Communitygithub.com

广告到落地页审计师

分析广告与落地页之间的信息匹配度。检查广告文案中的承诺是否在落地页的标题、正文和行动号召中得以延续,并标记导致转化率下降的脱节之处。适用于 Google、Meta 和 LinkedIn 广告。

广告到落地页审计师 是什么?

这是一个专为 AI Agent(如 Claude Code、Cursor、Codex 等)设计的技能,用于自动化审计广告到落地页的转化漏斗。其核心价值在于解决广告点击率很高但转化率低下的常见问题——即落地页未能兑现广告承诺。该技能能够解析用户提供的广告文案和落地页 URL,提取广告列表,逐一抓取并分析落地页内容,从承诺延续性、语言匹配、行动号召对齐等六个维度(满分 60 分)对信息匹配度进行评分。除了信息匹配度评分,还会评估落地页的转化摩擦,如加载速度、表单长度、CTA 清晰度等。最终生成一份结构化的 Markdown 审计报告,包含执行摘要、逐对分析、优先级修复建议和重写建议,并保存为本地文件。该技能无需任何 API 密钥,仅需 `fetch_webpage` 或 `curl` 工具,完全免费。虽然当前版本支持 Google、Meta 和 LinkedIn 广告,但其方法框架通用,易于扩展。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/gooseworks-ai/goose-skills/tree/HEAD/skills/ads/composites/ad-to-landing-page-auditor

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

广告到落地页审计师 是做什么的?

广告获得点击但无法转化的首要原因:落地页未能兑现广告的承诺。此技能审计完整的点击路径——从广告文案到落地页体验——并标记每一处脱节之处。

核心原则: 一条优秀的广告搭配一个不匹配的落地页,比一条平庸的广告搭配一个匹配的落地页更糟糕。信息匹配度是大多数初创公司忽视的最大转化杠杆。

使用时机

  • "为什么我的广告有点击但没转化?"
  • "审计我的广告到落地页流程"
  • "检查我们的广告活动信息匹配度"
  • "我的转化率很低——帮我找出原因"
  • "审查我们的广告活动落地页"

阶段 0:信息收集

  1. 广告文案 — 每个广告需提供:
    • 标题
    • 正文/描述文本
    • 行动号召文本
    • 平台(Google 搜索 / Meta / LinkedIn)
  2. 落地页 URL — 每个广告指向的 URL
  3. 转化目标 — 用户点击后应该做什么?(演示 / 试用 / 购买 / 下载)
  4. 已知转化率? — 每个广告/落地页当前的点击到转化率(如有)

如果用户从其广告平台导出 CSV 文件,请解析该文件。

阶段 1:广告清单

将提供的广告解析为以下格式:

广告 ID平台标题正文/描述行动号召落地页 URL转化率(如有)

阶段 2:落地页审计

对于每个唯一的落地页 URL,获取页面内容:

fetch_webpage: [landing_page_url]

如果 fetch_webpage 不可用,使用 curl 获取页面 HTML。

提取并评分:

2A:内容元素

元素是否找到?内容
主标题[是/否]"[文本]"
副标题[是/否]"[文本]"
主要行动号召[是/否]"[按钮文本]"
行动号召在首屏之上[是/否]—
社会证明[是/否][Logo / 客户评价 / 数据指标]
利益列表[是/否][列出的关键利益点]
表单/注册[是/否][字段数:N]
视频[是/否]—
信任信号[是/否][安全徽章、担保]

2B:信息匹配度评分

对于每个广告 → 落地页对,从以下维度评分:

维度分数 (1-10)标准
承诺延续性[X]落地页标题是否兑现了广告的承诺?
语言匹配[X]落地页是否使用了与广告相同的词汇/短语?
视觉延续性[X]落地页是否感觉是广告的延续?(搜索广告无法评估)
行动号召对齐[X]落地页的要求是否与广告暗示的一致?
具体性匹配[X]如果广告很具体("面向销售团队"),落地页也同样具体吗?
情绪匹配[X]如果广告使用了恐惧/紧迫感,落地页是否延续了这种情绪?

