esceptico/ntrp/mermaid
Claude Code and agent skill by esceptico/ntrp
- community
Checking that the SKILL.md file is still in the repository.
Produce a clean Mermaid diagram (flowchart / sequence / class / state / ER / gantt / mindmap and others) for the user's requirement. Returns a single fenced ```mermaid block ready to render in the desktop chat.
Install
npx vskill@latest install esceptico/ntrp/mermaidSKILL.md
Mermaid Diagram
Workflow
- Pick the diagram type from the table below.
- Read the matching reference file with
file_readfor syntax details and examples — only the file you actually need, to keep context small. - Emit a single fenced ```mermaid block with the diagram. No prose unless the user explicitly asked for an explanation.
Type → reference
| The user asks about… | Type | Reference | |
|---|---|---|---|
| processes, decisions, branches, "how does X flow" | flowchart | <skill_path>/references/flowchart.md | |
| API calls, RPC traces, who-talks-to-whom over time | sequence | <skill_path>/references/sequenceDiagram.md | |
| OO model, inheritance, fields/methods, UML | class | <skill_path>/references/classDiagram.md | |
| state machines, lifecycles, transitions | state | <skill_path>/references/stateDiagram.md | |
| database schema, FK relationships | ER | <skill_path>/references/erDiagram.md | |
| project plan, deadlines, dependencies | gantt | <skill_path>/references/gantt.md | |
| brainstorm tree, hierarchy without arrows | mindmap | <skill_path>/references/mindmap.md |
If the user asks for a diagram type not in the table (gitGraph, pie, quadrantChart, xychart-beta, sankey-beta, C4Context, architecture-beta, kanban, journey, timeline, requirementDiagram), Mermaid supports it — emit the diagram using your knowledge of the syntax. Reach for the official docs only if you're unsure.
Output rules — applies to every diagram
- One fenced ```mermaid block. No prose inside the fence.
- The first non-blank line is the type keyword (
flowchart TD,sequenceDiagram, …). - Indent with two spaces. One statement per line.
- Quote any label containing punctuation:
A["GET /users"] --> B. - Use
<br/>for line-breaks inside labels — not\n. - Use semantic IDs (
UserService, notn1). - Keep labels short. Long labels make the layout explode.
- Do not add
%%{init:…}%%directives or YAML frontmatter — the renderer already applies the project palette (mermaidneutraltheme + transparent fills + monospace text). Override only if the user specifically asks. - For accents on individual nodes, prefer top-level
classDefover inline styles (hex colors only — Mermaid ignores CSS color names). - Break a 30-node monster into 2–3 focused diagrams. Readability beats completeness.
Quick example
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingapps/server/skills/mermaid/SKILL.md
Popularity
- Repository stars
- 68
- Repository forks
- 10
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/esceptico/ntrp/mermaid)