agentleFS
Sign inStart free
MovGP0MovGP0/Skills/mermaid/SKILL.md

mermaid

Skill1 starsChanged 4 months agoMITView on GitHub

Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read Documentation: Read the corresponding syntax reference for the diagram type

    line 16
  2. Distinctive:

    Use semantic node naming

    line 65

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mermaid Diagram Generator

Generate high-quality Mermaid diagram code based on user requirements.

Workflow

  1. Understand Requirements: Analyze user description to determine the most suitable diagram type
  2. Read Documentation: Read the corresponding syntax reference for the diagram type
  3. Generate Code: Generate Mermaid code following the specification
  4. Apply Styling: Apply appropriate themes and style configurations

Diagram Type Reference

Select the appropriate diagram type and read the corresponding documentation:

TypeDocumentationUse Cases
Flowchartflowchart.mdProcesses, decisions, steps
Sequence DiagramsequenceDiagram.mdInteractions, messaging, API calls
Class DiagramclassDiagram.mdClass structure, inheritance, associations
State DiagramstateDiagram.mdState machines, state transitions
ER DiagramentityRelationshipDiagram.mdDatabase design, entity relationships
Gantt Chartgantt.mdProject planning, timelines
Pie Chartpie.mdProportions, distributions
Mindmapmindmap.mdHierarchical structures, knowledge graphs
Timelinetimeline.mdHistorical events, milestones
Git Graphgitgraph.mdBranches, merges, versions
Quadrant ChartquadrantChart.mdFour-quadrant analysis
Requirement DiagramrequirementDiagram.mdRequirements traceability
C4 Diagramc4.mdSystem architecture (C4 model)
Sankey Diagramsankey.mdFlow, conversions
XY ChartxyChart.mdLine charts, bar charts
Block Diagramblock.mdSystem components, modules
Packet Diagrampacket.mdNetwork protocols, data structures
Kanbankanban.mdTask management, workflows
Architecture Diagramarchitecture.mdSystem architecture
Radar Chartradar.mdMulti-dimensional comparison
Treemaptreemap.mdHierarchical data visualization
User JourneyuserJourney.mdUser experience flows
ZenUMLzenuml.mdSequence diagrams (code style)

Configuration & Themes

  • Theming - Custom colors and styles
  • Directives - Diagram-level configuration
  • Layouts - Layout direction and spacing
  • Configuration - Global settings
  • Math - LaTeX math support

Output Specification

Generated Mermaid code should:

  1. Be wrapped in ```mermaid code blocks
  2. Have correct syntax that renders directly
  3. Have clear structure with proper line breaks and indentation
  4. Use semantic node naming
  5. Include styling when needed to improve visual appearance

Example Output

flowchart TD
    A[Start] --> B{Condition}
    B -->|Yes| C[Execute]
    B -->|No| D[End]
    C --> D

User requirements: $ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free