Agent skill

Chart Visualization

by stophobia in stophobia/deerflow2.0-enhanced

This skill should be used when the user wants to visualize data.

MITAuto-check passedData & Analytics

Install Chart Visualization

skills CLI
$ npx skills add stophobia/deerflow2.0-enhanced --skill chart-visualization -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install stophobia/deerflow2.0-enhanced chart-visualization --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/stophobia/deerflow2.0-enhanced.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/chart-visualization .claude/skills/chart-visualization && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chart-visualization
GitHub stars
820
Token cost
~2.1k tokens
SKILL.md length
722 words
Files
29 (incl. scripts, references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when the user wants to visualize data.

  • Works in 4 steps: Intelligent Chart Selection → Parameter Extraction → Chart Generation → …
  • Wants to visualize data
  • SKILL.md covers Workflow, Interactive Charts (NEW!), 3D Charts (NEW!) and Real-time Dashboard (NEW!), plus 5 more sections
  • Calls node

What it does

Chart Visualization is an agent skill from stophobia/deerflow2.0-enhanced. This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script. Supports both static images and interactive HTML charts.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts and reference files (for example `references/generate_area_chart.md`, `references/generate_bar_chart.md` and `references/generate_boxplot_chart.md`).

It sits in Data & Analytics, covering HTML artifacts. It works with JavaScript. The repository describes itself as: DeerFlow 2.0 Enhanced - Chinese localization + New skills. The licence is MIT.

When your agent uses it

  • Wants to visualize data
  • Tasks that involve HTML artifacts

Example prompts

  • “/chart-visualization”

Requirements

  • Node.js

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Intelligent Chart Selection
  2. Parameter Extraction
  3. Chart Generation
  4. Result Return

What it can do on your machine

Read from SKILL.md and the folder at commit 814bde3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chart Visualization loads about 2.1k tokens when it runs, and up to ~9.2k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 722 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from stophobia/deerflow2.0-enhanced at commit 814bde3, republished under its MIT licence (© stophobia). 722 words, ~2,131 tokens.

Download SKILL.mdSave it as .claude/skills/chart-visualization/SKILL.md (or your agent's skills folder). This skill also uses 28 other files; get the full folder from GitHub.
name
chart-visualization
description
This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script. Supports both static images and interactive HTML charts.
dependency.nodejs
>=18.0.0

Chart Visualization Skill

This skill provides a comprehensive workflow for transforming data into visual charts. It handles chart selection, parameter extraction, and image generation. Supports both static images and interactive HTML charts.

Workflow

To visualize data, follow these steps:

1. Intelligent Chart Selection

Analyze the user's data features to determine the most appropriate chart type. Use the following guidelines (and consult references/ for detailed specs):

  • Time Series: Use generate_line_chart (trends) or generate_area_chart (accumulated trends). Use generate_dual_axes_chart for two different scales.
  • Comparisons: Use generate_bar_chart (categorical) or generate_column_chart. Use generate_histogram_chart for frequency distributions.
  • Part-to-Whole: Use generate_pie_chart or generate_treemap_chart (hierarchical).
  • Relationships & Flow: Use generate_scatter_chart (correlation), generate_sankey_chart (flow), or generate_venn_chart (overlap).
  • Maps: Use generate_district_map (regions), generate_pin_map (points), or generate_path_map (routes).
  • Hierarchies & Trees: Use generate_organization_chart or generate_mind_map.
  • Specialized:
    • generate_radar_chart: Multi-dimensional comparison.
    • generate_funnel_chart: Process stages.
    • generate_liquid_chart: Percentage/Progress.
    • generate_word_cloud_chart: Text frequency.
    • generate_boxplot_chart or generate_violin_chart: Statistical distribution.
    • generate_network_graph: Complex node-edge relationships.
    • generate_fishbone_diagram: Cause-effect analysis.
    • generate_flow_diagram: Process flow.
    • generate_spreadsheet: Tabular data or pivot tables for structured data display and cross-tabulation.
2. Parameter Extraction

Once a chart type is selected, read the corresponding file in the references/ directory (e.g., references/generate_line_chart.md) to identify the required and optional fields. Extract the data from the user's input and map it to the expected args format.

