Algorithm Design

by lingzhi2279e6c085d65e3No license386 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 7 months ago

Design algorithms with LaTeX pseudocode and UML diagrams. Generate algorithmic environments, Mermaid class/sequence diagrams, and ensure consistency between pseudocode and implementation. Use when formalizing methods for a paper.

Instructions onlyResearch & Analysis Software Development

AI-generated overview

Formalizes methods into LaTeX algorithm pseudocode and Mermaid UML diagrams, checking consistency with code.

What it does: Turns a method description or implementation into formal algorithm pseudocode written with LaTeX algorithm and algpseudocode environments, including inputs, outputs, parameters and numbered steps. It also produces Mermaid class and sequence diagrams for the system architecture. Finally it verifies that pseudocode steps, UML classes and parameter names match the implementation.
When to use it: Use when formalizing a method for a paper or technical write-up that needs standard algorithmic notation. It suits work where pseudocode and architecture diagrams must stay consistent with existing code.
Requirements: Needs LaTeX with the algorithm and algpseudocode packages for the pseudocode output, and Mermaid support for the diagrams. It reads a bundled reference file of algorithm and diagram templates. No scripts are shipped; instructions only.

Algorithm Design

Formalize methods into algorithm pseudocode and system architecture diagrams.

Input

$0 — Method description or implementation to formalize

References

Algorithm and diagram templates: ~/.claude/skills/algorithm-design/references/algorithm-templates.md

Workflow

Step 1: Formalize the Algorithm

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

Step 2: Generate LaTeX Pseudocode

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}

\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)

Class Diagram

mermaid

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

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

Sequence Diagram

mermaid

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

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

Step 4: Verify Consistency

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

Rules

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

Related Skills

Upstream: atomic-decomposition, math-reasoning
Downstream: experiment-code, paper-writing-section
See also: symbolic-equation

Source and attribution

Source:lingzhi227/agent-research-skillsinskills/algorithm-designat commit9e6c085

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Algorithm Design

Algorithm Design

Input

References

Workflow

Step 1: Formalize the Algorithm

Step 2: Generate LaTeX Pseudocode

Step 3: Generate UML Diagrams (Mermaid)

Class Diagram

Sequence Diagram

Step 4: Verify Consistency

Rules

Related Skills

Source and attribution

More from lingzhi227/agent-research-skills

Table Generation

Symbolic Equation

Survey Generation

Slide Generation

Self Review

Research Planning

More in Research & Analysis

Equity Research

Sector Overview

Idea Generation

Competitive Analysis

Notion Research Documentation

Notion Meeting Intelligence