# ai-interface-reviewer

This skill reviews AI-powered interfaces against a 44-principle taxonomy and returns structured findings with severity and remediation. Use it to assess chat, copilot features, or agent workflows.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 26
- Author: uxuiprinciples
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/uxuiprinciples/agent-skills/tree/HEAD/ai-interface-reviewer/SKILL.md
- Updated: 2026-08-31
- HTML: https://affpapa.org/en/nevibecode/skills/ai-interface-reviewer

## What it does

The skill checks AI interfaces against principles concerning transparency, trust, human control, consent, and conversational design. Its review produces structured findings, rates their severity, and suggests remediation. It applies to chat interfaces, voice assistants, and products where AI can take autonomous actions.

An API key is optional. Enriched results require API Access from uxuiprinciples.com and the `UXUI_API_KEY` variable. The skill includes `curl` calls to retrieve an individual Part V principle or list the principles. Without the key, enriched results are unavailable, so account for that when configuring the skill.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ai-interface-reviewer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ai-interface-reviewer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ai-interface-reviewer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ai-interface-reviewer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install uxuiprinciples/agent-skills ai-interface-reviewer
```

2. **Manually: put the files in place**
- File: `.github/skills/ai-interface-reviewer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/uxuiprinciples/agent-skills --path ai-interface-reviewer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ai-interface-reviewer/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add uxuiprinciples/agent-skills --skill ai-interface-reviewer -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/uxuiprinciples/agent-skills/tree/HEAD/ai-interface-reviewer/SKILL.md

## When to use it
- check whether an interface communicates AI limitations
- find points where users cannot override an agent action
- review how a chatbot handles ambiguous requests
- assess whether users can correct AI output
- spot gaps in consent for AI data use

## Example prompts
- Review this AI chat for clear limits and handling of ambiguous requests.
- Assess this agent workflow and flag actions users cannot override.
- Check whether copilot suggestions fit the interface context and can be dismissed.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [uxuiprinciples/agent-skills](https://affpapa.org/en/nevibecode/by/uxuiprinciples/agent-skills.md) — 5 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md