better-interface

Coordinates six domain skills to review interfaces and produce one prioritized findings report.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/chhpt/skills --skill better-interface-chhpt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: better-interface
Source: https://github.com/chhpt/skills/tree/main/skills/better-interface
Command: npx skills add https://github.com/chhpt/skills --skill better-interface-chhpt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reviewing an interface across accessibility, layout, writing, typography, color, and visual polish often produces six disconnected audits with duplicated or contradictory findings. This Skill orchestrates all six domain reviews into a single consolidated, severity-ranked report with evidence-backed findings. ## Core Features & Use Cases - Cross-Domain Orchestration: Delegates rules to better-accessibility, better-layout, better-writing, better-typography, better-colors, and better-ui, then merges results without duplicating issues. - Quick and Full Modes: Quick mode covers the primary user path with up to 5 HIGH/MEDIUM findings; full mode covers the entire scope including empty, loading, error, and narrow-width states with up to 15 findings. - Evidence-Based Findings: Every finding cites file and line, shows the current implementation, and is ranked by a shared HIGH/MEDIUM/LOW severity scale. - Use Case: Before shipping a new checkout flow, invoke a full interface review to get one ranked table of issues across all six design disciplines, plus a considered-but-rejected list and a final Block/Needs changes/Approve verdict. ## Quick Start Run a full interface review of the checkout flow and consolidate findings from all six design domains into one prioritized report.

Frequently Asked Questions about better-interface

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

FAQPage Schema
How do I run a full interface review across accessibility, layout, and visual design?

Invoke the skill with a scope such as a screen, flow, or feature and request full mode. It loads all six domain skills, reviews each in order, and consolidates results into one severity-ranked findings table with a final verdict.

What is the difference between quick and full interface review modes?

Quick mode covers the primary user path and highest-traffic states, reporting up to 5 HIGH and MEDIUM findings. Full mode covers the entire scope including empty, loading, error, and narrow-width states, with up to 15 findings including LOW severity.

What happens if one of the domain review skills is not available?

The missing domain is marked Not reviewed with the unavailable skill named, and the review continues with the remaining domains. The skill never recreates missing rules from memory or claims holistic coverage it did not perform.

Does the interface review modify my source code?

No, reviews are read-only by default. Source code is only edited when you explicitly ask for implementation, in which case the consolidated report becomes the change scope and verification is re-run afterward.

Why does the review report include a considered-but-rejected section?

It records borderline candidates that were inspected but deliberately rejected, such as changes the owning skill permits or that lack evidence. This makes the review's restraint visible and prevents repeated debate over settled decisions.