viz

Design and critique analytical visualizations and dashboard displays.

12|2|Updated Jun 8, 2026

Search Tags:#dashboard #visualization #sparklines #tufte #chart critique #analytical design

Ready to run

npx skills add https://github.com/Loringtonian/second-brain-template --skill viz-loringtonian

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: viz
Source: https://github.com/Loringtonian/second-brain-template/tree/main/.claude/skills/viz
Command: npx skills add https://github.com/Loringtonian/second-brain-template --skill viz-loringtonian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you design, critique, and clean up analytical visuals so they are easier to compare, more truthful, and less cluttered.

Core Features & Use Cases

Visualization critique: Spot misleading scales, weak baselines, decorative noise, and other forms of chartjunk.
Analytical design: Build dense dashboards, tables, small multiples, sparklines, and scorecards that preserve comparison and context.
Use cases: Improve trading dashboards, review queues, idea-ranking cockpits, feed-curation views, and HTML reports where the goal is to understand evidence quickly.

Quick Start

Use the viz skill to critique this dashboard and propose a cleaner, more truthful layout.

Frequently Asked Questions about viz

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I critique a dashboard to remove chartjunk and improve graphical integrity?▼

Dashboard critique spots misleading scales, weak baselines, and decorative chartjunk to improve graphical integrity. Applying Tufte-style comparison and layering ensures your analytical visualizations maintain high data-ink density and truthful scales for decision support.

What is the best way to design small multiples and sparklines for analytical dashboards?▼

Designing small multiples and sparklines requires Tufte-style comparison and layering. This approach builds dense dashboard displays and scorecards that preserve context and high data-ink density, allowing quick, truthful comparison of analytical evidence.

Can I use this visualization critique approach for HTML cockpit views and review queues?▼

Yes, this visualization critique approach works for HTML cockpit views, review queues, and feed-curation views. It designs truthful analytical displays with clear provenance, ensuring high data-ink density for faster evidence understanding and decision support.

How do I fix misleading scales and weak baselines in my data visualizations?▼

Fix misleading scales and weak baselines by applying analytical design principles that prioritize high data-ink density. Critiquing existing charts and tables identifies decorative noise, proposing cleaner, more truthful layouts that eliminate chartjunk and strengthen graphical integrity.

When should I not use dense dashboard displays for data comparison?▼

Avoid dense dashboard displays when clear provenance and truthful scales cannot be maintained. If analytical visualizations prioritize decorative noise over high data-ink density, Tufte-style comparison and layering will not effectively improve evidence understanding or decision support.