信息匹配度得分:[平均分/60]

评分指南

分数评级含义
50-60优秀强匹配——落地页兑现了广告的每项承诺
40-49良好轻微脱节,但整体连贯
30-39需要改进明显缺口——访问者需要费力寻找相关性
20-29差广告和落地页感觉像不同的产品
低于 20严重完全不匹配——立即修复

阶段 3:转化摩擦分析

除信息匹配度外,评估落地页的转化摩擦:

摩擦类型检查项状态
加载时间页面感觉沉重/缓慢吗?(资源数量作为代理指标)[快/慢/未知]
表单长度转化前有多少个字段?[N 个字段] — [合适/太多]
行动号召清晰度是否有一个明确的行动号召,还是有多个竞争操作?[清晰/混乱]
首屏转化用户能否在不滚动的情况下完成转化?[是/否]
社会证明位置证明信息是否靠近行动号召?[是/否]
导航干扰落地页是否有完整的站点导航?(应尽量精简)[最少/完整导航]
移动端体验是否存在任何不适合移动端的元素?[良好/有问题]

阶段 4:输出格式

# 广告到落地页审计 — [产品/客户] — [日期]

审计的广告数:[N]
唯一落地页数:[N]
平台:[Google / Meta / LinkedIn]
总体信息匹配度:[分数/60] — [评级]

---

## 执行摘要

[3-4 句话:总体发现、最大脱节、首要建议、预估转化影响]

---

## 审计结果(按广告 → 落地页对)

### 广告 1: "[广告标题片段]"
**平台:** [Google 搜索 / Meta / LinkedIn]
**广告文案:**
> 标题:"[文本]"
> 正文:"[文本]"
> 行动号召:"[文本]"

**落地页:** [URL]
> 落地页标题:"[文本]"
> 落地页副标题:"[文本]"
> 落地页行动号召:"[按钮文本]"

**信息匹配度得分:[X/60] — [评级]**

| 维度 | 分数 | 问题 |
|------|------|------|
| 承诺延续性 | [X/10] | [具体发现] |
| 语言匹配 | [X/10] | [具体发现] |
| 行动号召对齐 | [X/10] | [具体发现] |
| 具体性匹配 | [X/10] | [具体发现] |
| 情绪匹配 | [X/10] | [具体发现] |

**发现的脱节:** [脱节的具体描述]
**建议修复:** [对广告或落地页的具体修改]

### 广告 2: ...

---

## 落地页摩擦报告

### [落地页 URL]
| 摩擦点 | 状态 | 影响 | 修复 |
|--------|------|------|------|
| [摩擦] | [红/黄/绿] | [高/中/低] | [具体修复] |

---

## 优先级修复

### 严重(本周内修复)
1. **[广告/落地页对]:** [具体不匹配] → [具体修复]
   - 预估转化影响:[X% 提升]

### 重要(本月内修复)
2. **[问题]:** [修复]

### 锦上添花
3. **[问题]:** [修复]

---

## 重写建议

### 针对 [匹配最差的广告或落地页]:

**当前广告标题:** "[当前]"
**建议广告标题:** "[与落地页匹配的改写]"

或

**当前落地页标题:** "[当前]"
**建议落地页标题:** "[与广告匹配的改写]"

保存到当前工作目录(或用户指定的路径)的 ad-lp-audit-[YYYY-MM-DD].md 文件中。

成本

组件成本
落地页抓取免费
分析免费(LLM 推理)
总计免费

所需工具

  • fetch_webpage 或 curl — 用于落地页分析
  • 无需 API 密钥

触发短语

  • "审计我的广告到落地页匹配"
  • "为什么我的转化率这么低?"
  • "检查我们广告活动的信息匹配度"
  • "我们的落地页与广告匹配吗?"
  • "对我们的广告漏斗执行 CRO 审计"

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

gooseworks-ai/goose-skills

Burned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a split-screen seam (plate 25% above / 75% below) or at a fixed height, in a plate, outline or one-word serif style, with an optional red hook card; plates.py burns per-beat caption blocks (black, one union silhouette, placed in the emptiest band) for formats with no voice. The last caption (the CTA) holds to the final frame. Use as the last step of any video ad.

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

gooseworks-ai/goose-skills

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the cinematic-music-video format.

gooseworks-ai/goose-skills

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

gooseworks-ai/goose-skills

Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.

gooseworks-ai/goose-skills

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

gooseworks-ai/goose-skills

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

gooseworks-ai/goose-skills

Find speakers, hosts, and guest profiles at conferences and events on Luma. Two modes - free direct scrape for hosts, or Apify-powered search for full guest profiles with LinkedIn/Twitter/bio.

gooseworks-ai/goose-skills

Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.

相关技能