Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
forcedotcom avatar

Generating Visual Diagrams

  • 2.3k installs
  • 763 repo stars
  • Updated July 24, 2026
  • forcedotcom/sf-skills

generating-visual-diagrams is a Salesforce skill that renders ERDs, UI mockups, and architecture images using Gemini Nano Banana Pro.

About

generating-visual-diagrams produces rendered Salesforce visuals rather than text Mermaid diagrams. It covers visual ERDs, LWC and Experience Cloud mockups, architecture illustrations, and image edits using the Gemini Nano Banana Pro extension. A hard prerequisites gate runs check-prerequisites.sh before any generation, routing failures to gemini-cli-setup guidance. Interview-first workflow loads question banks for ERD, UI, architecture, and edit tasks unless the user requests quick mode with 1K draft defaults. The recommended loop drafts at 1K with gemini --yolo /generate, iterates with /edit, then exports final 2K or 4K images via generate_image.py. Default ERD style follows architect.salesforce.com aesthetics with dark borders and cloud accent colors. Out-of-scope tasks delegate to generating-mermaid-diagrams, generating-custom-object, generating-lwc-components, or generating-apex skills. Error recovery covers missing GEMINI_API_KEY, failed yolo runs, missing nanobanana extension installation, and fallback to generate_image.py scripts.

  • Rendered PNG and SVG ERDs, mockups, and architecture images via Nano Banana Pro.
  • Prerequisites check gate before any image generation attempt.
  • Interview-first workflow with quick-mode 1K draft defaults.
  • Iterate with /edit then upscale via generate_image.py at 2K or 4K.
  • Default architect.salesforce.com ERD aesthetic and delegation boundaries.

Generating Visual Diagrams by the numbers

  • 2,300 all-time installs (skills.sh)
  • +7 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #130 of 1,896 Design & UI/UX skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

generating-visual-diagrams capabilities & compatibility

Capabilities
prerequisites validation before image generation · interview driven prompt gathering for erd and ui · 1k draft generation and /edit iteration workflow · 2k and 4k export via generate_image.py · architect.salesforce.com default erd styling
Works with
gcp
Use cases
ui design · presentations · documentation
Runs
Runs locally
Pricing
Bring your own API key
npx skills add https://github.com/forcedotcom/sf-skills --skill generating-visual-diagrams

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2.3k
repo stars763
Security audit3 / 3 scanners passed
Last updatedJuly 24, 2026
Repositoryforcedotcom/sf-skills

How do I generate presentation-ready Salesforce ERDs or LWC mockups as PNG images instead of text diagrams?

Generate rendered PNG or SVG Salesforce visuals such as ERDs, UI mockups, and architecture diagrams via Nano Banana Pro.

Who is it for?

Salesforce architects needing rendered ERDs, Experience Cloud mockups, or slide-ready architecture visuals.

Skip if: Skip for Mermaid text diagrams, Apex code, or non-visual documentation tasks.

When should I use this skill?

User asks for PNG or SVG ERDs, UI mockups, wireframes, or says generate image or create mockup for Salesforce.

What you get

Interviewed prompts, 1K draft iterations, and final high-resolution images with architect.salesforce.com styling.

  • architecture diagram
  • integration flow visual

Files

SKILL.mdMarkdownGitHub ↗

generating-visual-diagrams: Salesforce Visual AI Skill

Use this skill when the user needs rendered visuals, not text diagrams: ERDs, UI mockups, architecture illustrations, slide-ready images, or image edits using Nano Banana Pro.

Scope

In scope:

  • PNG / SVG-style rendered image output
  • Visual ERDs and architecture diagrams
  • LWC or Experience Cloud mockups / wireframes
  • Image edits on previously generated visuals

Out of scope — delegate instead:

  • Mermaid or text-only diagrams → generating-mermaid-diagrams
  • Object / field metadata discovery for ERDs → generating-custom-object or generating-custom-field
  • LWC implementation after the mockup is approved → generating-lwc-components
  • Apex review / implementation → generating-apex

---

Hard Gate: Prerequisites First

Run the prerequisites check before using the skill:

scripts/check-prerequisites.sh

If prerequisites fail, stop and route the user to setup guidance in:

  • references/gemini-cli-setup.md

---

Required Inputs

Ask for or infer before generating:

InputDefault if not provided
Image typeERD
Subject scope and key entities / systemsAsk the user
Target qualityDraft (1K)
Preferred stylearchitect.salesforce.com aesthetic
Aspect ratioDefault (no override)
Quick mode or interview modeInterview mode

---

Interview-First Workflow

Unless the user asks for quick / simple / just generate, ask clarifying questions first using the question bank in references/interview-questions.md.

Request typeAsk about
ERD / schemaobjects, visual style, purpose, extras
UI mockupcomponent type, object/context, device/layout, style
architecture imagesystems, boundaries, protocols, emphasis
image editwhat to keep, what to change, output quality

Quick mode defaults (triggered by "quick", "simple", "just generate", "fast"):

  • professional style, 1K draft, legend included, one image first then iterate

---

Recommended Workflow

1. Run prerequisites check

Run scripts/check-prerequisites.sh and confirm all required tools pass before proceeding.

2. Gather inputs

  • object list / metadata (delegate to generating-custom-object / generating-custom-field if needed)
  • purpose: draft vs presentation vs documentation
  • desired aesthetic — read references/architect-aesthetic-guide.md for ERDs
  • aspect ratio / resolution

3. Run interview or use quick-mode defaults

Load references/interview-questions.md for the matching question set (ERD, LWC, architecture, code review).

4. Build a concrete prompt

Good prompts specify subject, composition, color treatment, labels/legends, and output quality goal.

5. Generate a fast draft at 1K

gemini --yolo "/generate 'Your prompt here'"

Open the result and review layout before spending on higher resolution.

