Communitygithub.com

Biznomad/agent-skills

落地頁面審核技能可對點擊後體驗進行全面評估,結合技術效能分析與轉換率優化(CRO)評估。

agent-skills 是什麼?

此技能旨在對落地頁面進行深度審核,涵蓋技術效能、內容相關性及轉換率優化(CRO)三大支柱。它會測量 Core Web Vitals(LCP、INP/INP、CLS),分析頁面速度、資源阻塞與行動裝置可用性,並估算對 Google Ads 品質分數的影響。同時,它還評估廣告文案與落地頁面內容的訊息匹配度,檢查行動呼籲(CTA)清晰度、表單設計、信任信號(如評論、認證)以及視覺層次,最終給出優先排序的改善建議。此技能支援 Claude Code、Cursor、Codex 和 Gemini 等平台,適合在使用者要求落地頁面審核、CRO 分析或改善品質分數時自動觸發。其輸出包含總體分數、分項評估、具體建議與預估的轉換率提升效果。

相容平台✓Claude Code✓Codex CLI✓Cursor✓Gemini CLI
npx skills add https://github.com/Biznomad/agent-skills/tree/HEAD/landing-page-audit

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

落地頁面審核

屬於 Agent Skills™ 系列,由 googleadsagent.ai™ 提供

說明

落地頁面審核技能可對點擊後體驗進行全面評估,結合技術效能分析與轉換率優化(CRO)評估。落地頁面品質直接影響 Google Ads 品質分數、轉換率,並最終決定每一元廣告支出的獲利能力。此技能審核落地頁面效能的三大支柱:速度、相關性與說服力。

技術效能分析以 Core Web Vitals 為核心——最大內容繪製(LCP)、首次輸入延遲(FID)/ 與下一次互動的繪製(INP)及累計版面配置位移(CLS)。Google 將這些指標作為落地頁面體驗評分的直接信號。此技能會測量跨裝置的真實世界效能,識別阻塞渲染的資源,分析關鍵渲染路徑,並產出可行的速度最佳化建議,附帶預估的品質分數影響。

相關性與 CRO 層級則評估廣告文案與落地頁面內容之間的訊息匹配度,判斷行動呼籲(CTA)的清晰度與突出程度,分析表單設計與摩擦點,檢查行動裝置回應性,評估信任信號(評論、認證、安全指示),並根據業界最佳實務對轉換元素進行基準測試。輸出結果為一份計分評估,附帶依預估轉換率影響排序的優先改善建議。

使用時機

  • 使用者要求「落地頁面審核」或「頁面檢討」
  • 使用者提及「落地頁面體驗」品質分數元件
  • 使用者想「改善轉換率」或進行「CRO 分析」
  • 使用者詢問「頁面速度」或「Core Web Vitals」
  • 使用者提及特定頁面「轉換率低」
  • 使用者想「改善品質分數」的落地頁面元件
  • 使用者詢問「行動落地頁面」效能
  • 使用者提及廣告與落地頁面間的「訊息匹配」
  • 使用者尋求「表單最佳化」或「CTA 最佳化」建議

架構

flowchart TD
    A[落地頁面 URL] --> B[平行分析管線]

    B --> C[技術效能]
    B --> D[內容與相關性]
    B --> E[CRO 評估]

    C --> C1[Core Web Vitals\nLCP, INP, CLS]
    C --> C2[頁面速度\nTTFB, FCP, SI]
    C --> C3[資源分析\n阻塞渲染、圖片]
    C --> C4[行動效能\n視埠、觸控目標]

    D --> D1[訊息匹配評分\n廣告文案 vs 頁面內容]
    D --> D2[關鍵字相關性\n目標關鍵字在內容中]
    D --> D3[內容品質\n可讀性、深度]
    D --> D4[SEO 一致性\nMeta 標籤、標頭]

    E --> E1[CTA 分析\n可見性、清晰度、急迫性]
    E --> E2[表單審核\n欄位數量、摩擦]
    E --> E3[信任信號\n評論、徽章、社交證明]
    E --> E4[視覺層次\n折頁上方內容、版面]

    C1 --> F[評分引擎]
    C2 --> F
    C3 --> F
    C4 --> F
    D1 --> F
    D2 --> F
    D3 --> F
    D4 --> F
    E1 --> F
    E2 --> F
    E3 --> F
    E4 --> F

    F --> G[總體落地頁面分數]
    G --> H[優先排序建議]
    G --> I[預估 QS 影響]
    G --> J[預估 CVR 提升]

