More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ↔️ RTL UI Release Gate

    2

    Find direction, logical-CSS, interpolation, icon-mirroring, and render-evidence gaps before an RTL release.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ↔️ RTL UI Release Gate

    ↔️ RTL UI Release Gate

    Example session with this skill installed

    Supply surfaces with id, lang, dir, hardcodedDirectionalProperties, iconDecisions, interpolations, and screenshotEvidenceRef.

    • Read your context and instructions
    • Compiled the rtl ui release

    A deterministic PASS, REVIEW, BLOCK, or CANNOT_ASSESS result with stable finding codes, report, manifest, and SHA-256 receipts.

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

    About this skill

    RTL UI Release Gate turns owner-supplied normalized evidence into a deterministic local preflight. RTL interfaces fail through wrong direction declarations, physical CSS, unisolated dynamic text, and blindly mirrored semantic icons. Audits explicit structural observations and semantic icon decisions; it does not claim a static rule can replace rendered or native review. It makes no network request and performs no import, translation, rewrite, upload, merge, delivery, publication, purchase, message, or account change. Stable findings and SHA-256 receipts support review, while PASS remains explicitly narrower than source truth or authorization.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for UX & UI Design.

    • It does not render, crawl, or modify an interface.
    • Screenshot evidence and semantic icon decisions remain owner supplied.
    • PASS does not prove visual or linguistic correctness.

    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 buying a skill.

    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 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    one
    owner-selected
    local
    JSON
    input
    new
    output
    directory

    The standard-library helper makes no network request and performs no external action.

    Listed3 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    No. It reads one local packet, writes one new local output directory, and makes no network request.

    No. PASS only means no encoded rule fired in supplied normalized evidence.

    The gate returns CANNOT_ASSESS or BLOCK; missing evidence never becomes a pass.

    Yes. Findings are sorted and persisted outputs carry stable SHA-256 receipts.

    No. It never publishes, contacts anyone, or adopts a founder, candidate, artist, or reviewer voice.

    New in UX & UI Design