How do I install the Claud3 skill?

Run npx skillmds add podo/claud3 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Claud3 safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Claud3?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Claud3 free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Claud3?

podo (@podo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claud3 by podo — Agent Skill

Name: Claud3
Rating: 4.666666666666667 (3 reviews)
Author: podo

Claud3

D3.js data visualization skill based on Edward Tufte principles. Selects the right chart type from 80+ options by analyzing the data question, then generates single-file HTML with D3 v7, dark theme, responsive layout, direct labels, and annotations.

podo fbdbecf 2 files · 1.9 KB Updated Sep 9, 2026

File contents

claud3

Catalogue stub — full package: dtran320/claud3

Decision tree

Is the package already installed? Check: ~/.design-agent-skills/skills/claud3/SKILL.md exists.
- Yes → invoke claud3 and proceed
- No → go to step 2
Do you have shell access?
- Yes → run the install command below, then invoke the skill
- No → show the install command; in Claude Code, send it as a chat message starting with ! — add -g for global install or omit for project-only

Install command

npx skills add dtran320/claud3

Invoke after install

Skill name: claud3
Trigger phrases: "claud3", "D3 Tufte", "80 chart types", "D3 dark theme"

What it does

Applies Edward Tufte's data visualization principles to D3.js chart generation. Analyzes the underlying data question to select the most appropriate chart type from a library of 80+ options, then produces self-contained single-file HTML using D3 v7 with a dark theme, responsive layout, direct data labels (no separate legend), and contextual annotations. Includes a playground mode for interactive exploration and refinement.

When NOT to use

Multi-library visualization agents — use data-viz-agent instead
AntV/G2 charts — use antvis-chart-skills instead
Quick single charts without Tufte constraints — use d3js-skill instead

Frequently asked questions