#361361st of 389 in Skills, plugins and prompts
oh-my-mermaid
Skill that has your AI coding tool generate Mermaid architecture docs for a repo
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.4k
- License
- MIT
- Last commit
- Apr 2026
- Last release
- Mar 2026
- Language
- TypeScript
966 on 21 Apr 20263,393 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
oh-my-mermaid is an npm CLI that registers an /omm-scan skill in AI coding tools (Claude Code, Codex, Cursor, OpenClaw, Antigravity). The AI analyzes the repo and writes nested "perspectives" (structure, data flow, integrations) into a .omm/ directory as Mermaid diagrams plus markdown fields. A local viewer (omm view) renders them, and an optional cloud push to ohmymermaid.com allows sharing.
Who it is for: Developers who want architecture docs generated from AI-written codebases
Strengths
- Output is plain files in .omm/ (diagram.mmd, description.md), easy to version in Git
- Recursive analysis: complex nodes get nested child diagrams, shown as expandable groups in the viewer
- Works with five AI tools via one `omm setup` command that auto-detects installed ones
- Each element has up to 7 fields, including constraint, concern and todo
Weaknesses
- Scan quality depends on the AI tool and model you run it with
- Sharing and team features go through the hosted ohmymermaid.com cloud service
- Only two skills (/omm-scan, /omm-push); no CI or automatic doc refresh described
What it needs
- no GPU
- Needs Node.js/npm, AI coding tool (Claude Code, Codex, Cursor, OpenClaw or Antigravity), ohmymermaid.com (optional, for cloud push)
Quick answers
Is oh-my-mermaid open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |