D: load_data()
    D-->>M: batches

Step 4: Verify Consistency

步骤4：验证一致性

Every pseudocode step must map to a code module
Every class in the UML must exist in the implementation
Parameter names must match between pseudocode and code

伪代码的每一步都必须对应到一个代码模块
UML中的每个类都必须在实现代码中存在
伪代码与代码中的参数名称必须一致

Rules

规则

Use standard algorithmic notation (not code syntax)
Number lines for easy reference
Include complexity analysis as a comment or proposition
Use
```
\Require
```
/
```
\Ensure
```
for inputs/outputs
Keep pseudocode at the right abstraction level — not too detailed, not too vague

使用标准算法符号（而非代码语法）
为代码行编号以便于引用
将复杂度分析作为注释或命题包含在内
使用
```
\Require
```
/
```
\Ensure
```
声明输入/输出
保持伪代码在合适的抽象层次——既不过于详细，也不过于模糊

algorithm-design

Original

Translation

Algorithm Design

算法设计

Input

输入

References

参考资料

Workflow

工作流程

Step 1: Formalize the Algorithm

步骤1：形式化算法

Step 2: Generate LaTeX Pseudocode

步骤2：生成LaTeX伪代码

Step 3: Generate UML Diagrams (Mermaid)

步骤3：生成UML图（Mermaid）

Class Diagram

类图

Sequence Diagram

序列图

Step 4: Verify Consistency

步骤4：验证一致性

Rules

规则

Related Skills

相关技能