visualize

A tool that turns structured data into interactive charts, comparison views, explorers, or adjustable simulations inside the conversation.

In plain words
What is it for?
Use it to explore CSV, TSV, JSON, Excel, or workspace data with charts, tables, filters, selections, and adjustable parameters.
Why use it?
It helps people inspect data by filtering, selecting, and drilling into details instead of reading raw files. The visual stays focused on the fields and interactions needed for the question.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nullskymc/aurevoy/visualize
Any agent
npx skills add nullskymc/Aurevoy --skill visualize
Clone the repo
git clone --depth 1 https://github.com/nullskymc/Aurevoy

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.01551
Opus 5 $0.00039 $0.00776
Sonnet 5 $0.00016 $0.00310
Haiku 4.5 $0.00008 $0.00155

Measured 2d ago against content hash 9128f9341d32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visualize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

apps/agent/skills/builtin/visualize/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visualize

使用 present_ui(kind="canvas") 将交互式可视化直接放入对话流。Canvas 在 sandbox iframe 中运行,HTML、CSS、JavaScript 与数据均不离开该片段;不要改为 HTML 文件附件,也不要声称它是应用页面。

数据与范围

  1. 先定位用户给出的 CSV、TSV、JSON、Excel 或工作区数据文件,读取少量样本与字段名,确认单位、时间范围、缺失值和唯一标识。
  2. 数据不存在时,简洁请求文件或路径。仅当用户明确说“随便生成”“示例”或“看看效果”时,才创建并标注为合成演示数据。
  3. 只保留支撑交互与详情的字段。大数据集先聚合、分箱或抽样,避免把原始大文件完整内联。
  4. 选择最小合适的图形:数值关系用散点/折线,分类比较用条形图,构成变化用堆叠图,密集类别用可选择网格;地理数据必须使用真实的 GeoJSON/经纬度与投影。

创建 Canvas

  1. 调用 present_ui,固定 kind="canvas"。根对象只能有 kindidfallbackTextpropstitledescriptionhtmlcssscriptstate 都必须放在 propsprops.html 必须是 HTML fragment(不是完整文档),交互时再提供 script;给稳定的 id,后续更新时复用它。
  2. 使用内联数据、CSS 和 JavaScript。不要使用 fetch、XHR、WebSocket、远程 CDN、外部图片、parenttopopener 或其他宿主窗口 API。
  3. 只添加用户要求的筛选、选择或参数控件;使用语义化的 labelselectinputbutton 和原生键盘交互。筛选变化必须立刻更新主图、列表/表格和选中详情。
  4. 保持一个主视觉、紧凑的已选项详情和必要的图例。默认不做 KPI 卡;只有用户明确要求且指标随交互变化时,最多保留三个。不要堆砌装饰性状态块、搜索框或“重置”按钮。
  5. 让图表本身可读:标注轴、单位、关键值和多系列图例;颜色之外同时使用形状、文字或线型。为 SVG/Canvas 提供标题、描述或等价可访问文本。
  6. 设计为窄宽度也可用:避免固定视口高度、水平溢出、固定定位和内部滚动;控件在窄屏换行,表格过宽时提供响应式容器。
  7. 所有用户输入与交互状态保留在 Canvas 内。window.aurevoy.state 只读地提供初始状态;不要尝试向宿主发送消息或读取宿主数据。

Aurevoy 视觉语言

Canvas 是 Aurevoy 对话的一部分,不是独立网页或通用暗色 dashboard。外层卡片已经展示 props.titleprops.description,因此 HTML fragment 内不要重复标题、日期横幅或第二层页面容器。

  1. 颜色必须使用 Canvas 已注入的主题变量:--av-bg--av-surface--av-text--av-muted--av-border--av-accent--av-accent-contrast--av-accent-soft-bg--av-accent-soft-fg。不要硬编码整套浅色/深色调色板、Tailwind 色值、白色卡片或黑灰背景;深浅主题必须自然切换。
  2. 根节点保持透明、无边框、无阴影、全宽。只在必要的选中详情或少量动态指标上使用一个低强调 surface;不要给每条列表项、分组或布局容器重复套卡片。
  3. 延续项目的克制留白与 Mist Teal 强调:正文使用 --av-text,辅助信息用 --av-muted,只将 --av-accent 用于当前选中态、关键标记和一个主要操作。不要把多种鲜艳颜色当作装饰。
  4. 片段内不使用 <h1>,也不重述用户请求。标题交给 props.title;图例、坐标、数值和当前选中项才留在片段中。
  5. 控件必须使用原生 <button><input><select><textarea>,并保留浏览器焦点样式。不要用可点击的 <div>、伪 tab 或仅靠颜色表达选中状态;筛选 tab 要用 button,并提供 aria-pressedaria-selected
  6. 列表或新闻流默认只展示摘要;点击或键盘选择一项后才显示该项详情。不要让全部条目在首屏同时展开。卡片点击区域应是明确的 button,而不是整个 div

Read the full file on GitHub · 54 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 54 lines · 79 tokens per session scan A 9128f9341d32

Subscribe to this mod's changes

visualize is a skill published in the GitHub repository nullskymc/Aurevoy (10 stars, last pushed 26d ago), licensed MIT. It adds 79 tokens to every session and 1,551 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

create_profile_style_skill

【META SKILL】分析当前剪辑逻辑与风格,总结并生成一个新的可复用 Skill 文件,存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.

FireRedTeam/FireRed-OpenStoryline · 64 tokens

company-product-context

Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.

lofcz/LLMTornado · 20 tokens

Paper Writing Workflow

Workflow phases for paper-writing tasks: triage, material inventory, research question, literature review, paper outline, data analysis summary, figure storyline, reader testing, and finalize packet. Each phase is a short contract — read the relevant rows for the current task only.

aristoteleo/PantheonOS · 58 tokens

codebase-context-extractor

This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.

lofcz/LLMTornado · 42 tokens

deep-researcher

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.

lofcz/LLMTornado · 27 tokens

llmtornado-tutorial-generator

Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.

lofcz/LLMTornado · 31 tokens