Claude Skill

bentossell/visualise

Visualise 是一个 Claude Skill,用于在代理对话中直接渲染内联交互式视觉元素(SVG 图表、HTML 组件、图表和解释器),以增强沟通效果。

概览

Stars462
Forks26
语言未知
最后更新2026-03-12
最近同步2026-07-03
前往 GitHub

仓库信息

拥有者bentossell
仓库visualise
完整名称bentossell/visualise
Repo ID1,180,254,768

安装这个 Skill

git clone https://github.com/bentossell/visualise.git ~/.agents/skills/visualise

Registry 信息

类型openclaw_skill
质量分70/100
验证状态readme_parsed
最近验证2026-06-11
平台
Claude
能力
browsermemoryterminal
识别文件
README.mdSKILL.md
安装方式
  • git clone https://github.com/bentossell/visualise.git ~/.agents/skills/visualise
  • git clone https://github.com/bentossell/visualise.git .agents/skills/visualise

项目简介

Visualise 是一个 Claude Skill,允许代理在对话中直接渲染内联交互式视觉元素,包括 SVG 图表、HTML 组件、图表和解释器,通过动态视觉内容增强沟通效果。

英文描述

Agent skill for rendering inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — in agent conversations.

要点

  • 渲染内联 SVG 图表,提供清晰的视觉解释
  • 支持 HTML 组件,实现交互式元素
  • 生成图表和图形,用于数据可视化
  • 创建解释器,简化复杂概念
  • 无缝集成到代理对话中

使用场景

  • 在代理回复中使用图表可视化数据趋势
  • 创建交互式图表用于技术解释
  • 构建自定义 HTML 组件以提升用户参与度
  • 通过视觉解释器简化复杂工作流程
  • 使用动态视觉元素增强代理沟通

README 摘要

# visualise An [Agent Skill](https://agentskills.io) that lets coding agents render rich interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly inline in conversations. Instead of describing a flowchart or pasting ASCII art, the agent generates a real interactive visual. Diagrams you can click, sliders you can drag, charts that update live. built by [droid](http://factory.ai/) ## Installation **User-level (recommended)** ``` git clone https://github.com/bentossell/visualise.git ~/.agents/skills/visualise ``` **Project-level** ``` git clone https://github.com/bentossell/visualise.git .agents/skills/visualise ``` ## Usage The skill activates automatically when you ask an agent to: - Visualize, diagram, or chart something - Explain how something works (spatial/sequential concepts) - Compare options side-by-side - Draw, map out, or illustrate an idea Or just say: *"show me"*. ## How It Works The skill uses progressive disclosure to stay lean. At startup, only the name and description are loaded (~100 tokens). When activated, the agent reads the main instructions, then pulls in only the reference docs it needs: - **design-system.md** — CSS variables, color ramps, typography - **components.md** — interactive explainers, comparisons, cards, steppers - **diagrams.md** — flowcharts, structural, illustrative diagrams - **charts.md** — Chart.js and data viz patterns Output is raw HTML/SVG fragments rendered in a sandboxed iframe. No build step, no dependencies. ## Client support This skill teaches agents *what to generate* — it doesn't include a renderer. The output is HTML/SVG wrapped in a `visualizer` code fence. If your agent client supports rendering that fence in a sandboxed iframe, visuals appear inline. If not, the output is s

话题

暂无话题

探索更多

数据来自 GitHub,同步时间:2026-07-03