UX Audit — Senior Designer Review in Minutes

    2

    Severity-rated UX findings with real fixes, from a 3× APEX-winning designer's checklist.

    Free

    18 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    UX Audit — Senior Designer Review in Minutes

    Example session with this skill installed

    Audit this login screen for a mobile B2B app. Users are field technicians often working outdoors. (Assuming screenshot attached)

    • Read your context and instructions
    • Compiled the ux audit

    I have audited the login screen provided. Assumptions: The user is a field technician in high-glare environments (outdoors), likely using one hand, on a mid-range mobile device.

    UX Audit Report: Field Tech Login Screen

    Executive Summary

    The layout is clean, but the low-contrast secondary actions and small touch targets will fail users in outdoor environments. The biggest friction point is the lack of visible password toggle, which will lead to high error rates for users wearing gloves or in bright light. Prioritize increasing contrast and hit areas immediately.

    Findings

    IDLocationUser ExperienceSeverityHeuristicRecommended FixEffort
    UX-01Primary CTA (Login)32px height is too small for reliable one-handed thumb taps, especially if the user is moving.S1H7: Flexibility & EfficiencyIncrease button height to 48px; span full width of container.S
    UX-02Password FieldNo visual way to confirm character entry; outdoor glare makes masking dots invisible.S2H1: Visibility of System StatusAdd "Show" icon toggle inside the right edge of the field.S
    UX-03"Forgot Password" link#999999 grey on white background fails WCAG AA contrast (2.8:1). Text is unreadable in sunlight.S2H10: Help & DocumentationChange text color to #2563EB (5.8:1 contrast ratio).S
    UX-04Error State (Invalid)Red border appears but no text explanation; user won't know if it's a network issue or wrong creds.S2H9: Help users recognize errorsAdd helper text: "Incorrect password. Try again or reset it below."S

    Keep Doing

    • The input labels stay visible when typing (floating labels), which helps users with short-term memory.
    • The "Remember Me" checkbox is pre-selected, reducing friction for repeat daily use.

    Next steps

    1. Update the button component to the 48px height variant in the design system.
    2. Implement the password visibility toggle to reduce login failures.
    3. Run a quick "squint test" on the updated contrast colors to ensure readability at max screen brightness.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Vague design feedback like "improve the hierarchy" or "make it pop" doesn't help developers write code. Design debt accumulates because teams lack a systematic way to identify usability blockers and translate them into actionable tickets.

    What it does

    • Identifies specific UI elements that will confuse or slow down users across 10 distinct checkpoints.
    • Ranks every finding using a S1 (Blocker) to S4 (Enhancement) severity scale to prioritize sprint planning.
    • Maps violations to industry-standard Nielsen heuristics for objective, non-subjective justification.
    • Provides precise technical fixes, including exact spacing (px), typography changes, and microcopy rewrites.
    • Generates a structured developer-handoff report with estimated implementation effort (S/M/L).

    Why this beats prompting it yourself

    General LLMs often give subjective "tastemaker" advice or miss edge cases like error states and loading feedback. This skill enforces a 10-step sequence—from eye-tracking analysis to accessibility quick-passes—ensuring no critical path friction is overlooked. It replaces "vibe-based" reviews with a repeatable, expert-level audit framework.

    Use cases

    • Reviewing a new sign-up flow before the first line of code is written.
    • Auditing a high-churn checkout page to identify drop-off points.
    • Conducting a heuristic evaluation on a legacy enterprise dashboard.
    • Sanity-checking a mobile prototype for platform convention consistency.

    Known limitations

    Static analysis of screenshots cannot detect motion, focus order, or live server response times. For full WCAG compliance, use a dedicated accessibility audit skill.

    Static analysis of images cannot detect hover states, motion, or focus order. Use an accessibility skill for full WCAG compliance. Requires context on user roles to be effective.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    18 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Simply upload high-resolution screenshots or image exports of your designs (Figma, Sketch, or live site captures); the agent analyzes the visual layout, typography, and hierarchy based on these inputs.

    Unlike general AI which offers subjective opinions, this skill uses a specific 10-point checklist and a S1-S4 severity scale derived from award-winning design frameworks to ensure every fix is technical and actionable.

    You receive a structured developer-handoff report that includes heuristic violations, precise technical fixes (like pixel-perfect spacing), and estimated implementation effort (S/M/L) for each task.

    This skill is optimized for top-tier multimodal agents capable of image analysis, such as GPT-4o or Claude 3.5 Sonnet, ensuring the most accurate visual parsing of your UI.

    While it is excellent for identifying layout, contrast, and labeling issues, it cannot test motion, focus order, or screen readers; we recommend a specialized accessibility tool for full WCAG certification.

    Yes, once purchased, you will receive all future logic updates and checklist refinements to the skill at no additional cost as design trends and industry heuristics evolve.

    New in UX & UI Design

    Free