What problem does it solve?
Chat responses bury structured analytical results in markdown tables and code blocks. This Skill turns standalone analytical output — metrics, audits, billing investigations, charts — into a live React canvas the user can open beside the conversation.
Core Features & Use Cases
- Canvas authoring workflow: Decide when a canvas is warranted, then create, patch, or rewrite a single TSX artifact via CreateCanvas, PatchCanvas, and UpdateCanvas.
- Component SDK: Build with the
bitfun/canvas SDK — charts (Bar, Line, Pie), tables, cards, stats, forms, diff views, DAG layouts, and usage bars — styled with host appearance tokens.
- Design policy enforcement: Flat minimal styling with forbidden slop patterns (gradients, emojis, box-shadows), mandatory plot labeling, and a pre-delivery self-check.
- Use Case: After querying a database for a billing investigation, render the categorized findings as a labeled chart and table canvas instead of dumping a markdown table into chat.
Quick Start
Ask the agent to analyze your data and present the results as a BitFun Canvas you can open beside the chat.