More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Reviews-to-Offer Page

    1

    Turn supplied reviews and verified offer facts into an evidence-grounded offer page without cherry-picking.

    $14

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Reviews-to-Offer Page

    Reviews-to-Offer Page

    Example session with this skill installed

    Use these eight supplied reviews and the verified facts for my physical focus mat to create one offer page for remote workers. Show explicit mention counts and denominator, include objections and contradictory evidence, map every claim to both review evidence and an offer fact, and use one CTA.

    • Read your context and instructions
    • Compiled the reviews-to-offer page

    Complete demonstration

    This is the same-case worked artifact shipped with the Skill. It preserves the evidence boundaries and does not claim publication or commercial results.

    <!doctype html>
    <html lang="en">
    <head>
      <meta charset="utf-8">
      <meta name="viewport" content="width=device-width, initial-scale=1">
      <title>DeskBloom — Demonstration Offer Page</title>
      <style>
        :root{--ink:#17251f;--mint:#dcecdf;--lime:#d8ef5a;--paper:#fbfcf7;--line:#cad7cd}
        *{box-sizing:border-box}body{margin:0;background:var(--paper);color:var(--ink);font-family:Arial,sans-serif;line-height:1.55}
        main{max-width:1040px;margin:auto;padding:30px}.label{display:inline-block;background:var(--ink);color:white;padding:7px 11px;font-size:12px}
        header{padding:64px 0 44px}h1{font-size:clamp(44px,7vw,82px);line-height:.98;margin:20px 0;max-width:920px}.lead{font-size:20px;max-width:740px}.cta{display:inline-block;background:var(--ink);color:white;padding:14px 18px;text-decoration:none;margin-top:18px}
        section{padding:44px 0;border-top:1px solid var(--line)}h2{font-size:30px}.grid{display:grid;grid-template-columns:repeat(3,1fr);gap:16px}.card{padding:22px;background:var(--mint);border:1px solid var(--line)}
        .count{font-size:34px;font-weight:800}.evidence{font-size:12px;font-weight:bold}.matrix{overflow:auto;background:var(--ink);color:white;padding:20px;font-family:monospace;white-space:pre}.limit{border-left:4px solid #d36c52;padding-left:18px}
        @media(max-width:720px){.grid{grid-template-columns:1fr}main{padding:18px}}
      </style>
    </head>
    <body>
    <main>
      <header>
        <span class="label">Demonstration Output — fictional data, not supplied by the user</span>
        <h1>Give every task a visible place to land.</h1>
        <p class="lead">DeskBloom is a fictional washable focus mat with printed zones for today, later, and done—built for a visible desk reset, not a productivity guarantee.</p>
        <a class="cta" href="#fit">See if the physical workflow fits you</a>
      </header>
    
      <section>
        <h2>What the supplied fictional reviews emphasized</h2>
        <div class="grid">
          <article class="card"><div class="count">5/8</div><h3>Visual organization</h3><p>Five fictional reviews explicitly valued seeing task categories without opening an app.</p><div class="evidence">R01,R02,R04,R05,R08 + O01</div></article>
          <article class="card"><div class="count">2/8</div><h3>First-day setup friction</h3><p>Two reviewers wanted clearer examples for deciding what belongs in each zone.</p><div class="evidence">R03,R07</div></article>
          <article class="card"><div class="count">1/8</div><h3>Texture mismatch</h3><p>One reviewer disliked the surface feel. This remains a fit limitation, not a defect verdict.</p><div class="evidence">R06</div></article>
        </div>
      </section>
    
      <section>
        <h2>The offer, grounded in product facts</h2>
        <div class="grid">
          <div class="card"><h3>No app required</h3><p>The workflow stays on the desk. No claim is made about distraction reduction.</p><div class="evidence">O01</div></div>
          <div class="card"><h3>Three printed zones</h3><p>Today, later, and done provide a repeatable visual reset structure.</p><div class="evidence">O02</div></div>
          <div class="card"><h3>Washable surface</h3><p>Care guidance is part of the fictional offer facts; durability beyond that is not established.</p><div class="evidence">O03</div></div>
        </div>
      </section>
    
