Skill

Review

Audit score 70

sf-diagram-mermaid

jaganpro/sf-skills

Generate Salesforce architecture diagrams in Mermaid with ASCII fallback for docs and terminals.

What is sf-diagram-mermaid?

Creates text-based diagrams (Mermaid and ASCII) for Salesforce systems: OAuth flows, ERDs, integration sequences, and architecture visualizations. Use this when you need diagrams that live in markdown, READMEs, or issues—not rendered images.

Generate Mermaid diagrams for OAuth flows, ERDs, sequence diagrams, and system architecture
Provide ASCII fallback versions for terminal and plaintext documentation compatibility
Support flowchart, sequence diagram, and ERD layouts optimized for Salesforce patterns
Integrate with sf-metadata for grounded object discovery and relationship mapping
Output diagrams ready to embed directly in markdown and version control

How to install sf-diagram-mermaid

npx skills add https://github.com/jaganpro/sf-skills --skill sf-diagram-mermaid

Prerequisites

Mermaid-capable renderer for diagram previews (GitHub, GitLab, Notion, or local Mermaid viewer)
Optional: sf-metadata skill for grounded ERD generation from actual org schema

Claude Code

Cursor

Windsurf

Cline

How to use sf-diagram-mermaid

1.Specify the diagram type needed (sequence, flowchart, ERD, or architecture)
2.Provide scope and entities involved, or let the skill infer from context
3.Request output preference: Mermaid only, ASCII only, or both
4.Review the generated diagram and ask for refinements (layout, styling, detail level)
5.Copy the Mermaid or ASCII output into your documentation or markdown file

Use cases

Good for

Document Salesforce OAuth authorization flows (Authorization Code, JWT, PKCE, Device Flow)
Visualize data models and object relationships with ERDs
Map integration sequences and event choreography between systems
Show Agentforce agent-to-topic-to-action behavior hierarchies
Create role and permission hierarchy diagrams for access control documentation

Who it's for

Salesforce architects designing system landscapes
Integration engineers documenting OAuth and API flows
Data modelers creating entity-relationship diagrams
Technical writers embedding diagrams in documentation
Developers building Agentforce agents and automation

sf-diagram-mermaid FAQ

When should I use this instead of sf-diagram-nanobananapro?

Use sf-diagram-mermaid for text-based diagrams that live in docs, READMEs, and version control. Use sf-diagram-nanobananapro when you need rendered PNG/SVG images or polished visual mockups.

Can this skill generate diagrams from my actual Salesforce org?

Yes, when you use it together with sf-metadata to discover real objects and relationships. The skill can then ground the ERD in your actual schema.

What if my diagram is too complex for a single view?

Break it into multiple focused diagrams, each with a single primary story. The skill recommends keeping scope tight for readability.

Do I need Mermaid installed locally?

No. Mermaid diagrams render natively in GitHub, GitLab, and many markdown viewers. For local preview, use the included mermaid_preview.py script.

Can I customize colors and styling?

Yes. The skill supports Mermaid styling and includes a color-palette reference. Styling is kept minimal by default for documentation-first clarity.

Full instructions (SKILL.md)

Source of truth, from jaganpro/sf-skills.

name: sf-diagram-mermaid description: > Salesforce architecture diagrams using Mermaid with ASCII fallback. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use sf-diagram-nanobananapro), or asks about non-Salesforce systems. license: MIT compatibility: "Requires Mermaid-capable renderer for diagram previews" metadata: version: "1.2.0" author: "Jag Valaiyapathy" scoring: "80 points across 5 categories"

sf-diagram-mermaid: Salesforce Diagram Generation

Use this skill when the user needs text-based diagrams: Mermaid diagrams for architecture, OAuth, integration flows, ERDs, or Agentforce structure, plus ASCII fallback when plain-text compatibility matters.

When This Skill Owns the Task

Use sf-diagram-mermaid when the user wants:

Mermaid output
ASCII fallback diagrams
architecture, sequence, flowchart, or ERD views in markdown-friendly form
diagrams that can live directly in docs, READMEs, or issues

Delegate elsewhere when the user wants:

rendered PNG/SVG images or polished mockups → sf-diagram-nanobananapro
non-Salesforce systems only → use a more general diagramming skill
object discovery before an ERD → sf-metadata

Supported Diagram Families

Type	Preferred Mermaid form	Typical use
OAuth / auth flows	`sequenceDiagram`	Authorization Code, JWT, PKCE, Device Flow
ERD / data model	`flowchart LR`	object relationships and sharing context
integration sequence	`sequenceDiagram`	request/response or event choreography
system landscape	`flowchart`	high-level architecture
role / access hierarchy	`flowchart`	users, profiles, permissions
Agentforce behavior map	`flowchart`	agent → topic → action relationships

Required Context to Gather First

Ask for or infer:

diagram type
scope and entities / systems involved
output preference: Mermaid only, ASCII only, or both
whether styling should be minimal, documentation-first, or presentation-friendly
for ERDs: whether org metadata is available for grounding

Recommended Workflow

1. Pick the right diagram structure

use sequenceDiagram for time-ordered interactions
use flowchart LR for ERDs and capability maps
keep a single primary story per diagram when possible

2. Gather data

For ERDs and grounded diagrams:

use sf-metadata when real schema discovery is needed
optionally use the local metadata helper script for counts / relationship context when appropriate

3. Generate Mermaid first

Apply:

accurate labels
simple readable node text
consistent relationship notation
restrained styling that renders cleanly in markdown viewers

4. Add ASCII fallback when useful

Provide an ASCII version when the user wants terminal compatibility or plaintext documentation.

5. Explain the diagram briefly

Call out the key relationships, flow direction, and any assumptions.

High-Signal Rules

For sequence diagrams

use autonumber when step order matters
distinguish requests vs responses clearly
use notes sparingly for protocol detail

For ERDs

prefer flowchart LR
keep object cards simple
use clear relationship arrows
avoid field overload unless the user explicitly asks for field-level detail
color-code object types only when it improves readability

For ASCII output

keep width reasonable
align arrows and boxes consistently
optimize for readability over decoration

Output Format

## <Diagram Title>

### Mermaid Diagram
```mermaid
<diagram>
```

### ASCII Fallback
```text
<ascii>
```

### Notes
- <key point>
- <assumption or limitation>

Cross-Skill Integration

Need	Delegate to	Reason
real object / field definitions	sf-metadata	grounded ERD generation
rendered diagram / image output	sf-diagram-nanobananapro	visual polish beyond Mermaid
connected-app auth setup context	sf-connected-apps	accurate OAuth flows
Agentforce logic visualization	sf-ai-agentscript	source-of-truth behavior details
Flow behavior diagrams	sf-flow	actual Flow logic grounding

Reference Map

Start here

Styling / ERD specifics

Preview

Score Guide

Score	Meaning
72–80	production-ready diagram
60–71	clear and useful with minor polish left
48–59	functional but could be clearer
35–47	needs structural improvement
< 35	inaccurate or incomplete