AI Interface Reviewer

Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires uxuiprinciples.com API Access.

32 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer
Manual install
git clone --depth 1 https://github.com/uxuiprinciples/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/ai-interface-reviewer ~/.claude/skills/ai-interface-reviewer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

```toml
[toolbox.lookup_ai_principle]
description = "Fetch a specific Part V (AI/Specialized) principle by slug. Returns code, aiSummary, businessImpact, tags, and difficulty."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?slug={slug}&include_content=false"]

[toolbox.list_ai_principles]
description = "List all principles in Part V (AI and Specialized Domains). Returns all 44 principles with codes, slugs, and aiSummary fields."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?part=part-5"]
```

## What This Skill Does

You review AI-powered interfaces against the Part V taxonomy: 61 research-backed principles for AI, voice, and agentic interfaces. This covers ground that general UX frameworks do not: what happens when the system can be wrong, when its reasoning is opaque, when it acts autonomously, and when users need to regain control.

Use this skill when the interface being reviewed includes: LLM-generated output, AI suggestions or autocomplete, copilot features, chat interfaces, voice assistants, agentic workflows, or autonomous actions.

For non-AI interfaces, use `uxui-evaluator` (Parts 1-4) instead.

## Part V Framework Structure

Part V (Specialized Domains) is organized into chapters. The AI-relevant chapters are:

### Chapter S.1.1: Voice and Conversational Interfaces
Read the full skill on GitHub

Details

Skill name
ai-interface-reviewer
Path
ai-interface-reviewer/SKILL.md
Repo updated
13 November 2026

FAQ

What does the AI Interface Reviewer skill do?

Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires uxuiprinciples.com API Access.

How do I install the AI Interface Reviewer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Interface Reviewer popular?

It lives in uxuiprinciples/agent-skills, which has 32 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Flow Checker

32

uxuiprinciples/agent-skills

Run preflight and postflight checklists against UX flows before you design and before you ship. Covers onboarding, forms, pricing, dashboards, and empty states. Returns structured findings with severity and smell linkage. Requires uxuiprinciples.com API Access (pro tier).

Frontend & DesignIn 1 list

Interface Auditor

32

uxuiprinciples/agent-skills

Detect UX antipatterns (smells) in interface descriptions using the uxuiprinciples smell taxonomy. Returns structured findings with matched symptoms, severity, and step-by-step remediation recipes. API key optional — full remediation recipes require uxuiprinciples.com API Access.

Software DevelopmentIn 1 list

Uxui Evaluator

32

uxuiprinciples/agent-skills

Evaluate interface descriptions against 195 research-backed UX/UI principles. Returns structured findings with severity, remediation, and business impact. API key optional — enriched output requires uxuiprinciples.com API Access.

Frontend & DesignIn 1 list

Remembering Conversations

43

obra/clank

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

AI, LLMs & Agents26

MCP Builder

49

vitoworleone/claude-code-handbook

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

AI, LLMs & Agents

Siwa

43

builders-garden/siwa

SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.

AI, LLMs & Agents12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.