More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Turn Your AI Agent into a Senior UI Reviewer

    1

    Most UI problems that cost you sign-ups are measurable: grey text at 2.3:1 contrast, a 23 px button nobody can tap, an email field with no label.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Turn Your AI Agent into a Senior UI Reviewer

    Turn Your AI Agent into a Senior UI Reviewer

    Example session with this skill installed

    Our landing page is sample/bad.html. Before I send it to the developer, check it against the UI rules and tell me what to fix. It has no dark theme and no dashboard.

    • Read your context and instructions
    • Compiled the turn your ai
    • Generated the app files

    Example output (real run on sample/bad.html)

    The script output is saved in sample/bad-audit-output.txt; this report is built from it plus a look at sample/bad-phone.png.

    UI audit: sample/bad.html (8 Nov 2026)

    Verdict: FIX FIRST Score: 52/100 over 27 rules (11 PASS, 6 WARN, 10 FAIL)
    Out of the score: 4 N/A, 4 NOT CHECKED. Groups judged: typography, spacing, colour, interface states, mobile. Dark mode, dashboards and process rules were left out on purpose (no dark theme, no dashboard, one page).
    Score working: (11 + 0.5 x 6) / 27 = 14 / 27 = 51.9, rounded to 52.

    GroupPASSWARNFAILN/ANot checked
    Typography (8)33200
    Spacing (6)32001
    Colour and contrast (8)20321
    Interface states (7)10222
    Mobile (6)21300
    Total (35)1161044

    Findings (FAIL first)

    IDRuleViewportMeasuredElementFix
    CC1Text contrast 4.5:1both2.32:1p.lead (#aaa on white)Use #222 (15.91:1)
    CC1Text contrast 4.5:1both3.32:1both inline links (#2a9d8f on white)Use #1d6f64 (5.98:1)
    CC2Button text contrastboth3.32:1form>button, white on #2a9d8fButton fill #1d6f64, white text (5.98:1)
    CC5Links marked beyond colourbothno underlinelinks "story", "origins"text-decoration: underline
    TY1Running text 16 px on phonephone14 px and 12 pxp.lead, span.tag16 px for both
    TY5Uppercase for 4 words or fewerboth12 words in capitalsspan.tagSentence case, shorter: "Free shipping on orders over 30 pounds"
    ST1Visible label on every inputbothplaceholder "Email" onlyform>inputAdd <label for="em">Email address</label>, give the input id="em"
    ST2Button names its outcomeboth"OK"form>button"Start my subscription"
    MO1Touch target 44 px, never under 24both / phonebutton 35 x 23; input 212 x 27form>button, form>inputmin-height: 48px; button min-width: 120px
    MO2Form text 16 pxboth13 pxform>inputfont-size: 16px
    MO3Right keyboardbothtype="text" on an email fieldform>inputtype="email" autocomplete="email"
    TY2Line height 1.4 to 1.6both1.10p.lead (body rule)line-height: 1.5 on body
    TY345 to 75 characters per linephone116 per linep.leadShorter text and max-width: 36rem; the real fix is cutting the paragraph
    TY7Tighten large headingsboth40 px, spacing normalh1letter-spacing: -0.02em
    SP1One spacing scaleboth14 (6 uses), 6 (4), 13 (4), 10 (3)page-wideMove to 8, 16, 24
    SP2Group gap 1.5 x the gap inside a groupeyepromo line touches the form; blocks 10 to 14 px apartspan.tag, form16 to 24 px between blocks, 8 inside the form
    MO5Main a

    bad.html

    ZIP · project files

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    About this skill

    "Looks fine to me" is not a test. Most UI problems that cost you sign-ups are measurable: grey text at 2.3:1 contrast, a 23 px button nobody can tap, an email field with no label. This skill turns your agent into a reviewer that measures them instead of giving opinions.

    It checks any landing page, app screen or dashboard against 50 concrete rules in 8 groups: typography, spacing, colour and contrast, interface states, mobile, dark mode, dashboards and process.

    The proof

    A real run on a sample coffee-subscription landing page (the files ship inside the skill, so you can check them):

    • Before: 52/100, 10 FAIL and 6 WARN: text contrast 2.32:1, a 35 x 23 px button, a placeholder instead of a label, 13 px form text, a button that just says "OK".
    • After the fixes: 0 FAIL, 0 WARN at desktop and phone width, re-checked by the same script.

    What you get

    • SKILL.md for Claude Code and OpenAI Codex
    • RULES.md: 50 rules, each with a number or a yes/no test, thresholds and sources
    • ui_audit.py: a Playwright script that measures the page at desktop and phone width
    • A report format: PASS / WARN / FAIL per rule, the element, the measured value and the exact fix
    • Sample pages: a faulty page, its fixed version, the real audit outputs and phone screenshots
    • Testing notes and a changelog

    How to use

    1. Install once: pip install playwright then playwright install chromium (about two minutes).
    2. Ask your agent: "Audit this page against the UI rules", with a URL or a local HTML file.
    3. Read the scored report, let your agent apply the fixes, then ask it to re-check.

    Known limitations

    • A screening tool, not an accessibility certificate.
    • Some rules need a human eye (visual hierarchy, image quality). The report marks them as eye checks and never guesses.
    • Web pages only: it does not inspect native iOS or Android apps.
    • The script needs Python 3.9+ and Playwright.

    FAQ

    My agent can already review UI. Why this? It can give opinions. This gives measurements: the contrast ratio, the tap-target size in pixels, the exact element, so fixes are right first time and can be re-checked.

    Does it work on dashboards and dark mode? Yes. Six rules cover dashboards (units, scales, chart clarity) and six cover dark mode.

    Will it change my code? Only if you ask your agent to apply the fixes. The audit itself only reads the page.

    Mac or Linux? Yes. Tested on Windows 11; Playwright runs the same on macOS and Linux.

    Requires Python 3.9+ and Playwright installation. Cannot measure elements behind logins without manual HTML export. Text over images or gradients results in unmeasured contrast.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    Requires

    Python
    Playwright
    Chromium
    pip
    Windows

    Permissions

    Terminal / Shell
    Browser
    Read Files
    Write Files
    Network Access
    Listed7 days ago

    What's inside

    Frequently Asked Questions

    The kit includes a specialized Python auditing script, a Playwright-based measurement environment, and a comprehensive 50-rule technical framework (RULES.md) that covers typography, spacing, and accessibility standards.

    Unlike standard prompts that might guess at dimensions, this skill uses Playwright and Chromium to programmatically measure CSS values, contrast ratios, and touch targets to ensure mathematical accuracy.

    The skill is compatible with any AI agent capable of executing Python 3.9+ code and running Playwright. It is optimized for local environments or cloud containers that allow headless browser execution.

    Yes, while it excels at live URLs, you can also audit local HTML files or static exports. This is particularly useful for checking pages that sit behind complex login walls or are still in early development.

    The audit focuses on objective technical rules; it cannot evaluate subjective "brand feel" or measure contrast for text placed over complex images or gradients.

    The kit generates a prioritized "Fix List" that includes specific CSS selectors and the exact values required to bring the interface into compliance with the 50-rule framework.

    New in Frontend & Web Apps