ux-baseline-check

Core pack — always active for visual work. Enforces UX quality standards on any screen, flow, form, or dashboard. Ensures nothing ships with missing states. Auto-activates alongside design-review for all frontend work.

3,891 stars

Best use case

ux-baseline-check is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Core pack — always active for visual work. Enforces UX quality standards on any screen, flow, form, or dashboard. Ensures nothing ships with missing states. Auto-activates alongside design-review for all frontend work.

Teams using ux-baseline-check should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/ux-baseline-check/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aa-on-ai/ux-baseline-check/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/ux-baseline-check/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How ux-baseline-check Compares

Feature / Agentux-baseline-checkStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Core pack — always active for visual work. Enforces UX quality standards on any screen, flow, form, or dashboard. Ensures nothing ships with missing states. Auto-activates alongside design-review for all frontend work.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# UX Baseline Check

## Core Pack — Always Active
This is a core skill. Apply it on ALL visual and frontend work alongside design-review.

Every screen ships with ALL states covered. No exceptions. This is the minimum bar.

## The State Inventory

Before any page or component is "done", verify each applicable state exists:

### 1. Data States
- [ ] **Empty** — no data yet. Helpful message + clear CTA, not a blank screen
- [ ] **Loading** — skeleton, spinner, or shimmer. Never a white flash
- [ ] **Loaded** — the happy path, obviously
- [ ] **Error** — API failure, network issue. User-friendly message + retry action
- [ ] **Partial** — some data loaded, some failed. Don't hide what works
- [ ] **Long content** — what happens with 200 items? 2000-character names? Test it

### 2. Interaction States
- [ ] **Hover** — every clickable element has a hover state
- [ ] **Focus** — keyboard navigation works, focus rings visible
- [ ] **Active/pressed** — buttons respond to clicks visually
- [ ] **Disabled** — grayed out with clear reason why (tooltip or helper text)
- [ ] **Selected** — multi-select, current tab, active filter all visually distinct

### 3. Form States
- [ ] **Validation** — inline errors on blur, not just on submit
- [ ] **Required fields** — clearly marked
- [ ] **Success feedback** — user knows their action worked (toast, inline, redirect)
- [ ] **Destructive confirmation** — delete/remove actions require confirmation
- [ ] **Autofill** — doesn't break layout when browser autofills

### 4. Responsive
- [ ] **Mobile (375px)** — usable, not just visible. Touch targets ≥48px with ≥8px spacing between them
- [ ] **Tablet (768px)** — layout adapts, not just shrinks
- [ ] **Desktop (1280px)** — the primary target, looks intentional
- [ ] **Wide (1800px+)** — content doesn't stretch absurdly. Max-width or centered

### 5. Accessibility
- [ ] **Keyboard nav** — can reach all interactive elements with Tab
- [ ] **Screen reader** — semantic HTML, aria-labels on icons, alt text on images
- [ ] **Color contrast** — 4.5:1 minimum for text (use WebAIM checker)
- [ ] **No color-only indicators** — don't rely solely on red/green for status

### 6. Edge Cases
- [ ] **First-time user** — onboarding or empty state guides them
- [ ] **Permission denied** — user sees why they can't access, not a broken page
- [ ] **Stale data** — timestamps or refresh indicators when data might be outdated
- [ ] **Concurrent edits** — what happens if two people edit the same thing?

## How to Use

Run this checklist AFTER the feature works but BEFORE design review. For each missing state, either:
1. **Implement it** (preferred)
2. **Document it as a known gap** and tell Aaron explicitly

Never silently skip a state. If it's intentionally deferred, say so.

## Quick Pass vs Full Pass

**Quick pass** (components, small features): States 1-2 only
**Full pass** (pages, flows, shipping features): All 6 sections

## The Test

Ask yourself: "What happens if the network is slow, the data is weird, the user is on a phone, or they're using a keyboard?" If you don't know, you haven't finished.

Related Skills

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

time-checker

3891
from openclaw/skills

Check accurate current time, date, and timezone information for any location worldwide using time.is. Use when the user asks "what time is it in X", "current time in Y", or needs to verify timezone offsets.

General Utilities

hna-666-flight-checker

3891
from openclaw/skills

查询海南航空 666Plus 权益可往返航班,自动遍历指定目的地

SKILL: stock-checker

3891
from openclaw/skills

## Description

double-check

3891
from openclaw/skills

在修改任何文件后(包括删除功能),自动进行两次独立验证(测试/编译/运行检查/文档或配置检查),确保无误才结束。本技能应默认应用于所有文件修改任务。 / After any file changes (including feature removal), automatically perform two independent verifications (tests/compilation/runtime checks/docs or config checks) to ensure correctness. This skill should be applied by default to any file modification task.

doctorbot-healthcheck-free

3891
from openclaw/skills

🩺 Free Security & Health Audit. Your OpenClaw deserves a check-up. This skill performs a non-invasive scan to detect security risks, outdated software, and misconfigurations.

truthcheck

3891
from openclaw/skills

Verify claims, fact-check content, check URL trustworthiness, and trace claims to their origin using the TruthCheck CLI. Use when: (1) user asks to fact-check or verify a claim, (2) user wants to check if a URL/source is trustworthy, (3) user wants to trace where a claim originated, (4) user asks about misinformation or content verification. Requires: pip install truthcheck

assignment-check

3891
from openclaw/skills

Check use's assignment folder and extracts and read uses assignment question files and tell user the deadline and how long approximately to finish them.

health-check

3891
from openclaw/skills

每日安全检查。检查 OpenClaw Gateway、磁盘空间、内存使用等系统健康状态。触发时机:cron 定时任务或手动调用。

checksum

3891
from openclaw/skills

A CLI utility for generating and verifying cryptographic file checksums (MD5, SHA1, SHA256). Supports recursive directory hashing and verification from file.

minimax-plan-checker

3891
from openclaw/skills

获取 MiniMax 平台的套餐信息,包括套餐名称、额度、当前使用情况。当用户询问 MiniMax 套餐、额度使用情况、API 调用量、计费信息时使用此技能。

openclaw-security-policy-check

3891
from openclaw/skills

OpenClaw 网关安全自动化审计与配置检查工具。自动检查 OpenClaw 配置文件中的常见安全风险,执行安全审计。适用于: