Turns your method descriptions into LaTeX algorithm blocks and Mermaid diagrams that actually match your code. It generates pseudocode using the algorithmic package with proper Require/Ensure blocks, numbered lines, and standard notation, then creates corresponding UML class and sequence diagrams. The real value is in step 4: it enforces consistency between your pseudocode, diagrams, and implementation so parameter names and structure stay aligned. Best used when you're writing a paper and need to formalize an existing implementation, or when you're designing something new and want the documentation to guide the code. Saves you from the usual mess of pseudocode that doesn't match what you actually built.

skills.sh installs
1.7K
GitHub stars
459
last updated
Aug 21, 2026

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill algorithm-design --agent claude-code

Installs into .claude/skills of the current project.

Files

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

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

Step 2: Generate LaTeX Pseudocode

Use algorithm + algpseudocode environments:

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

Sponsors

Details

Repository
github.com/lingzhi227/agent-research-skills
Categories
AI & Agent Building, Data Science & ML, Sales & Marketing, Design & UI/UX
First seen
Jun 3, 2026

More from lingzhi227/agent-research-skills

All 31
1xtone avatarpr-triagextone/ai_development_toolsPRの変更内容をトリアージし、変更カテゴリ分類・表層チェック・必要リファレンス判定を行います。結果を`.pr-triage.json`に出力し、後続のコードレビューフェーズで活用します。CI環境でのコスト最適化に使用してください。1.7Kskills.sh installs
2sergiodxa avatarowasp-security-checksergiodxa/agent-skillsSecurity audit guidelines for web applications and REST APIs based on OWASP Top 10 and web security best practices. Use when checking code for vulnerabilities, 1.7Kskills.sh installs
3tinybirdco avatartinybirdtinybirdco/tinybird-agent-skillsTinybird file formats, SQL rules, optimization patterns, and best practices for datasources, pipes, endpoints, and materialized views.1.7Kskills.sh installs
4ailabs-393 avatarpitch-deckailabs-393/ai-labs-claude-skillsGenerate professional PowerPoint pitch decks for startups and businesses. Use this skill when users request help creating investor pitch decks, sales presentati1.7Kskills.sh installs
5ai-native-camp avatarday1-onboardingai-native-camp/camp-1AI Native Camp Day 1 온보딩. Claude와 대화하면서 Claude Code를 익힌다. "1일차", "Day 1", "온보딩" 요청에 사용.1.7Kskills.sh installs
6mapbox avatarmapbox-store-locator-patternsmapbox/mapbox-agent-skillsCommon patterns for building store locators, restaurant finders, and location-based search applications with Mapbox. Covers marker display, filtering, distance 1.7Kskills.sh installs