# k-dense-ai/claude-scientific-skills architecture

> Architecture diagram of the GitHub repository k-dense-ai/claude-scientific-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-10-23). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/k-dense-ai/claude-scientific-skills
- Repository: https://github.com/k-dense-ai/claude-scientific-skills

## Overview

##### Project type and purpose
- This is an open‐source “Claude Code” plugin repository (monorepo) containing a large set of Python “skills” (code + docs) for scientific domains.
- Its purpose is to register with the Claude Code or any MCP‐compatible client and provide:
- 24 database‐access skills
- 43 scientific‐package skills
- 6 lab‐integration skills
- 1 context‐initialization skill
- 122 documented workflows
- Extensive documentation and code examples

##### File structure
- Top‐level files:
- marketplace.json (plugin manifest)
- README.md, LICENSE.md, .github/workflows (CI/CD)
- docs/*.md (overview docs)
- Skill directories (monolithic layout by category):
- scientific-databases/…
- scientific-packages/…
- scientific-integrations/…
- scientific-helpers/…
- scientific-thinking/…
- Each skill subdirectory contains:
- SKILL.md (describes the skill)
- references/ (API docs, endpoint lists)
- scripts/ (executable Python examples)
- No backend server or database; this is “code + docs” only.

##### README for additional insights
- Describes how to install as a Claude plugin or via any MCP client.
- Explains plugin categories, counts, use cases, quick examples.
- Mentions CI (release.yml) and license constraints.

##### Elements
- Labels:
- “User”
- “MCP Client / Claude Code”
- “Plugin Marketplace (GitHub + marketplace.json)”
- “Plugin Loader”
- “External Python Libraries” (RDKit, Scanpy, etc.)
- “CI/CD Pipeline”
- user→client→marketplace→loader→skill
- skill→external library
- commit→CI/CD→release
- Skill categories in another (domain modules)
- CI/CD in a third (automation)
- External dependencies in a fourth (libraries)

##### Detail
- **all five** top‐level categories as separate components.
- Within each, illustrate one or two example skill subdirectories.
- Plugin manifest (marketplace.json) as the discovery artifact.
- Flow: “Prompt → Skill Selector → Skill Script → External call → Return result.”
- Don’t overcomplicate – broad separation by component/domain is sufficient.

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Actors and External
    User["User"]:::external
    Client["MCP Client<br/>/ Claude Code"]:::integration

    %% Plugin Discovery & Loading
    Marketplace["Plugin Marketplace<br/>(GitHub)"]:::integration
    Manifest["marketplace.json"]:::integration
    Loader["Plugin Loader"]:::integration

    %% Documentation
    Docs["README.md"]:::docs
    DocsDB["docs/scientific-databases.md"]:::docs
    DocsPKG["docs/scientific-packages.md"]:::docs
    DocsINT["docs/scientific-integrations.md"]:::docs
    DocsTHINK["docs/scientific-thinking.md"]:::docs
    License["LICENSE.md"]:::docs

    %% CI/CD
    CI["CI/CD Pipeline<br/>(GitHub Actions)"]:::automation

    %% Skill Categories and Modules
    subgraph "Skill Categories" 
        direction TB
        subgraph "scientific-databases" 
            direction TB
            Alphafold["Alphafold Skill<br/>SKILL.md"]:::domain
            Chembl["ChEMBL Example<br/>example_queries.py"]:::domain
        end
        subgraph "scientific-packages" 
            direction TB
            Scanpy["Scanpy Skill<br/>qc_analysis.py"]:::domain
        end
        subgraph "scientific-integrations" 
            direction TB
            Benchling["Benchling Integration<br/>SKILL.md"]:::domain
        end
        subgraph "scientific-helpers" 
            direction TB
            ContextInit["Context Init<br/>SKILL.md"]:::domain
        end
        subgraph "scientific-thinking" 
            direction TB
            ThinkingDoc["Other Thinking Skills"]:::domain
        end
    end

    %% External Dependencies
    ExtLib["External Python Libs<br/>(RDKit, Scanpy, etc.)"]:::dependencies

    %% Flows
    User -->|"installs"| Client
    Client -->|"fetches"| Marketplace
    Marketplace -->|"reads"| Manifest
    Client -->|"loads"| Loader
    Loader -->|"discovers"| Manifest
    Loader -->|"registers"| Alphafold
    Loader -->|"registers"| Chembl
    Loader -->|"registers"| Scanpy
    Loader -->|"registers"| Benchling
    Loader -->|"registers"| ContextInit
    Loader -->|"registers"| ThinkingDoc
    Alphafold -->|"imports"| ExtLib
    Chembl -->|"imports"| ExtLib
    Scanpy -->|"imports"| ExtLib

    Docs -->|"guide install"| Client
    DocsDB -->|"category overview"| Marketplace
    DocsPKG -->|"category overview"| Marketplace
    DocsINT -->|"category overview"| Marketplace
    DocsTHINK -->|"category overview"| Marketplace
    License -->|"license info"| Marketplace

    %% CI/CD Flow
    Manifest -->|"on commit"| CI
    CI -->|"publish release"| Marketplace

    %% Click Events
    click Manifest "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/.claude-plugin/marketplace.json"
    click CI "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/.github/workflows/release.yml"
    click Docs "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/README.md"
    click DocsDB "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/docs/scientific-databases.md"
    click DocsPKG "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/docs/scientific-packages.md"
    click DocsINT "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/docs/scientific-integrations.md"
    click DocsTHINK "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/docs/scientific-thinking.md"
    click License "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/LICENSE.md"
    click Alphafold "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/scientific-databases/alphafold-database/SKILL.md"
    click Chembl "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/scientific-databases/chembl-database/scripts/example_queries.py"
    click Scanpy "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/scientific-packages/scanpy/scripts/qc_analysis.py"
    click Benchling "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/scientific-integrations/benchling-integration/SKILL.md"
    click ContextInit "https://github.com/k-dense-ai/claude-scientific-skills/blob/main/scientific-helpers/scientific-context-initialization/SKILL.md"
    click scientific-databases/ "https://github.com/k-dense-ai/claude-scientific-skills/tree/main/scientific-databases/"
    click scientific-packages/ "https://github.com/k-dense-ai/claude-scientific-skills/tree/main/scientific-packages/"
    click scientific-integrations/ "https://github.com/k-dense-ai/claude-scientific-skills/tree/main/scientific-integrations/"
    click scientific-helpers/ "https://github.com/k-dense-ai/claude-scientific-skills/tree/main/scientific-helpers/"
    click scientific-thinking/ "https://github.com/k-dense-ai/claude-scientific-skills/tree/main/scientific-thinking/"

    %% Styles
    classDef external fill:#f9f,stroke:#333,stroke-width:2px;
    classDef integration fill:#bbf,stroke:#333,stroke-width:2px;
    classDef domain fill:#bfb,stroke:#333,stroke-width:2px;
    classDef automation fill:#fbf,stroke:#333,stroke-width:2px;
    classDef dependencies fill:#ffb,stroke:#333,stroke-width:2px;
    classDef docs fill:#eef,stroke:#333,stroke-width:2px;
```
