# dreambigou/eli5 architecture

> Architecture diagram of the GitHub repository dreambigou/eli5, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dreambigou/eli5
- Repository: https://github.com/dreambigou/eli5

## Overview

ELI5 is a Claude Code skill that adapts explanations to an intended audience. Its principal workflow is described in the README, but the skill instructions themselves were not sampled, so the runtime stages are represented at a documented, high level. The repository also includes an evaluation workflow; its runner excerpt shows calls to the Claude CLI, while omitted code limits detail about orchestration.

Main entry points: [`eli5-workspace/run-evals.py`](https://github.com/dreambigou/eli5/blob/main/eli5-workspace/run-evals.py) (Eval runner), [`skills/eli5/SKILL.md`](https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md) (ELI5 skill), [`eli5-workspace/evals.json`](https://github.com/dreambigou/eli5/blob/main/eli5-workspace/evals.json) (Eval cases)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_skill["Explanation skill"]
  node_skill_file["ELI5 skill<br/>[SKILL.md]"]
  node_audience["Audience detection<br/>[SKILL.md]"]
  node_calibration["Style calibration<br/>[SKILL.md]"]
  node_explanation["Adapted explanation"]
end

subgraph group_evaluation["Evaluation workflow"]
  node_eval_runner["Eval runner<br/>[run-evals.py]"]
  node_eval_cases["Eval cases<br/>[evals.json]"]
  node_eval_results["Evaluation outputs<br/>[run-evals.py]"]
end

node_user(("User"))
node_claude_code["Claude Code"]
node_claude_cli["Claude CLI"]

node_user -->|"submits prompt"| node_claude_code
node_claude_code -->|"uses skill"| node_skill_file
node_skill_file -->|"guides detection"| node_audience
node_audience -->|"informs style"| node_calibration
node_calibration -->|"shapes response"| node_explanation
node_claude_code -->|"returns response"| node_explanation
node_eval_runner -->|"loads cases"| node_eval_cases
node_eval_runner -->|"runs prompts"| node_claude_cli
node_eval_runner -->|"grades responses"| node_claude_cli
node_eval_runner -->|"writes outputs"| node_eval_results

click node_skill_file "https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md"
click node_audience "https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md"
click node_calibration "https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md"
click node_eval_runner "https://github.com/dreambigou/eli5/blob/main/eli5-workspace/run-evals.py"
click node_eval_cases "https://github.com/dreambigou/eli5/blob/main/eli5-workspace/evals.json"
click node_eval_results "https://github.com/dreambigou/eli5/blob/main/eli5-workspace/run-evals.py"

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_skill_file,node_audience,node_calibration,node_explanation,node_user toneBlue
class node_eval_runner,node_eval_cases,node_eval_results toneAmber
class node_claude_code,node_claude_cli toneIndigo
```

## Components

### Explanation skill

- [ELI5 skill](https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md): `skills/eli5/SKILL.md`
- [Audience detection](https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md): `skills/eli5/SKILL.md`
- [Style calibration](https://github.com/dreambigou/eli5/blob/main/skills/eli5/SKILL.md): `skills/eli5/SKILL.md`
- **Adapted explanation**

### Evaluation workflow

- [Eval runner](https://github.com/dreambigou/eli5/blob/main/eli5-workspace/run-evals.py): `eli5-workspace/run-evals.py`
- [Eval cases](https://github.com/dreambigou/eli5/blob/main/eli5-workspace/evals.json): `eli5-workspace/evals.json`
- [Evaluation outputs](https://github.com/dreambigou/eli5/blob/main/eli5-workspace/run-evals.py): `eli5-workspace/run-evals.py`

### Other components

- **User**
- **Claude Code**
- **Claude CLI**

## Connections

- User → Claude Code: submits prompt
- Claude Code → ELI5 skill: uses skill
- ELI5 skill → Audience detection: guides detection
- Audience detection → Style calibration: informs style
- Style calibration → Adapted explanation: shapes response
- Claude Code → Adapted explanation: returns response
- Eval runner → Eval cases: loads cases
- Eval runner → Claude CLI: runs prompts
- Eval runner → Claude CLI: grades responses
- Eval runner → Evaluation outputs: writes outputs
