New top-level nav section documenting OpenPencil's programmability: - CLI: inspecting, exporting, analyzing, scripting (eval) - JSX Renderer: elements, style props, visual diffing - MCP Server: moved from Reference (setup + tool list) - AI Chat: setup, 87 tools, example prompts - Collaboration: room sharing, cursors, follow mode Restructured sidebar: - Programmable added to nav bar (7 locales) - Context Menu moved from User Guide to Reference - MCP and eval-command removed from Reference
1.9 KiB
1.9 KiB
| title | description |
|---|---|
| AI Chat | Built-in AI assistant with 87 tools for creating and modifying designs. |
AI Chat
Press ⌘J (Ctrl + J) to open the AI assistant. Describe what you want — it creates shapes, sets styles, manages layout, works with components, and analyzes your design.
Setup
- Open the AI chat panel (⌘J)
- Click the settings icon
- Enter your OpenRouter API key
- Choose a model (Claude, GPT-4, Gemini, etc.)
No backend, no subscription — your key talks directly to OpenRouter.
What It Can Do
The assistant has 87 tools across these categories:
- Create — frames, shapes, text, components, pages. Renders JSX for complex layouts.
- Style — fills, strokes, effects, opacity, corner radius, blend modes.
- Layout — auto-layout, alignment, spacing, sizing.
- Components — create components, instances, component sets. Manage overrides.
- Variables — create/edit variables, collections, modes. Bind to fills.
- Query — find nodes, read properties, list pages, fonts, selection.
- Analyze — color palette, typography audit, spacing consistency, cluster detection.
- Export — PNG, SVG, JSX with Tailwind classes.
- Vector — boolean operations, path manipulation.
Example Prompts
- "Create a card with a title, description, and a blue button"
- "Make all buttons on this page use the same border radius"
- "What fonts are used in this file?"
- "Change the background of the selected frame to a gradient from blue to purple"
- "Export the selected frame as SVG"
- "Find all text nodes with font size less than 12"
Tips
- Select nodes before asking — the assistant knows what's selected.
- Be specific about colors, sizes, and positions for precise results.
- The assistant can modify multiple nodes in one message.
- Use "undo" in the editor if you don't like the result.