3. Chart Generation

Invoke the scripts/generate.js script with a JSON payload.

Payload Format (Static Image):

json
{
  "tool": "generate_chart_type_name",
  "args": {
    "data": [...],
    "title": "...",
    "theme": "...",
    "style": { ... }
  }
}

Payload Format (Interactive HTML):

json
{
  "tool": "generate_chart_type_name",
  "args": {
    "data": [...],
    "title": "...",
    "theme": "...",
    "interactive": true,
    "style": { ... }
  }
}

Execution Command:

bash
node ./scripts/generate.js '<payload_json>'
4. Result Return

The script will output the URL of the generated chart image (or HTML file for interactive charts). Return the following to the user:

  • The image/HTML URL.
  • The complete args (specification) used for generation.

Enhanced Capabilities (v2.0)

Interactive Charts (NEW!)

In addition to static images, now you can generate interactive HTML charts with ECharts:

When to Use Interactive Charts
  • User wants to explore data (hover, zoom, click)
  • Dashboard presentations
  • Web embedding
  • Data storytelling with drill-down
Interactive Chart Types

All 26 chart types support interactive mode. Key additions:

Chart TypeUse CaseInteractive Features
Line/AreaTrendsZoom, pan, tooltip
Bar/ColumnComparisonsSort, filter, tooltip
Pie/TreemapCompositionDrill-down, legend toggle
ScatterCorrelationZoom, brush selection
MapGeographicZoom, pan, region click
SankeyFlowHover highlight, flow focus
NetworkRelationshipsDrag nodes, zoom
RadarMulti-dim comparisonTooltip, legend
How to Generate Interactive Charts

Step 1: Add interactive: true to args:

json
{
  "tool": "generate_line_chart",
  "args": {
    "data": [
      {"month": "Jan", "value": 120},
      {"month": "Feb", "value": 150},
      {"month": "Mar", "value": 180}
    ],
    "title": "Monthly Sales Trend",
    "interactive": true
  }
}

Step 2: Execute:

bash
node ./scripts/generate.js '<payload>'

Step 3: Output:

  • Returns HTML file path: /mnt/user-data/outputs/chart_xxxxx.html
  • Open in browser for full interactivity
  • Can be embedded in websites
Interactive Features Available
FeatureDescription
TooltipHover to see exact values
LegendClick to toggle series
Zoom/PanDrag to zoom, scroll to pan
DataZoomSlider for range selection
ToolboxSave as image, data view, etc.
Drill-downClick to see details
AnimationSmooth transitions

Show full SKILL.md (285 more words)Show less

3D Charts (NEW!)

Generate 3D visualizations for impressive presentations:

Available 3D Charts
  • generate_3d_bar_chart - 3D bar comparison
  • generate_3d_scatter_chart - 3D scatter plot
  • generate_3d_surface_chart - 3D surface (for terrain/heatmaps)
  • generate_globe_chart - Interactive globe for geographic data
Usage
json
{
  "tool": "generate_3d_bar_chart",
  "args": {
    "data": [...],
    "title": "3D Sales Comparison",
    "theme": "dark"
  }
}

Real-time Dashboard (NEW!)

Create a dashboard with multiple interactive charts:

Use Case
  • Multi-metric monitoring
  • Cross-chart filtering
  • Time-range selection
How to Create
  1. Generate multiple interactive charts
  2. Combine into dashboard HTML
  3. Add cross-filter functionality

Example payload:

json
{
  "tool": "generate_dashboard",
  "args": {
    "charts": [
      {"type": "line", "data": [...], "title": "Trend"},
      {"type": "bar", "data": [...], "title": "Comparison"},
      {"type": "pie", "data": [...], "title": "Distribution"}
    ],
    "layout": "grid",
    "theme": "light"
  }
}

Geo Visualization (NEW!)