6. Iterate using edits

gemini --yolo "/edit 'Specific change instruction'"

Use /edit for small adjustments — cheaper than regenerating. See references/iteration-workflow.md.

7. Generate final at 2K/4K using the Python script

Run scripts/generate_image.py when layout is confirmed:

uv run scripts/generate_image.py -p "Refined prompt" -f "output.png" -r 4K

8. Error recovery

  • If gemini --yolo returns no image: re-run once; if it fails again, fall back to the Python script path.
  • If the Python script fails with GEMINI_API_KEY not found: verify the key is exported in your shell profile (~/.zshrc on macOS/zsh, ~/.bashrc on Linux) and the terminal session is refreshed.
  • If the extension is missing: run gemini extensions install nanobanana and re-run the prerequisites check.

---

Default Style Guidance

For ERDs, default to the architect.salesforce.com aesthetic unless the user asks otherwise:

  • dark border + light fill cards
  • cloud-specific accent colors
  • clean labels and relationship lines
  • presentation-ready whitespace and hierarchy

Full style specification: references/architect-aesthetic-guide.md

---

Common Patterns

PatternDefault approach
visual ERDget metadata if available, then render a draft first
LWC mockupload assets/lwc/data-table.md, assets/lwc/record-form.md, or assets/lwc/dashboard-card.md for the matching template
architecture illustrationload assets/architecture/integration-flow.md; emphasize systems and flows
image refinementuse /edit for small changes before regenerating
final production assetswitch to script-driven 2K/4K generation via scripts/generate_image.py
Apex / LWC code reviewload assets/review/apex-review.md or assets/review/lwc-review.md for the review prompt template

---

Output Expectations

Deliverables produced by this skill:

  • Draft image (<name>.png) — 1K resolution rendered via gemini --yolo "/generate ..." for layout review
  • Final image (<name>.png) — 2K or 4K resolution rendered via scripts/generate_image.py once composition is approved
  • Edit iteration (<name>.png) — incremental refinement via gemini --yolo "/edit ..." without full regeneration

After delivering each image:

  • Open the file in Preview or attach it in the session for multimodal review
  • Ask the user whether to iterate on layout, labeling, or color before finalizing
  • Only proceed to high-res output after draft composition is confirmed

---

Rules / Constraints

RuleRationale
Always run prerequisites check before any generationMissing tools produce silent failures
Always draft at 1K before generating at 4KCost and time savings; composition changes at high res are wasteful
Use /edit for incremental changes, not full regenerationCheaper and faster for small adjustments
Never commit GEMINI_API_KEY to version controlKey is personal and tied to billing
Delegate text diagrams to generating-mermaid-diagramsThis skill owns rendered images only

---

Gotchas

IssueResolution
Edit not applying correctlyBe specific: reference existing elements by name; one change at a time
4K output looks different from 1K draftUse exact same prompt text; minor variations are normal model behavior
gemini --yolo fails silentlyCheck that the Nano Banana extension is installed: gemini extensions list
Image dimensions wrongSet --aspect-ratio explicitly in scripts/generate_image.py using -a "16:9"
RGBA image causes errors in Python scriptScript auto-converts RGBA→RGB; ensure Pillow is installed via uv

---

Cross-Skill Integration

NeedDelegate toReason
Mermaid first draft or text diagramgenerating-mermaid-diagramsfaster structural diagramming
Object / field discovery for ERDgenerating-custom-object / generating-custom-fieldaccurate schema grounding
Turn mockup into real LWC componentgenerating-lwc-componentsimplementation after design
Apex review / implementationgenerating-apexcode-quality follow-up

---

Reference File Index

FileWhen to read
references/gemini-cli-setup.mdPrerequisites fail — Gemini CLI / Nano Banana setup guidance
references/interview-questions.mdStep 3 — load question set matching the request type
references/iteration-workflow.mdStep 6 — draft-to-final iteration patterns and cost tips
references/architect-aesthetic-guide.mdStep 4 — ERD color palettes, box styles, prompt templates
references/examples-index.mdStep 4 — example prompts for ERD, LWC, architecture, code review
assets/erd/core-objects.mdStep 4 — prompt template for core CRM objects (Account, Contact, Opportunity, Case)
assets/erd/custom-objects.mdStep 4 — prompt template for custom object ERDs
assets/lwc/data-table.mdStep 4 — prompt template for lightning-datatable mockups
assets/lwc/record-form.mdStep 4 — prompt template for lightning-record-form mockups
assets/lwc/dashboard-card.mdStep 4 — prompt template for dashboard card / metric tile mockups
assets/architecture/integration-flow.mdStep 4 — prompt template for integration architecture diagrams
assets/review/apex-review.mdStep 4 — Gemini review prompt template for Apex code
assets/review/lwc-review.mdStep 4 — Gemini review prompt template for LWC components
scripts/check-prerequisites.shStep 1 — run to verify all required tools are installed
scripts/generate_image.pyStep 7 — run for 2K/4K resolution output and image editing with resolution control

Related skills

Forks & variants (1)

Generating Visual Diagrams has 1 known copy in the catalog totaling 531 installs. They canonicalize to this original listing.

How it compares

Use this over generic diagram skills when documenting Salesforce-centric integration flows with OAuth, middleware, and protocol-labeled connectors.

FAQ

When should I use quick mode?

Quick mode triggers on words like quick or just generate and defaults to professional 1K draft with legend included.

What if gemini --yolo returns no image?

Re-run once; if it fails again, fall back to the Python generate_image.py script path.

Who owns object metadata discovery for ERDs?

Delegate metadata discovery to generating-custom-object or generating-custom-field before building the visual prompt.

Is Generating Visual Diagrams safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Design & UI/UXuibranding

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.