OpenParable
Skip to content
← Back to skills

Architecture Diagram

Design

Architecture Diagram is an Agent Skill for design published in the agentic-in/elephant-agent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Produces clean architecture and system diagrams from actual repo or product truth instead of decorative boxes.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/agentic-in/elephant-agent/blob/HEAD/packages/skills/builtin_packages/creative/architecture-diagram/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/architecture-diagram-6d7df354, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Architecture Diagram

Use this built-in skill when the user needs a system, data-flow, or component diagram that should stay faithful to the real implementation.

Core rules

  • Start from the actual repo, API contract, or product behavior before drawing.
  • Pick the simplest editable format that fits the request: Mermaid, SVG, or code-native graphics.
  • Keep labels sparse and information hierarchy obvious.
  • Optimize for explanation, not visual noise.

Default workflow

  1. Identify the audience and the level of abstraction.
  2. Extract the canonical components, boundaries, and flows.
  3. Produce one clear diagram with consistent naming and direction.
  4. Verify that the diagram matches the implementation or stated architecture.

Guardrails

  • Do not invent systems or edges that are not grounded in source truth.
  • Do not overload one frame with too many concepts.
  • Do not hide uncertainty; mark assumptions when architecture is inferred.