Enhanced map capabilities:

Features
  • Choropleth Map: Color-coded by value
  • Heat Map: Density visualization
  • Flow Map: Movement between locations
  • Bubble Map: Size-coded points
  • Route Map: Path visualization
Data Format
json
{
  "data": [
    {"name": "Beijing", "value": 100},
    {"name": "Shanghai", "value": 80},
    {"name": "Guangzhou", "value": 60}
  ],
  "geoJson": "china"  // or custom GeoJSON URL
}

Usage Guidelines

Choosing Chart Type
Data TypeStatic ImageInteractive
Simple comparison✅ Bar, Column✅ Bar, Column
Time series✅ Line, Area✅ Line, Area (recommended)
Composition✅ Pie, Treemap✅ Pie (recommended)
Correlation✅ Scatter✅ Scatter (recommended)
Geographic✅ Map✅ Map (recommended)
Complex relationships⚠️ Network✅ Network (recommended)
Dashboard❌✅ Multiple charts
Best Practices
  1. Interactive for exploration - Use interactive when user will explore data
  2. Static for reports - Use static images for PDF reports
  3. 3D sparingly - 3D can distort perception, use for impact only
  4. Dashboard for monitoring - Combine related metrics
  5. Mobile consideration - Interactive charts work on mobile too

Output Handling

Static Images
  • Format: PNG
  • Resolution: 1920x1080 (default)
  • Location: /mnt/user-data/outputs/
Interactive HTML
  • Format: HTML with ECharts
  • Features: Full interactivity
  • Location: /mnt/user-data/outputs/chart_*.html
  • Can be opened in browser or embedded
Sharing
  • Use present_files tool to share with user
  • For interactive, share the HTML file path
  • Can be hosted on internal server

Reference Material

Detailed specifications for each chart type are located in the references/ directory. Consult these files to ensure the args passed to the script match the expected schema.

License

This SKILL.md is provided by antviz/chart-visualization-skills. Licensed under the MIT License.

© stophobia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 28 other files (scripts, references) in skills/public/chart-visualization of stophobia/deerflow2.0-enhanced.

  • SKILL.md
  • references/generate_area_chart.md
  • references/generate_bar_chart.md
  • references/generate_boxplot_chart.md
  • references/generate_column_chart.md
  • references/generate_district_map.md
  • references/generate_dual_axes_chart.md
  • references/generate_fishbone_diagram.md
  • references/generate_flow_diagram.md
  • references/generate_funnel_chart.md
  • references/generate_histogram_chart.md
  • references/generate_line_chart.md
  • references/generate_liquid_chart.md
  • references/generate_mind_map.md
  • references/generate_network_graph.md
  • references/generate_organization_chart.md
  • references/generate_path_map.md
  • references/generate_pie_chart.md
  • references/generate_pin_map.md
  • references/generate_radar_chart.md
  • … and 9 more

Open the folder on GitHubat commit 814bde3

Compare with similar skills

Chart Visualization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chart Visualization compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chart Visualization this skillstophobia/deerflow2.0-enhanced820—~2.1kAutomated safety check: PassMIT
HTML DesignNimaChu/html-design101—~2.7kAutomated safety check: PassNone
Sdf Artshaun8149/sdf-js421—~9.7kAutomated safety check: PassCustom licence
Mvizmatsonj/mviz226—~11kAutomated safety check: PassNone
Checking A Pageawss1i/assay102—~712Automated safety check: PassMIT
Web Design EngineerConardLi/garden-skills13k—~8.8kAutomated safety check: PassMIT

Similar skills

  • HTML Design

    NimaChu/html-design

    Create, redesign, repair, validate, preview, and package lightweight standalone HTML deliverables.

    101 GitHub stars~2.7k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Sdf Art

    shaun8149/sdf-js

    Generate sdf-js code from a natural-language scene description.

    421 GitHub stars~9.7k tokensUpdated 18 days ago
    Frontend & DesignAuto-check passed
  • Mviz

    matsonj/mviz

    A chart & report builder for AI. An agent skill from matsonj/mviz.

    226 GitHub stars~11k tokensUpdated 4 mo ago
    Data & AnalyticsAuto-check passed
  • Checking A Page

    awss1i/assay

    Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it.

    102 GitHub stars~712 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Web Design Engineer

    ConardLi/garden-skills

    Builds polished browser-rendered HTML, CSS, JavaScript and React pages, dashboards, prototypes and slide decks, aiming for a stunning rather than merely functional result.

    13k GitHub stars~8.8k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • D3 Visualization

    benchflow-ai/skillsbench

    Build deterministic, verifiable data visualizations with D3.js (v6).

