ux-audit SKILL.md skillA
ux-audit from qa-aman/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qa-aman/claude-skills/ux-audit@git:20260303.00c2750Pins git:20260303.00c2750 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qa-aman/claude-skills
- Path
skills/by-role/designer/ux-audit/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260303.00c2750, committed Mar 3, 2026
- Size
- 4,379 bytes
- Repository stars
- 21
- License
- MIT
Audit a user flow for friction and drop-off points. Use when the user says "UX audit", "audit this flow", "where are users dropping off", "why isn't this converting", "review the onboarding", "usability audit", "what's causing friction", "user journey review", or wants to identify why users struggle with a flow - even if they don't explicitly say "UX audit".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Overview Based on **"Don't Make Me Think"** by Steve Krug. Krug's core principle: every question a user has to ask themselves is a source of friction. Good UX eliminates questions. Users don't read - they scan. They don't make optimal choices - they satisfice (pick the first option that seems good enough). Design for scanning, not reading. Design for satisficing, not deliberation. Krug's usability testing insight: you don't need 20 users. 5 users reveal ~85% of usability problems (Nielsen's law). The fastest audit tool is watching one real user try to use the product. ## Workflow ### Step 1: Define the flow and success criteria State the flow you're auditing and what success looks like: - Flow: [start state] to [end state] (e.g., landing page to first value moment) - Success: [specific action that means the user succeeded] - Current conversion/completion rate: [if known] ### Step 2: Map every step in the flow List every screen and decision point a user encounters. Include: - What the user sees - What the user must do (read, decide, input, wait) - What the user must remember from a previous step Steps requiring memory or prior knowledge are friction points. …
Read the whole file at its exact version.
How to install
mdr add qa-aman/claude-skills/ux-audit@sha256:932be5ea285a5817The line at the top of this page pins the label git:20260303.00c2750, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pi64vaqcb7frq2tu)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Mar 3, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4379 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
qa-aman/claude-skills · 21 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pi64vaqcb7frq2tu GET https://markdownregistry.com/api/v1/resolve?ref=qa-aman/claude-skills/ux-audit GET https://markdownregistry.com/api/v1/blob/932be5ea285a58177933a9595826ba635988c1d07badc117afcfd3ffb4148e14
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from qa-aman/claude-skills
Every file in qa-aman/claude-skills