# menakod/skills architecture
> Architecture diagram of the GitHub repository menakod/skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-06-18). It is an AI-made overview: check details against the source.
- Interactive diagram: https://gitdiagram.com/menakod/skills
- Repository: https://github.com/menakod/skills
## Overview
This repository is a small skill catalog for Gemini CLI rather than an application or library.
1. **Top-level purpose**
- The repo packages specialized “skills” that Gemini CLI can load or reference.
- Its architecture is documentation/prompt driven: the main deliverable is skill guidance, not executable code.
2. **Repository root as entry point**
- `README.md` is the public index.
- It introduces the collection and points users to the available skill(s), acting as the navigation layer for the repo.
3. **Skill boundary**
- `code-explainer/` is a self-contained skill module.
- Each skill lives in its own directory, which creates a clear boundary for adding more skills later without mixing concerns.
4. **Skill implementation artifact**
- `code-explainer/SKILL.md` is the core definition for the Code Explainer skill.
- Based on the repo structure, the skill is likely represented as a structured Markdown spec or prompt rather than source code.
5. **Functional role of the skill**
- The Code Explainer skill is described as an expert programming tutor that explains code to beginners.
- Architecturally, this means the repo’s main “logic” is instructional behavior encoded in the skill document.
6. **Data flow**
- A user or CLI reads the root README to discover available skills.
- Gemini CLI then loads the relevant skill document from the skill directory.
- The skill content guides the model’s behavior when explaining code.
7. **Extensibility model**
- The layout suggests a plugin-like organization: one directory per skill, one skill file per capability.
- Adding new skills should not require changing existing skill definitions; the README is just the catalog.
8. **Technology profile**
- No runtime, build system, package manager, or external service is visible from the tree.
- The repository appears to rely on Markdown documentation and the Gemini CLI skill-loading convention.
9. **Operational boundary**
- There is no indication of application state, persistence, networking, or deployment infrastructure.
- The main operational concern is content maintenance: keeping skill instructions clear and discoverable.
10. **Architectural takeaway for a diagram**
- Diagram this as a documentation-driven skill repository with:
- a catalog/index layer at the root,
- isolated skill packages beneath it,
- and Gemini CLI as the consumer of those skill definitions.
Main entry points: [`README.md`](https://github.com/menakod/skills/blob/master/README.md) (README), [`code-explainer`](https://github.com/menakod/skills/tree/master/code-explainer) (Code Explainer), [`code-explainer/SKILL.md`](https://github.com/menakod/skills/blob/master/code-explainer/SKILL.md) (SKILL)
## Diagram (Mermaid)
```mermaid
flowchart TD
subgraph group_root["Root"]
node_readme["README
catalog index
[README.md]"]
node_catalog_view(("Skill Catalog
discovery flow"))
end
subgraph group_skill["Skill Module"]
node_skill_dir["Code Explainer
skill package"]
node_skill_md["SKILL
[SKILL.md]"]
node_explain_behavior{{"Tutor Behavior
instruction outcome"}}
end
node_gemini_cli["Gemini CLI
consumer"]
node_gemini_cli -->|"discover skills"| node_readme
node_readme -->|"publishes"| node_catalog_view
node_readme -->|"points to"| node_skill_dir
node_skill_dir -->|"contains"| node_skill_md
node_gemini_cli -->|"loads"| node_skill_md
node_skill_md -->|"defines"| node_explain_behavior
node_skill_dir -.->|"encapsulates"| node_explain_behavior
click node_readme "https://github.com/menakod/skills/blob/master/README.md"
click node_skill_dir "https://github.com/menakod/skills/tree/master/code-explainer"
click node_skill_md "https://github.com/menakod/skills/blob/master/code-explainer/SKILL.md"
classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_readme,node_catalog_view toneBlue
class node_skill_dir,node_skill_md,node_explain_behavior toneAmber
class node_gemini_cli toneNeutral
```
## Components
### Root
Repository entry and catalog layer
- [README](https://github.com/menakod/skills/blob/master/README.md): catalog index · Public entry point that lists the available skills and directs users to them · `README.md`
- **Skill Catalog**: discovery flow · The repository presented as a browsable set of available skills
### Skill Module
Self-contained skill package
- [Code Explainer](https://github.com/menakod/skills/tree/master/code-explainer): skill package · Directory boundary for the code-explainer skill · `code-explainer`
- [SKILL](https://github.com/menakod/skills/blob/master/code-explainer/SKILL.md): skill spec · Markdown definition of the Code Explainer skill and its behavior · `code-explainer/SKILL.md`
- **Tutor Behavior**: instruction outcome · Beginner-friendly code explanation behavior encoded by the skill document
### Other components
- **Gemini CLI**: consumer · External runtime that discovers and loads the skill content
## Connections
- Gemini CLI → README: discover skills · CLI or user starts from the repository index
- README → Skill Catalog: publishes · README serves as the navigation layer for the catalog
- README → Code Explainer: points to · Index references the available skill package
- Code Explainer → SKILL: contains · The skill lives in its own directory as a single Markdown spec
- Gemini CLI → SKILL: loads · CLI consumes the skill definition when the capability is needed
- SKILL → Tutor Behavior: defines · Instruction text determines how the model explains code
- Code Explainer → Tutor Behavior: encapsulates · The package boundary isolates the skill’s behavior from other skills