      <section>
        <h2>Evidence matrix</h2>
        <div class="matrix">THEME                 SOURCES                 OFFER FACT   CONFLICT     PAGE USE
    Visual organization    R01,R02,R04,R05,R08    O01,O02      none         hero + benefit
    Setup uncertainty      R03,R07                O02          none         onboarding FAQ
    Surface preference     R06                    O03          isolated     fit boundary
    
    CLAIM C01 -> SUPPORTED BY R01,R02,R04,R05,R08 + O01,O02
    CLAIM C02 -> QUALIFIED BY R03,R07
    CLAIM C03 -> BLOCKED: no review authenticity evidence</div>
      </section>
    
      <section id="fit">
        <h2>Fit and non-fit</h2>
        <div class="grid">
          <div class="card"><h3>Likely fit</h3><p>You prefer a physical, visible desk ritual and already know the small set of tasks you want to sort.</p></div>
          <div class="card"><h3>May not fit</h3><p>You need reminders, team collaboration, analytics, or a texture-neutral digital system.</p></div>
          <div class="card"><h3>Start clearly</h3><p>Use one task per zone on day one. The fictional setup guide would show three worked examples.</p></div>
        </div>
      </section>
    
      <section>
        <h2>Evidence boundary</h2>
        <p class="limit">This demonstration uses eight fictional reviews. It does not establish review authenticity, market frequency, customer satisfaction, product quality, productivity impact, or conversion performance.</p>
        <pre>CORPUS SIGNAL LEDGER v1.1
    Corpus: 8 fictional reviews
    Majority signal: 5/8 visual organization — R01,R02,R04,R05,R08 + O01,O02
    Minority friction: 2/8 setup uncertainty — R03,R07 + O02
    Isolated objection: 1/8 texture preference — R06 + O03
    Conflict status: VISIBLE — no universal buyer claim</pre>
        <strong>VERDICT: DEMONSTRATION — OFFER PAGE READY FOR SELLER REVIEW</strong>
      </section>
    </main>
    </body>
    </html>
    
    

    Next step: review the evidence ledger and release blockers before using the asset externally.

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

    About this skill

    The problem

    Review-mining prompts often cherry-pick praise and turn one comment into a universal buyer truth. The resulting copy cannot show where its claims came from.

    What this skill delivers

    Reviews-to-Offer Page transforms a supplied review corpus and verified offer facts into a theme and objection matrix plus a self-contained HTML offer page. It records source IDs, mention counts, denominator, claim-to-offer dependencies, contradictory themes, missing evidence, fit boundaries, and one CTA.

    Why it is different

    • Every sales claim depends on review evidence and a verified offer fact.
    • Minority and contradictory signals qualify the copy.
    • Denominators prevent single comments becoming universal claims.
    • An executable Corpus-Signal Gate checks the result.

    Included

    Source Skill, worked HTML demonstration, executable validator, and a six-page English buyer guide inside the ZIP.

    Boundaries

    No scraping, authentication claim, fabricated testimonial, popularity claim, performance guarantee, customer reply, or publication.

    Does not authenticate, collect, or scrape reviews; reply to customers; fabricate testimonials or popularity; guarantee conversion or product performance; or publish the page.

    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 2 months ago

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    Unlike typical AI tools that cherry-pick praise, this skill uses a rigorous matrix to map every claim to specific review IDs and offer facts, ensuring minority opinions and contradictory signals are included for a balanced, high-trust page.

    This skill delivers a source skill file, a fully-coded HTML demonstration, an executable validator to check output integrity, and a comprehensive six-page buyer guide.

    The skill requires two primary inputs: a corpus of raw customer reviews (with unique IDs) and a set of verified facts about your product or service.

    No, this skill is designed for evidence-grounded synthesis; it does not include web scraping, authentication of reviews, or the fabrication of testimonials.

    The skill generates a self-contained HTML offer page that features a single clear Call to Action (CTA), structured around a theme-and-objection matrix derived from your data.