實作

Core Web Vitals 與技術效能分析:

async function auditLandingPage(url, config) {
  const { adCopyText, targetKeywords, device = 'both' } = config;

  const [technical, content, cro] = await Promise.all([
    runTechnicalAudit(url, device),
    runContentAudit(url, adCopyText, targetKeywords),
    runCROAudit(url, device)
  ]);

  const overallScore = calculateOverallScore(technical, content, cro);

  return {
    url,
    overallScore,
    technical,
    content,
    cro,
    recommendations: prioritizeRecommendations(technical, content, cro),
    estimatedQSImpact: estimateQualityScoreImpact(overallScore),
    estimatedCVRImprovement: estimateCVRImprovement(cro)
  };
}

async function runTechnicalAudit(url, device) {
  const mobileMetrics = device !== 'desktop' ? await measurePerformance(url, 'mobile') : null;
  const desktopMetrics = device !== 'mobile' ? await measurePerformance(url, 'desktop') : null;

  const metrics = mobileMetrics || desktopMetrics;

  return {
    coreWebVitals: {
      lcp: { value: metrics.lcp, rating: rateLCP(metrics.lcp) },
      inp: { value: metrics.inp, rating: rateINP(metrics.inp) },
      cls: { value: metrics.cls, rating: rateCLS(metrics.cls) }
    },
    additionalMetrics: {
      ttfb: metrics.ttfb,
      fcp: metrics.fcp,
      speedIndex: metrics.speedIndex,
      totalBlockingTime: metrics.tbt
    },
    resourceAnalysis: {
      renderBlockingResources: metrics.renderBlocking,
      unoptimizedImages: metrics.unoptimizedImages,
      unusedCSS: metrics.unusedCSS,
      unusedJS: metrics.unusedJS,
      totalPageWeight: metrics.totalBytes
    },
    mobileUsability: {
      viewportConfigured: metrics.hasViewport,
      textReadable: metrics.fontSizeAdequate,
      touchTargetsSized: metrics.touchTargetsAdequate,
      contentFitsViewport: metrics.noHorizontalScroll
    }
  };
}

function rateLCP(ms) {
  if (ms <= 2500) return { score: 'good', color: 'green' };
  if (ms <= 4000) return { score: 'needs_improvement', color: 'orange' };
  return { score: 'poor', color: 'red' };
}

function rateINP(ms) {
  if (ms <= 200) return { score: 'good', color: 'green' };
  if (ms <= 500) return { score: 'needs_improvement', color: 'orange' };
  return { score: 'poor', color: 'red' };
}

function rateCLS(value) {
  if (value <= 0.1) return { score: 'good', color: 'green' };
  if (value <= 0.25) return { score: 'needs_improvement', color: 'orange' };
  return { score: 'poor', color: 'red' };
}

訊息匹配與 CRO 評估:

function scoreMessageMatch(adCopy, pageContent) {
  const adHeadlines = adCopy.headlines.map(h => h.toLowerCase());
  const adDescriptions = adCopy.descriptions.map(d => d.toLowerCase());
  const pageText = pageContent.toLowerCase();

  let matchScore = 0;

  const headlineMatches = adHeadlines.filter(h =>
    pageText.includes(h) || fuzzyMatch(h, pageText) > 0.8
  );
  matchScore += (headlineMatches.length / adHeadlines.length) * 40;

  const keyPhrases = extractKeyPhrases([...adHeadlines, ...adDescriptions]);
  const phraseMatches = keyPhrases.filter(p => pageText.includes(p));
  matchScore += (phraseMatches.length / keyPhrases.length) * 30;

  const aboveFoldContent = pageContent.aboveFold?.toLowerCase() || '';
  const aboveFoldRelevance = keyPhrases.filter(p => aboveFoldContent.includes(p));
  matchScore += (aboveFoldRelevance.length / keyPhrases.length) * 30;

  return {
    score: Math.round(matchScore),
    headlinePresence: headlineMatches,
    missingPhrases: keyPhrases.filter(p => !pageText.includes(p)),
    aboveFoldRelevance: aboveFoldRelevance.length / keyPhrases.length
  };
}

function auditCTA(pageData) {
  return {
    ctaPresent: pageData.ctaElements.length > 0,
    ctaAboveFold: pageData.ctaElements.some(cta => cta.yPosition < pageData.viewportHeight),
    ctaContrast: pageData.ctaElements.map(cta => ({
      text: cta.text,
      contrastRatio: calculateContrast(cta.color, cta.backgroundColor),
      meetsWCAG: calculateContrast(cta.color, cta.backgroundColor) >= 4.5
    })),
    ctaClarity: evaluateCTAText(pageData.ctaElements),
    ctaCount: pageData.ctaElements.length,
    recommendation: pageData.ctaElements.length === 0
      ? '在折頁上方新增一個清晰、醒目的 CTA'
      : pageData.ctaElements.length > 3
        ? '減少 CTA 選項以避免選擇癱瘓'
        : 'CTA 數量適當'
  };
}

function auditForm(formData) {
  return {
    fieldCount: formData.fields.length,
    frictionScore: calculateFormFriction(formData),
    recommendations: [
      formData.fields.length > 5 && '將表單欄位減少至 3-5 個以提升完成率',
      !formData.hasProgressIndicator && formData.steps > 1 && '為多步驟表單新增進度指示器',
      !formData.hasInlineValidation && '新增行內驗證以減少提交錯誤',
      formData.requiredFields > formData.fields.length * 0.8 && '將較少欄位標記為必填以減少摩擦'
    ].filter(Boolean)
  };
}

