AI Loading UX

A pattern library for AI thinking/progress/streaming indicators, with a real decision framework, not just a mood board.

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · edc0db1

Ran a real baseline-vs-skill design pass for a 3-step research-agent loading state: the skill-guided version correctly classified the task via its own decision framework (Progress Steps, not Reasoning Display), picked the Vertical List layout its reference file names for 3-7 steps, and added an aria-live/role=progressbar accessibility spec and failure-recovery edge case the freeform baseline never considered.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 5/5

What AI Loading UX does

A design reference for AI waiting-state UX: reasoning/chain-of-thought displays, multi-step progress indicators, token-streaming states, and background status indicators, each with anatomy diagrams, state machines, accessibility notes, and named anti-patterns. Triggers when explicitly asked to design or improve AI loading, thinking, or progress UX; not for generic (non-AI) loading spinners.

How to install AI Loading UX

git clone https://github.com/rohunvora/cool-claude-skills
cd cool-claude-skills
mkdir -p ~/.claude/skills
cp -r skills/ai-loading-ux ~/.claude/skills/ai-loading-ux

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger AI Loading UX

  • /ai-loading-ux A pattern library for AI thinking/progress/streaming indicators, with a real decision framework, not just a mood board.

It also activates on plain-language prompts like these:

  • Design the loading state for my 3-step AI research agent
  • What's the best way to show token streaming progress in my chat UI?
  • Pick an accessible progress indicator pattern for my AI pipeline

Frequently asked questions

Is the AI Loading UX skill free?
Yes. The skill itself is free from rohunvora/cool-claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does AI Loading UX work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran a real baseline-vs-skill design pass for a 3-step research-agent loading state: the skill-guided version correctly classified the task via its own decision framework (Progress Steps, not Reasoning Display), picked the Vertical List layout its reference file names for 3-7 steps, and added an aria-live/role=progressbar accessibility spec and failure-recovery edge case the freeform baseline never considered.
What is the AI Loading UX SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install AI Loading UX?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use AI Loading UX with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.