larashero3-dotcom/lieflat-charts

Data visualization Skill for AI Agents, turning data into polished, interactive HTML charts. 面向 AI Agents 的数据可视化 Skill，将数据快速生成精致、可交互的 HTML 图表。

What it solves

Lieflat Charts provides a standardized system for AI agents to generate high-quality, editorially-styled data visualizations and full-page HTML reports. It moves beyond generic charting by offering specific visual grammars tailored to different reading speeds—ranging from detailed, narrative-driven data stories to high-level, rapid-judgment dashboards—ensuring that data is presented with professional typography, spacing, and motion.

How it works

The project is implemented as an "Agent Skill" (compatible with SKILL.md formats used by agents like Moxt, Claude Code, and Codex). It provides a library of 49 chart types and 12 full-page report templates. The agent follows a specific workflow: it analyzes the data contract, selects the appropriate visual style (Lupi, Glance, or Basics), and generates an HTML output using a mix of hand-written SVG, Chart.js, and ECharts. It also includes a system of visual tokens for consistent coloring (Mono, Porcelain Blue, Palm Green, and Editorial Red) or custom brand colors.

Who it’s for

  • AI Agent Developers: Those wanting to equip their agents with the ability to produce professional data reports.
  • Data Analysts and Researchers: Users who need to transform raw data into publication-ready visuals for papers, annual reports, or dashboards via an AI interface.
  • Content Creators: People creating data-driven stories for newsletters or social media.

Highlights

  • Three Distinct Visual Styles:
    • Lupi: Narrative-driven, high-detail, and slow-reading (ideal for papers and annual reports).
    • Glance: Aggregated, bold, and fast-reading (ideal for weekly reports and dashboards).
    • Basics: Familiar chart silhouettes with refined editorial quality.
  • Full-Page Report Generation: 12 bilingual (Chinese/English) templates for various scenarios like financial analysis, research briefs, and personal records.
  • Interactive Capabilities: Specialized templates for network graphs, paths, and high-density relationship data.
  • Automated Color Selection: Agents can automatically choose color schemes based on data structure (e.g., Porcelain Blue for ordered sequences) or apply custom brand colors.

Related

  • Project
    op7418/guizang-ppt-skill

    An AI agent skill for generating professional single-file HTML presentations with built-in presenter mode and two distinct high-end visual styles.

  • Project
    markdown-viewer/skills

    A collection of agent skills that enable AI agents to generate professional diagrams, charts, and infographics within Markdown using various rendering engines.

  • Project
    GiMi-Xiaomi/gimi-illustration-skill

    An AI Agent Skill that converts text articles and scripts into conceptual illustrations using customizable styles and consistent character IPs.

  • Project
    plannotator/effective-html

    A collection of specialized agent skills that enable AI agents to create self-contained HTML artifacts like wireframes, prototypes, and diagrams for better visual communication.

  • Project
    KKKKhazix/khazix-skills

    A collection of structured instruction sets for AI agents that provide specialized workflows for goal setting, disk cleanup, research, and writing, following the Agent Skills open standard.