# github/evals architecture

> Architecture diagram of the GitHub repository github/evals, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-21). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/github/evals
- Repository: https://github.com/github/evals

## Overview

GitHub Copilot Evals is a plugin and VS Code extension for authoring, running, reviewing, and comparing evaluations of Copilot skills, custom agents, and MCP tools. The documented user workflow starts in the `/eval` commands or Evals Canvas, proceeds through eval creation and review, then an approved local run, saved results, and comparison. The README also documents setup, model-invocable skills, automation blueprints, and an MCP server. The supplied tree contains no implementation files, so undocumented component paths and internal relationships are omitted; edges shown are supported by README statements.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Eval workflow"]
  node_setup["Eval setup"]
  node_author["Eval authoring"]
  node_review["Eval review"]
  node_compare["Run comparison"]
end

subgraph group_interfaces["User interfaces"]
  node_cli["&#96;/eval&#96; commands"]
  node_canvas["Evals Canvas"]
end

subgraph group_capabilities["Plugin capabilities"]
  node_skills["Six eval skills"]
  node_automations["Automation blueprints"]
  node_mcp["MCP server"]
end

subgraph group_execution["Execution and results"]
  node_runner["Local eval runner"]
  node_run["Eval run"]
  node_results[("Saved reports")]
end

node_user(("Project user"))
node_project["Local project"]

node_user -->|"invokes"| node_cli
node_user -->|"opens"| node_canvas
node_cli -->|"creates eval"| node_author
node_canvas -->|"drafts eval"| node_author
node_canvas -->|"reviews eval"| node_review
node_cli -->|"reviews results"| node_review
node_cli -->|"configures"| node_setup
node_user -->|"installs runner"| node_setup
node_user -->|"approves run"| node_review
node_runner -->|"executes"| node_run
node_run -->|"saves report"| node_results
node_canvas -->|"browses reports"| node_results
node_results -->|"compares runs"| node_compare
node_cli -->|"compares runs"| node_compare
node_user -->|"requests skill"| node_skills
node_user -->|"uses blueprints"| node_automations
node_mcp -->|"resolves workspace"| node_project

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_setup,node_author,node_review,node_compare,node_user toneBlue
class node_cli,node_canvas toneAmber
class node_skills,node_automations,node_mcp toneMint
class node_runner,node_run,node_results toneRose
class node_project toneIndigo
```

## Components

### Eval workflow

- **Eval setup**
- **Eval authoring**
- **Eval review**
- **Run comparison**

### User interfaces

- **`/eval` commands**
- **Evals Canvas**

### Plugin capabilities

- **Six eval skills**
- **Automation blueprints**
- **MCP server**

### Execution and results

- **Local eval runner**
- **Eval run**
- **Saved reports**

### Other components

- **Project user**
- **Local project**

## Connections

- Project user → `/eval` commands: invokes (evidence: `README.md`)
- Project user → Evals Canvas: opens (evidence: `README.md`)
- `/eval` commands → Eval authoring: creates eval (evidence: `README.md`)
- Evals Canvas → Eval authoring: drafts eval (evidence: `README.md`)
- Evals Canvas → Eval review: reviews eval (evidence: `README.md`)
- `/eval` commands → Eval review: reviews results (evidence: `README.md`)
- `/eval` commands → Eval setup: configures (evidence: `README.md`)
- Project user → Eval setup: installs runner (evidence: `README.md`)
- Project user → Eval review: approves run (evidence: `README.md`)
- Local eval runner → Eval run: executes (evidence: `README.md`)
- Eval run → Saved reports: saves report (evidence: `README.md`)
- Evals Canvas → Saved reports: browses reports (evidence: `README.md`)
- Saved reports → Run comparison: compares runs (evidence: `README.md`)
- `/eval` commands → Run comparison: compares runs (evidence: `README.md`)
- Project user → Six eval skills: requests skill (evidence: `README.md`)
- Project user → Automation blueprints: uses blueprints (evidence: `README.md`)
- MCP server → Local project: resolves workspace (evidence: `README.md`)
