antvis/chart-visualization-skills

⛏️ Turning data into a visual language for better thinking with Skills.

What it solves

This project provides a set of AI-powered skills and tools to automate the generation of professional data visualizations. It bridges the gap between raw data and visual charts by allowing AI agents to intelligently select chart types, generate runnable code for various AntV libraries, and create complex infographics or narrative reports.

How it works

The project functions as a plugin system for AI agents (like Claude Code) and a context retrieval service. It offers several specialized "skills" that the AI can use to generate specific outputs:

  • Chart Generation: Uses AntV libraries (G2, G6, X6) to produce everything from statistical charts and network graphs to interactive diagram editors.
  • GPT-Vis: A framework-agnostic approach using a markdown-like syntax for streaming chart generation.
  • Infographics & Narratives: Tools to transform text into visual infographics or structured narrative reports using T8 Syntax.
  • Context Service: An HTTP API and CLI tool that provides the AI with the relevant documentation and constraints (via hybrid search) to ensure the generated code is accurate and follows best practices.

Who it’s for

  • AI Agent Developers: Those building agents that need to generate high-quality, runnable visualization code.
  • Data Analysts: Users who whom want to automate the data-to-chart workflow using AI.
  • Frontend Developers: Developers using AntV libraries who want AI-assisted code generation for complex charts.

Highlights

  • Comprehensive Library: Supports 26+ chart types and multiple specialized libraries for graphs, editors, and infographics.
  • Harness Engineering: Rigorously tested to achieve up to 98.2% accuracy in chart generation compared to baseline LLMs.
  • Hybrid Retrieval: Combines FTS and Vector search to provide AI models with precise context for code generation.
  • Multi-Framework Support: Generates code for HTML, React, and Vue.

Related

  • Project
    antvis/mcp-server-chart

    An MCP server that enables AI models to generate over 26 types of professional charts and diagrams using the AntV visualization library.

  • Project
    yjz211/vivid-figures-skill

    Vivid Figures is an Agent‑Skill that equips AI assistants with 143 ready‑made chart templates and seven colour palettes. By feeding an assistant a data file (CSV, Excel, JSON) and a natural‑language request, the skill automatically selects a suitable plot, renders PNG/PDF outputs, and provides the full Python source for later tweaking. It follows the open Agent Skills spec, runs on Python 3.10+, and is free for personal, non‑commercial use.

  • Project
    MoizIbnYousaf/ai-agent-skills

    A genuine npm‑based CLI/TUI that ships a curated library of AI‑agent skills, lets you build and manage your own skill collections, and integrates with many LLM‑agents via the Agent Skills spec.

  • Project
    yejy53/Editable-Design

    Editable‑Design is a GitHub project that offers Codex Skills for AI‑driven creation of editable visual assets (posters, infographics, research diagrams). Users install a Skill, give a natural‑language prompt, and receive structured HTML/CSS (or PPTX) with real text, separate image layers, a visual editor, and a replay of the agent’s design steps.

  • Project
    OpenSenseNova/SenseNova-Skills

    A suite of end-to-end office capabilities for AI agents, enabling automated PPT generation, deep research, Excel data analysis, and infographic creation.