From sf-skills
Generates rendered PNG/SVG images: visual ERDs, UI mockups, wireframes, and architecture diagrams for Salesforce via Nano Banana Pro. Use when the user needs image output instead of text diagrams.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sf-skills:generating-visual-diagramsThe summary Claude sees in its skill listing — used to decide when to auto-load this 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.
CREDITS.mdREADME.mdassets/architecture/integration-flow.mdassets/erd/core-objects.mdassets/erd/custom-objects.mdassets/lwc/dashboard-card.mdassets/lwc/data-table.mdassets/lwc/record-form.mdassets/review/apex-review.mdassets/review/lwc-review.mdreferences/architect-aesthetic-guide.mdreferences/examples-index.mdreferences/gemini-cli-setup.mdreferences/interview-questions.mdreferences/iteration-workflow.mdscripts/check-prerequisites.shscripts/generate_image.pyUse 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.
In scope:
Out of scope — delegate instead:
Run the prerequisites check before using the skill:
scripts/check-prerequisites.sh
If prerequisites fail, stop and route the user to setup guidance in:
Ask for or infer before generating:
| Input | Default if not provided |
|---|---|
| Image type | ERD |
| Subject scope and key entities / systems | Ask the user |
| Target quality | Draft (1K) |
| Preferred style | architect.salesforce.com aesthetic |
| Aspect ratio | Default (no override) |
| Quick mode or interview mode | Interview mode |
Unless the user asks for quick / simple / just generate, ask clarifying questions first using the question bank in references/interview-questions.md.
| Request type | Ask about |
|---|---|
| ERD / schema | objects, visual style, purpose, extras |
| UI mockup | component type, object/context, device/layout, style |
| architecture image | systems, boundaries, protocols, emphasis |
| image edit | what to keep, what to change, output quality |
Quick mode defaults (triggered by "quick", "simple", "just generate", "fast"):
Run scripts/check-prerequisites.sh and confirm all required tools pass before proceeding.
generating-custom-object / generating-custom-field if needed)Load references/interview-questions.md for the matching question set (ERD, LWC, architecture, code review).
Good prompts specify subject, composition, color treatment, labels/legends, and output quality goal.
gemini --yolo "/generate 'Your prompt here'"
Open the result and review layout before spending on higher resolution.
gemini --yolo "/edit 'Specific change instruction'"
Use /edit for small adjustments — cheaper than regenerating. See references/iteration-workflow.md.
Run scripts/generate_image.py when layout is confirmed:
uv run scripts/generate_image.py -p "Refined prompt" -f "output.png" -r 4K
gemini --yolo returns no image: re-run once; if it fails again, fall back to the Python script path.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.gemini extensions install nanobanana and re-run the prerequisites check.For ERDs, default to the architect.salesforce.com aesthetic unless the user asks otherwise:
Full style specification: references/architect-aesthetic-guide.md
| Pattern | Default approach |
|---|---|
| visual ERD | get metadata if available, then render a draft first |
| LWC mockup | load assets/lwc/data-table.md, assets/lwc/record-form.md, or assets/lwc/dashboard-card.md for the matching template |
| architecture illustration | load assets/architecture/integration-flow.md; emphasize systems and flows |
| image refinement | use /edit for small changes before regenerating |
| final production asset | switch to script-driven 2K/4K generation via scripts/generate_image.py |
| Apex / LWC code review | load assets/review/apex-review.md or assets/review/lwc-review.md for the review prompt template |
Deliverables produced by this skill:
<name>.png) — 1K resolution rendered via gemini --yolo "/generate ..." for layout review<name>.png) — 2K or 4K resolution rendered via scripts/generate_image.py once composition is approved<name>.png) — incremental refinement via gemini --yolo "/edit ..." without full regenerationAfter delivering each image:
| Rule | Rationale |
|---|---|
| Always run prerequisites check before any generation | Missing tools produce silent failures |
| Always draft at 1K before generating at 4K | Cost and time savings; composition changes at high res are wasteful |
Use /edit for incremental changes, not full regeneration | Cheaper and faster for small adjustments |
Never commit GEMINI_API_KEY to version control | Key is personal and tied to billing |
Delegate text diagrams to generating-mermaid-diagrams | This skill owns rendered images only |
| Issue | Resolution |
|---|---|
| Edit not applying correctly | Be specific: reference existing elements by name; one change at a time |
| 4K output looks different from 1K draft | Use exact same prompt text; minor variations are normal model behavior |
gemini --yolo fails silently | Check that the Nano Banana extension is installed: gemini extensions list |
| Image dimensions wrong | Set --aspect-ratio explicitly in scripts/generate_image.py using -a "16:9" |
| RGBA image causes errors in Python script | Script auto-converts RGBA→RGB; ensure Pillow is installed via uv |
| Need | Delegate to | Reason |
|---|---|---|
| Mermaid first draft or text diagram | generating-mermaid-diagrams | faster structural diagramming |
| Object / field discovery for ERD | generating-custom-object / generating-custom-field | accurate schema grounding |
| Turn mockup into real LWC component | generating-lwc-components | implementation after design |
| Apex review / implementation | generating-apex | code-quality follow-up |
| File | When to read |
|---|---|
| references/gemini-cli-setup.md | Prerequisites fail — Gemini CLI / Nano Banana setup guidance |
| references/interview-questions.md | Step 3 — load question set matching the request type |
| references/iteration-workflow.md | Step 6 — draft-to-final iteration patterns and cost tips |
| references/architect-aesthetic-guide.md | Step 4 — ERD color palettes, box styles, prompt templates |
| references/examples-index.md | Step 4 — example prompts for ERD, LWC, architecture, code review |
| assets/erd/core-objects.md | Step 4 — prompt template for core CRM objects (Account, Contact, Opportunity, Case) |
| assets/erd/custom-objects.md | Step 4 — prompt template for custom object ERDs |
| assets/lwc/data-table.md | Step 4 — prompt template for lightning-datatable mockups |
| assets/lwc/record-form.md | Step 4 — prompt template for lightning-record-form mockups |
| assets/lwc/dashboard-card.md | Step 4 — prompt template for dashboard card / metric tile mockups |
| assets/architecture/integration-flow.md | Step 4 — prompt template for integration architecture diagrams |
| assets/review/apex-review.md | Step 4 — Gemini review prompt template for Apex code |
| assets/review/lwc-review.md | Step 4 — Gemini review prompt template for LWC components |
| scripts/check-prerequisites.sh | Step 1 — run to verify all required tools are installed |
| scripts/generate_image.py | Step 7 — run for 2K/4K resolution output and image editing with resolution control |
npx claudepluginhub ccmalcom/sf-skills-plugin --plugin sf-skillsCreates technical and product diagrams (architecture, flowchart, sequence, etc.) as standalone HTML files with inline SVG. Includes style guide setup and 14 diagram types.
Generates and edits diagrams in draw.io using built-in AI with Gemini, Claude, or OpenAI from natural language prompts. Covers API configuration, custom LLM endpoints, and mxGraph XML best practices.
Generates Excalidraw diagram JSON files that argue visually, not just display information. Use for workflows, architectures, or concepts.