與 Buddy™ Agent 整合

落地頁面審核技能在 Buddy™ Agent 中作為點擊後品質保證層運作。當 Google Ads 審核在高支出關鍵字上偵測到「低於平均」的落地頁面體驗分數時,Buddy™ 會自動觸發相關 URL 的落地頁面審核,並預先載入相關的廣告文案與關鍵字以進行訊息匹配分析。

Buddy™ 維護一個落地頁面效能資料庫,追蹤每個接收廣告流量的 URL 的 Core Web Vitals 與轉換率。它會偵測效能衰退(如網站更新後速度下降、CLS 增加),並在使用者感受到品質分數影響前發出警報。該平台也會在廣告文案變更時監控訊息匹配,確保落地頁面內容與更新的訊息保持一致。

對於管理多個客戶的代理商,Buddy™ 會跨帳戶彙總落地頁面洞察,識別可大規模解決的系統性問題(如常見 CMS 效能問題、共享範本弱點)。

最佳實務

  1. 將 LCP 目標設為行動裝置低於 2.5 秒,這是影響最大的單一速度指標
  2. 確保主要 CTA 在行動與桌機的折頁上方皆可見
  3. 在落地頁面上直接使用成效最佳廣告標題的原文
  4. 將表單欄位限制在最低必要數量——每增加一個欄位,轉換率約降低 4-7%
  5. 至少包含三種信任信號:客戶評論、安全徽章、產業認證
  6. 在真實行動裝置上測試頁面,而非僅使用回應式桌機預覽
  7. 將圖片壓縮為 WebP 格式,並對折頁下方內容實作延遲載入
  8. 每個頁面區塊使用單一、清晰的 CTA,以避免決策癱瘓
  9. 每季審核落地頁面,並在每次重大網站更新後進行審核
  10. 以足夠流量(每種變體至少 500 次工作階段)進行落地頁面變體的 A/B 測試

平台相容性

平台支援
Claude Code✅
Cursor✅
Codex✅
Gemini✅

相關技能

  • 品質分數最佳化 - 落地頁面體驗是品質分數三大子元件之一
  • 廣告文案生成 - 廣告文案與落地頁面內容的訊息匹配影響相關性與轉換
  • 轉換追蹤 - 落地頁面 CRO 改善直接影響轉換率與追蹤準確性
  • 長期工作流程 - 多頁面網站審核受益於分階段、具有檢查點的工作流程執行

關鍵字

落地頁面審核, core web vitals, 頁面速度, 轉換率最佳化, CRO, 訊息匹配, CTA 最佳化, 表單最佳化, 行動落地頁面, 落地頁面體驗, 品質分數落地頁面, LCP, INP, CLS, 頁面效能


© 2026 googleadsagent.ai™ | Agent Skills™ | MIT 授權

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

Biznomad/agent-skills

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and conversion rate potential. Use when user says "landing page", "post-click experience", "landing page audit", "conversion rate", or "landing page optimization".

Biznomad/agent-skills

TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", or "TikTok campaign".

Biznomad/agent-skills

YouTube Ads specific analysis covering campaign types, creative quality, audience targeting, and measurement. Evaluates video ad performance across skippable, non-skippable, bumper, Shorts, and Demand Gen formats. Use when user says "YouTube Ads", "video ads", "pre-roll", "bumper ads", "YouTube campaign", or "Shorts ads".

Biznomad/agent-skills

Help users get promoted at work. Use when someone is preparing for a promotion conversation, building their case for advancement, trying to understand what's blocking their promotion, or figuring out how to get to the next level in their career.

Biznomad/agent-skills

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.

Biznomad/agent-skills

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

Biznomad/agent-skills

Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

Biznomad/agent-skills

HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.

Biznomad/agent-skills

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.

Biznomad/agent-skills

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, and registry discovery.

Biznomad/agent-skills

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

Biznomad/agent-skills

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

Biznomad/agent-skills

Write high-converting landing page copy using proven frameworks like PAS (Problem-Agitate-Solution), AIDA, and StoryBrand. Creates headlines, value propositions, CTAs, and full page sections optimized for conversion. Use when users need landing page copy, sales page content, or marketing website text.

Biznomad/agent-skills

Optimize landing pages for higher conversion rates using proven frameworks and design patterns. Use when designing, reviewing, or improving landing pages, hero sections, pricing pages, CTAs, or when the user asks about conversion optimization.

Biznomad/agent-skills

Read-only queue dashboard for workspace-aware ship. (gstack)

Biznomad/agent-skills

Building promotion cases, brag documents, tracking wins, and self-advocacy for career advancement. Use when preparing for promotions, documenting accomplishments, or building your case for advancement.

Biznomad/agent-skills

Best practices for Remotion - Video creation in React

Biznomad/agent-skills

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

Biznomad/agent-skills

Produce programmable videos with Remotion using scene planning, asset orchestration, and validation gates for automated, brand-consistent video content.

Biznomad/agent-skills

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

相關技能