Skip to main content
skill CX Codex

millers-law — Claude Code skill: what it does, how to install

Chunks interface elements into groups of about four to fit working memory limits. Useful when structuring navigation menus, onboarding flows, and form sections.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Owl-Listener/designer-skills --skill millers-law -a claude-code
Open on GitHub

What millers-law does

This skill guides the agent in structuring interfaces using cognitive psychology. Structure comes before counting. Instead of treating seven items as an absolute limit, it incorporates Nelson Cowan's 2001 findings. Working memory reliably holds roughly 4 ± 1 meaningful chunks. The skill applies this directly to navigation links and long forms.

The instructions divide long lists into readable sections using headings and whitespace. Common examples include phone numbers, data tables, and pricing tiers with 3–5 bullets. When the goal is reducing available decision branches rather than grouping them, the skill defers to hicks-law. This distinction prevents confusion between organizing data and cutting choices.

The rule does not apply to colors or icons. Visual chunking operates under different mechanisms. Familiarity also expands chunk capacity, so experienced users easily handle higher information density. The prompt advises testing actual recall after navigation instead of policing raw item numbers.

What it helps with

  • split long forms into distinct titled sections
  • group flat navigation menus into category clusters
  • structure multi-step onboarding into 3–5 named phases
  • format pricing tier feature lists into concise blocks

Example prompts for the agent

  • Apply Miller's Law to organize this flat settings menu into grouped categories.
  • Break this registration form into distinct sections with clear headings.
  • Organize this 12-step onboarding sequence into 3 to 5 named phases.

How to install millers-law

1Skills CLI (Vercel)

npx skills add Owl-Listener/designer-skills --skill millers-law -a claude-code

2Manually: put the files in place

~/.claude/skills/millers-law/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/millers-law/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about millers-law

How do I install millers-law in Claude Code?

Run npx skills add Owl-Listener/designer-skills --skill millers-law -a claude-code.

What does the millers-law skill do?

It provides guidelines for chunking interface items like navigation links, form inputs, and table rows into groups of about four units. This aligns interface complexity with human working memory limits.

When should I use hicks-law instead of millers-law?

Use millers-law when you need to organize and group elements into readable chunks. If your task is to decrease the actual number of choices presented to the user, use hicks-law.

Source text

SKILL.md · MIT
---
name: millers-law
description: Apply Miller's Law — chunk information into groups of about four to fit working memory. Use when grouping fields, menu items, or steps. For reducing the number of choices offered, use `hicks-law`.
---
# Miller's Law
You are an expert in cognitive psychology as it applies to information design and interface structure.
## What You Do
You apply chunking and grouping strategies informed by working memory research to make interfaces easier to scan, understand, and recall.
## The Principle and Its Limits
George Miller's 1956 paper proposed that working memory can hold **7 ± 2 items** (5–9). This figure has been widely cited in UX design — and just as widely misapplied.
More recent research (particularly Nelson Cowan, 2001) suggests the realistic limit for **meaningful chunks in working memory is closer to 4 ± 1**. The important nuance Miller himself made: the "7" applies to **chunks**, not raw items. A chunk is whatever unit has meaning to the person — a word, a concept, a familiar pattern.
**What this means for design:**
- Grouping items into meaningful chunks reduces cognitive load regardless of the exact number
- The precise ceiling is less important than the principle: working memory is limited, and structure helps
- Don't cite "7 items" as a design rule; cite chunking as the strategy
## Where Chunking Applies
- **Navigation**: group menu items by category; flat lists of 10+ items are harder to scan than 3 groups of 3–4
- **Forms**: break long forms into sections with clear headings — each section should feel completeable as a unit
- **Phone numbers and codes**: formatted as chunks (e.g. `555-867-5309`, `XXXX-XXXX` verification codes) for easier recall
- **Data tables**: use visual grouping (alternating rows, section headers) to break long lists into scannable blocks
- **Onboarding steps**: show progress as 3–5 named phases rather than a raw step count of 12
- **Feature lists and pricing**: 3–5 bullet points per tier; beyond that, users stop reading
## Common Misapplications
- Using "7 is the limit" to justify navigation menus of exactly 7 items
- Applying it to visual elements (colors, icons) where visual chunking works differently than verbal memory
- Ignoring that familiarity expands chunk size: expert users chunk more than novice users
## Best Practices
- Structure first, count second — meaningful groupings matter more than hitting a number
- Use headings, whitespace, and visual dividers to make chunks explicit
- Test recall, not just comprehension — can users remember what options were available after navigating away?
- Adjust for user expertise: power users handle larger information density than first-time users

© Owl-Listener · MIT · Owl-Listener/designer-skills

Similar skills

Everything for Design →

From the same set111

critique-information-density A skill that critiques a rendered screen's density: cognitive load, content priority, scanning patterns and progressive disclosure. Useful when a screen feels overwhelming. CX Codex +1 1,700installs research-repository Helps teams organize UX findings into a structured repository so research insights stay searchable, reusable, and linked to evidence. CX Codex +1 1,700installs doherty-threshold This skill sets response-time targets for interface interactions and suggests feedback patterns when a wait cannot be avoided. CX Codex +1 1,700installs content-strategy Works out what content a product needs, where it lives and who owns it. Useful when the content itself is the problem, not the layout. CX Codex +1 1,700installs design-system-governance This skill lays out how a design system changes over time: ownership, contribution, versioning, deprecation. It fits teams where more than one group ships components. CX Codex +1 1,700installs design-debt-audit Takes stock of accumulated design inconsistencies across a product and returns a prioritised fix plan. Useful once drift has built up over time. CX Codex +1 1,700installs von-restorff-effect This skill guides coding agents to isolate a single primary action on a screen using visual contrast. It applies when one choice must grab attention immediately. CX Codex +1 1,700installs hicks-law A skill that applies Hick's Law — decision time grows with the number of simultaneous choices. Useful when a screen throws too many options at the user. CX Codex +1 1,700installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor