一键导入
canvas
Render charts and images in the canvas window by outputting JSON. Use for visualisation, graphing, and displaying data visually.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Render charts and images in the canvas window by outputting JSON. Use for visualisation, graphing, and displaying data visually.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Collaborate over x0x — contacts, messages, spaces, boards, files, presence, trusted-machine port forwards, and replicated stores. Use for sharing cards, connecting people, or cross-device work.
Guide for surfacing one relevant Fae capability that the user hasn't set up yet. Warm, specific, one thing at a time.
Deep pipeline diagnostic — every model, system specs, audio config, speaker state. Flags missing or broken components. Use for diagnose, debug, or health check.
Extract training signals from Fae's memory — SFT examples, DPO correction pairs, engagement scores, and interest-weighted sampling.
Set up (or turn off) a cloud brain for harder questions via OpenRouter — privacy-first, plain language. Use when the user wants a bigger or smarter brain or mentions the cloud.
A warm first conversation for someone meeting Fae for the first time — getting to know their name, where they live, and what they care about, showing one thing live, and explaining how to talk to her.
| name | canvas |
| description | Render charts and images in the canvas window by outputting JSON. Use for visualisation, graphing, and displaying data visually. |
| metadata | {"author":"fae","version":"1.0"} |
You have a canvas window. When you output chart or image data, it renders automatically in the canvas for the user to see.
Show a chart when the user asks to visualise, chart, graph, compare, or display data visually. Do NOT use the canvas for simple text answers.
To show a chart, output ONLY a JSON object as your entire response — no text before or after it. The system detects the JSON and renders it to the canvas automatically. You will not see the JSON; the user sees the chart.
After outputting the JSON, on the next turn briefly describe what you showed (e.g. "That bar chart shows sales by quarter.").
Bar chart (comparison):
{"type":"Chart","data":{"chart_type":"bar","data":{"labels":["A","B","C"],"values":[10,20,30]},"title":"My Chart"}}
Line chart (trends):
{"type":"Chart","data":{"chart_type":"line","data":{"labels":["Jan","Feb","Mar"],"values":[100,150,200]},"title":"Trend"}}
Pie chart (proportions):
{"type":"Chart","data":{"chart_type":"pie","data":{"labels":["Red","Blue"],"values":[60,40]},"title":"Split"}}
Scatter plot (correlation):
{"type":"Chart","data":{"chart_type":"scatter","data":{"points":[{"x":1,"y":2},{"x":3,"y":4}]},"title":"Scatter"}}
{"type":"Image","data":{"src":"https://example.com/photo.jpg"}}