Set up an agent

The fastest way to get diagrams is to let a coding agent do the drawing. vizzy’s app has a Copy init prompt button that copies the prompt below; paste it into your agent (Claude Code, Codex, etc.) and it will add a reusable skill that teaches any agent how to author and maintain vizzy diagrams in your repo.

What the agent does

Rather than drawing the diagrams once, the init prompt asks the agent to create a vizzy skill — e.g. .claude/skills/vizzy/SKILL.md — that captures the format so the work can be done on demand later and stays consistent over time. The skill should teach:

Where diagrams live — a vizzy/ folder, one concern per file.
Frontmatter — title, layout, and created / lastEdited dates.
mermaid vs vizzy fences — when to draw with Mermaid and when to reach for vizzy.
Diagram types, styling, hints, and theming — everything in the Authoring section.

Do a good job

Whether it’s you or an agent authoring, the same rules apply:

Explore the real code first — diagram what’s actually there, not a guess.
Short, stable ids; readable labels. On edges, show what is exchanged (payloads).
Prefer a sequence diagram for a request/response flow, an architecture fence for the static service map, a flowchart for branching logic.
Add a short prose paragraph above each diagram explaining its intent.
When the architecture changes in code, update the matching vizzy/*.vizzy.md and bump its lastEdited date.