    1.8k GitHub stars~1.5k tokensUpdated 2 mo ago
    Data & AnalyticsAuto-check passed

More from stophobia/deerflow2.0-enhanced

  • Company Research

    stophobia/deerflow2.0-enhanced

    综合企业背景调研技能,用于尽职调查、合作伙伴评估、投资分析、市场研究等场景。支持公司工商信息、财务数据、法律风险、舆情分析、竞品对比等多维度调研,自动生成Markdown和HTML格式的专业调研报告。触发条件:用户提及"企业调研"、"公司背景"、"尽职调查"、"合作伙伴评估"、"投资分析"、"市场研究"等关键词。

    820 GitHub stars~845 tokensUpdated 6 mo ago
    Auto-check passed
  • Multi Language

    stophobia/deerflow2.0-enhanced

    多语言翻译技能,支持中英日德法等多种语言的互译。专注于专业术语的准确翻译,保持原文格式一致性,适用于技术文档、学术论文、商业报告等专业化内容的翻译。触发条件:用户提及"翻译"、"中英翻译"、"英文版"、"多语言"、"localization"等关键词。

    820 GitHub stars~650 tokensUpdated 6 mo ago
    Auto-check passed
  • Paper Research

    stophobia/deerflow2.0-enhanced

    学术论文调研技能,用于搜索、筛选和分析学术论文。支持 arXiv、Google Scholar、Semantic Scholar 等学术数据库,提供论文检索、引用分析、研究趋势追踪、文献综述生成等功能。触发条件:用户提及"论文"、"学术研究"、"文献综述"、"arXiv"、"研究趋势"、"学术搜索"等关键词。

    820 GitHub stars~661 tokensUpdated 6 mo ago
    Auto-check passed
  • Report To Ppt

    stophobia/deerflow2.0-enhanced

    将 Markdown 格式的报告自动转换为 PPT 演示文稿。智能提取报告中的标题、关键信息、图表描述,生成结构清晰的幻灯片。适用于调研报告、咨询报告、市场分析等文档的快速 PPT 化。触发条件:用户提及"报告转PPT"、"Markdown转PPT"、"生成演示文稿"、"做PPT"等关键词,且已有 Markdown 报告文件。

    820 GitHub stars~646 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Chart Visualization

What does Chart Visualization do?

This skill should be used when the user wants to visualize data. 0-enhanced. This skill should be used when the user wants to visualize data.

When should I use Chart Visualization?

Chart Visualization fits situations like: wants to visualize data; tasks that involve HTML artifacts.

How do I install Chart Visualization in Claude Code?

Run `npx skills add stophobia/deerflow2.0-enhanced --skill chart-visualization -a claude-code`. Or copy the skill folder (skills/public/chart-visualization in stophobia/deerflow2.0-enhanced) into .claude/skills/chart-visualization in your project. Claude Code loads it when a task matches its description.

How do I install Chart Visualization in Codex?

Run `npx skills add stophobia/deerflow2.0-enhanced --skill chart-visualization -a codex`. Or copy the skill folder (skills/public/chart-visualization in stophobia/deerflow2.0-enhanced) into .agents/skills/chart-visualization in your project. Codex loads it when a task matches its description.

Can I use Chart Visualization in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add stophobia/deerflow2.0-enhanced --skill chart-visualization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chart-visualization, .gemini/skills/chart-visualization, .github/skills/chart-visualization and .opencode/skills/chart-visualization in your project.

What does Chart Visualization need to run?

Going by SKILL.md and its folder, Chart Visualization needs the command-line tools its instructions call (node). Our summary lists: Node.js.

Does Chart Visualization access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Chart Visualization safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Chart Visualization use?

Chart Visualization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chart Visualization use?

About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.1k tokens, read only when the agent opens those files.

What are the alternatives to Chart Visualization?

Skills that share tags, products or a category with Chart Visualization: HTML Design (NimaChu/html-design, 101 stars), Sdf Art (shaun8149/sdf-js, 421 stars), Mviz (matsonj/mviz, 226 stars) and Checking A Page (awss1i/assay, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chart Visualization?

stophobia (a GitHub user) maintains it in stophobia/deerflow2.0-enhanced, which has 820 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on March 23, 2026.

Source: stophobia/deerflow2.0-enhanced on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.