Is the UX Audit Walkthrough skill free?

Yes. The skill itself is free from AIPexStudio/AIPex. SkillProof publishes the install command and an independent test verdict at no cost.

What is the UX Audit Walkthrough SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.

How do I install UX Audit Walkthrough?

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 UX Audit Walkthrough 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.

UX Audit Walkthrough

Scores a UI flow against four minimalist principles and outputs a graded UX report

by AIPexStudio · AIPexStudio/AIPex

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 31c3e72

The scoring framework is the real value and it beats a freeform baseline: on a sample signup-modal audit it produced a base-80-minus-deductions health score with each finding tagged to a violated principle and an actual-versus-theoretical click count, where the baseline just gave loose prose. The catch is the SKILL.md mandates a PRIMARY workflow of capture_screenshot, computer, search_elements and a download_current_chat_report_zip export, which are AIPex browser-extension tools with no equivalent in a standard Claude Code install, so the advertised automated walkthrough and ZIP export don't function. Install is clean and the skill is a single self-contained SKILL.md with no bundled scripts.

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 7/10
Docs & honesty 3/5

What UX Audit Walkthrough does

A UX interaction-audit framework that walks a flow and grades it against four principles (fewer clicks, less UI, no hidden logic, don't make users think), producing a 100-point health score, principle-tagged findings and a click-efficiency metric. Triggers on requests to audit or evaluate the usability of a web interface or Figma prototype.

How to install UX Audit Walkthrough

git clone https://github.com/AIPexStudio/AIPex.git
mkdir -p ~/.claude/skills
cd AIPex && cp -r packages/browser-runtime/src/skill/built-in/ux-audit-walkthrough ~/.claude/skills/ux-audit-walkthrough

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

Commands — how to trigger UX Audit Walkthrough

/ux-audit-walkthrough Scores a UI flow against four minimalist principles and outputs a graded UX report

It also activates on plain-language prompts like these:

Audit this signup modal against usability principles and score it.
How many clicks does this checkout flow actually need versus ideal?
Grade this Figma prototype's UX and flag any hidden-logic problems.

Frequently asked questions

Is the UX Audit Walkthrough skill free?: Yes. The skill itself is free from AIPexStudio/AIPex. SkillProof publishes the install command and an independent test verdict at no cost.
Does UX Audit Walkthrough work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. The scoring framework is the real value and it beats a freeform baseline: on a sample signup-modal audit it produced a base-80-minus-deductions health score with each finding tagged to a violated principle and an actual-versus-theoretical click count, where the baseline just gave loose prose. The catch is the SKILL.md mandates a PRIMARY workflow of capture_screenshot, computer, search_elements and a download_current_chat_report_zip export, which are AIPex browser-extension tools with no equivalent in a standard Claude Code install, so the advertised automated walkthrough and ZIP export don't function. Install is clean and the skill is a single self-contained SKILL.md with no bundled scripts.
What is the UX Audit Walkthrough SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
How do I install UX Audit Walkthrough?: 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 UX Audit Walkthrough 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.