Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Landing Page Conversion Auditor

    1

    Evidence-based conversion and technical audit skill that diagnoses friction and generates implementation-ready tickets.

    Free

    4 usesSecurity scanned
    Landing Page Conversion Auditor

    Landing Page Conversion Auditor

    Example session with this skill installed

    Audit the provided HTML and screenshot for a B2B SaaS signup page. The goal is trial starts. Traffic comes from LinkedIn ads promising a '14-day free trial'.

    • Read your context and instructions
    • Compiled the landing page conversion

    Audit complete for B2B SaaS signup page. I have mapped the decision path and identified three P1 blockers related to message mismatch and form friction.

    Conversion Audit: SaaS Trial Funnel

    IDDimensionSeverityEvidence StatusFindingRecommended Change
    001Message MatchCRITICALOBSERVEDLinkedIn ad promises "14-day trial," but page hero text and CTA specify "Start Free Demo."Update hero H1 and CTA to "Start 14-Day Free Trial" to maintain intent.
    002Choice ArchitectureHIGHOBSERVEDThree different CTA styles (Outline, Solid Blue, Ghost) above the fold with equal visual weight.Standardize primary CTA to Solid Blue; move secondary "View Pricing" to ghost style.
    003Form FrictionMEDIUMINFERREDForm requires Phone Number field without a "Why" tooltip; high likelihood of drop-off.Make Phone Number optional or add micro-copy explaining it is for 2FA only.
    004AccessibilityMEDIUMOBSERVEDSubmit button background (#E0E0E0) and text (#FFFFFF) contrast ratio is 1.2:1 (fails WCAG).Update button CSS to #2563EB for 4.5:1+ contrast ratio.

    Experiment Backlog

    • Hypothesis: Clarifying the "Free" nature of the trial in the CTA will increase click-through.
    • Control: "Start Trial"
    • Variant: "Start My Free 14-Day Trial"
    • Metric: CTA Click-through Rate (Primary), Trial Activation Rate (Guardrail).

    Next steps

    1. Update the CSS color tokens for button contrast to meet AA standards.
    2. Synchronize the H1 headline with the LinkedIn campaign copy to reduce immediate bounce.
    3. Remove the mandatory phone field from the auth-form component to reduce friction.

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

    About this skill

    SEE LIVE DEMO OUTPUT: Click Here to See Live Output

    The problem

    Vague "best practice" audits often ignore real evidence, leading to wasted engineering effort on low-impact tweaks. Developers and growth teams struggle to separate qualitative guesses from observed user friction and technical blockers.

    What it does

    • Analyzes URLs, screenshots, and HTML/CSS to map the visitor decision path from entry to conversion.
    • Classifies every claim as OBSERVED, INFERRED, HYPOTHESIS, or CALCULATED to maintain rigorous evidence standards.
    • Identifies technical friction in CTAs, form hierarchy, mobile responsiveness, and accessibility barriers.
    • Generates structured implementation tickets with clear acceptance criteria and instrumentation requirements.
    • Builds an experiment backlog with defined control/variant mechanics and primary/guardrail metrics.

    Frameworks & tools

    Compatible with any web stack including React, Next.js, Webflow, and Shopify. Supports analysis of analytics exports (GA4/Mixpanel) and structured HTML/CSS evidence.

    Why this beats prompting it yourself

    Generic prompts result in shallow feedback like "make the button bigger." This skill enforces a strict evidence graph, preventing the AI from fabricating metrics or promising fake conversion lifts. It forces a distinction between visual observations and code-level technical verification.

    Use cases

    • Pre-launch technical and conversion audit for new landing pages or funnels.
    • Translating qualitative user session recordings into actionable Jira or Linear tickets.
    • Validating message match between ad copy and destination page architecture.
    • Auditing mobile-specific layout shifts and tap-target accessibility risks.

    Known limitations

    Cannot prove DOM semantics or screen-reader behavior from screenshots alone. Performance claims are limited to visible risk signals unless raw Core Web Vitals data is provided.

    Cannot verify screen-reader output or keyboard focus order from visual evidence alone. Requires raw data for precise performance metrics. Scope is limited to the provided evidence assets.

    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

    4 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill moves beyond generic advice by enforcing a strict evidence graph, classifying every insight as OBSERVED, INFERRED, or HYPOTHESIS to ensure recommendations are rooted in technical reality rather than guesswork.

    The skill accepts live URLs, static screenshots, and raw HTML/CSS snippets, allowing it to bridge the gap between visual design and underlying code-level technical friction.

    Yes, the skill is designed to output structured data compatible with project management tools like Jira, Linear, or Trello, complete with acceptance criteria and suggested instrumentation.

    While the skill identifies visible mobile layout shifts and tap-target risks, a full accessibility audit requires providing the raw HTML to accurately analyze DOM semantics beyond what a screenshot can reveal.

    The purchase includes the full skill configuration for your AI agent, a guide on optimizing data inputs for best results, and access to all future logic updates and framework compatibility patches.

    New in Research & Analysis