agentleFS
KumailQaziKumailQazi/krmaazha-binance-mcp/.agents/skills/external-diagram-mermaid-generate/SKILL.md

external-diagram-mermaid-generate

Skill4 starsChanged 38 days agoMITView on GitHub

Salesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. 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 asks about non-Salesforce systems.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user needs text-based diagrams: Mermaid diagrams for architecture, OAuth, integration flows, ERDs, or Agentforce …

    line 32
  2. Very specific:

    Use external-diagram-mermaid-generate when the user wants:

    line 37
  3. Distinctive:

    Ask for or infer:

    line 64
  4. Very specific:

    use sequenceDiagram for time-ordered interactions

    line 76
  5. Very specific:

    use flowchart LR for ERDs and capability maps

    line 77
  6. Distinctive:

    keep a single primary story per diagram when possible

    line 78
  7. Distinctive:

    use platform-custom-object-generate or platform-custom-field-generate when real schema discovery is needed

    line 82
  8. Distinctive:

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

    line 96
  9. Very specific:

    use autonumber when step order matters

    line 103
  10. Distinctive:

    use notes sparingly for protocol detail

    line 105
  11. Distinctive:

    keep object cards simple

    line 109
  12. Distinctive:

    use clear relationship arrows

    line 110
  13. Distinctive:

    avoid field overload unless the user explicitly asks for field-level detail

    line 111

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

external-diagram-mermaid-generate: 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.

Scope

In Scope

Use external-diagram-mermaid-generate 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

Out of Scope — Delegate elsewhere when the user wants:

  • non-Salesforce systems only → use a more general diagramming skill
  • object discovery before an ERD → platform-custom-object-generate or platform-custom-field-generate

Supported Diagram Families

TypePreferred Mermaid formTypical use
OAuth / auth flowssequenceDiagramAuthorization Code, JWT, PKCE, Device Flow
ERD / data modelflowchart LRobject relationships and sharing context
integration sequencesequenceDiagramrequest/response or event choreography
system landscapeflowcharthigh-level architecture
role / access hierarchyflowchartusers, profiles, permissions
Agentforce behavior mapflowchartagent → 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 platform-custom-object-generate or platform-custom-field-generate 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

NeedDelegate toReason
real object / field definitionsplatform-custom-object-generate / platform-custom-field-generategrounded ERD generation
connected-app auth setup contextintegration-connectivity-connected-app-configureaccurate OAuth flows
Agentforce logic visualizationagentforce-generatesource-of-truth behavior details
Flow behavior diagramsautomation-flow-generateactual Flow logic grounding

Gotchas

IssueResolution
Mermaid renderer not availableProvide ASCII fallback automatically; note that the Mermaid block still carries the diagram for copy-paste into a renderer
ERD becomes unreadable with too many objectsSplit into sub-diagrams by domain (Sales, Service, etc.) and link them in prose
Sequence diagram step order unclearUse autonumber directive to make step ordering explicit
OAuth flow actors differ by grant typeRead the relevant asset template first before generating to avoid actor mismatch

Reference File Index

Conventions & rules — read before generating

  • references/diagram-conventions.md — consistency rules for all diagram types
  • references/mermaid-reference.md — Mermaid syntax quick reference
  • references/usage-examples.md — worked examples per diagram type

Styling

  • references/mermaid-styling.md — theming and annotation patterns
  • references/color-palette.md — color-blind-friendly palette with hex values
  • references/erd-conventions.md — ERD-specific layout and notation rules

Preview

  • references/preview-guide.md — how to render Mermaid locally
  • scripts/README.md — setup and usage instructions for all scripts in this skill
  • scripts/mermaid_preview.py — live-reload preview server; run to preview diagrams in browser
  • scripts/query-org-metadata.py — queries org schema to ground ERD generation

OAuth flow templates — load the matching template when generating OAuth diagrams

  • assets/oauth/authorization-code.md — Authorization Code grant
  • assets/oauth/authorization-code-pkce.md — PKCE variant for mobile/SPA
  • assets/oauth/jwt-bearer.md — JWT Bearer server-to-server
  • assets/oauth/client-credentials.md — Client Credentials service accounts
  • assets/oauth/device-authorization.md — Device Flow for CLI/IoT
  • assets/oauth/refresh-token.md — Refresh Token renewal flow
  • assets/oauth/user-agent-social-sign-on.md — User-Agent / Social Sign-On

Data model ERD templates — load the matching template when generating ERDs

  • assets/datamodel/salesforce-erd.md — core Salesforce objects
  • assets/datamodel/sales-cloud-erd.md — Sales Cloud objects
  • assets/datamodel/service-cloud-erd.md — Service Cloud objects
  • assets/datamodel/b2b-commerce-erd.md — B2B Commerce objects
  • assets/datamodel/campaigns-erd.md — Campaigns and campaign member model
  • assets/datamodel/consent-erd.md — Consent and privacy objects
  • assets/datamodel/files-erd.md — Files and ContentDocument model
  • assets/datamodel/forecasting-erd.md — Forecasting objects
  • assets/datamodel/fsl-erd.md — Field Service Lightning objects
  • assets/datamodel/party-model-erd.md — Party model objects
  • assets/datamodel/quote-order-erd.md — Quote and Order objects
  • assets/datamodel/revenue-cloud-erd.md — Revenue Cloud objects
  • assets/datamodel/scheduler-erd.md — Scheduler objects
  • assets/datamodel/territory-management-erd.md — Territory Management objects

Other diagram templates

  • assets/architecture/system-landscape.md — system landscape overview template
  • assets/integration/api-sequence.md — API callout sequence template
  • assets/agentforce/agent-flow.md — Agentforce agent → topic → action flow
  • assets/role-hierarchy/user-hierarchy.md — role and permission hierarchy template

Output Expectations

Deliverables produced by this skill for each request:

  • Mermaid code block — fenced ```mermaid block ready to paste into GitHub, Confluence, or any Mermaid-capable renderer
  • ASCII fallback (when requested or when Mermaid renderer is unavailable) — text-only diagram using box/arrow characters
  • Brief explanation — 2-5 bullet points calling out key relationships, flow direction, and any assumptions or limitations in the diagram
  • For ERDs: object cards with field labels and relationship type annotations
  • For sequence diagrams: numbered steps (autonumber) with clear actor labels

Score Guide

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

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.