Token导航 LogoToken导航

Agent Skill · 研究检索

ad-creative-intelligence(广告创意智力)

ad-creative-intelligence 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ad-creative-intelligence 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 66,724。

总安装 259周安装 11GitHub Stars 607下载 91核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ad-creative-intelligence(广告创意智力)
来源仓库:https://github.com/athina-ai/goose-skills
仓库路径:skills/ad-creative-intelligence
安装命令:
npx skills add https://github.com/athina-ai/goose-skills --skill ad-creative-intelligence
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/athina-ai/goose-skills --skill ad-creative-intelligence

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

广告创意智力通过爬取竞争对手的广告并分析创意模式,寻找新的广告方向和识别市场中的成功案例。适用于需要了解竞争对手广告策略、寻找新创意角度或审计广告领域的场景。提供核心原则和具体使用步骤,帮助团队基于证据制定创意策略。

安装命令:npx skills add https://github.com/athina-ai/goose-skills --skill ad-creative-intelligence。使用前需确认权限范围、维护状态及是否触发联网或文件读写操作。

来源仓库内路径:skills/ad-creative-intelligence

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/athina-ai/goose-skills --skill ad-creative-int…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ad-creative-intelligence 怎么安装?

在终端执行 npx skills add https://github.com/athina-ai/goose-skills --skill ad-creative-intelligence。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ad-creative-intelligence 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ad-creative-intelligence 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

ad-creative-intelligence 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ad-creative-intelligence 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 607 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ad-creative-intelligence 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ad-creative-intelligence

广告创意智力 · 本页

259607接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Ad Creative Intelligence

Scrape competitor ads from Meta and Google, then analyze creative patterns — hooks, formats, angles, CTAs — to find directions you haven't tried and identify what's resonating in the market.

Core principle: The best ad creative teams don't guess. They start with evidence from what's already working, then differentiate.

When to Use

  • "What ads are my competitors running?"
  • "Find new creative angles for our paid campaigns"
  • "What hooks are working in [our space]?"
  • "I want to audit the ad landscape before we launch"
  • "What format — video, image, carousel — is dominant in our category?"

Phase 0: Intake

  1. Competitor names and website domains (e.g., apollo.io, clay.run)
  2. Your own domain (to optionally include for self-audit comparison)
  3. Channels to cover: Meta only, Google only, or both? (default: both)
  4. Time range: active ads only (default) or historical?
  5. What's your product category? (helps with analysis framing)

Phase 1: Scrape Meta Ads

Run meta-ad-scraper for each competitor:

python3 skills/meta-ad-scraper/scripts/scrape_meta_ads.py \
  --domain <competitor_domain> \
  --output json

Collect per ad:

  • Ad copy (headline + body text)
  • Visual description / media type (image, video, carousel)
  • CTA button text
  • Landing page URL
  • Estimated run time (active duration proxy)
  • Platforms (Facebook, Instagram, etc.)

Phase 2: Scrape Google Ads

Run google-ad-scraper for each competitor:

python3 skills/google-ad-scraper/scripts/scrape_google_ads.py \
  --domain <competitor_domain> \
  --output json

Collect per ad:

  • Headline variants (up to 3)
  • Description lines
  • Ad type (search, display, YouTube)
  • Landing page URL

Phase 3: Cluster & Analyze

After collecting all ads, perform structured analysis:

Hook Pattern Clustering

Group all ad headlines/openers by hook type:

Hook TypePatternExample
Fear/LossRisk of missing out or falling behind"Your competitors are already using AI SDRs"
OutcomeDirect result promise"10x your pipeline in 30 days"
QuestionChallenges current assumption"Still doing outbound manually?"
Social proofNames customers or numbers"Join 500+ B2B teams using [product]"
ContrarianChallenges conventional wisdom"Cold email isn't dead. Your copy is."
EmpathyValidates their pain"We know SDR ramp time is brutal"
Product-ledFeature as hook"[Feature] is live — see what's new"

Count how many ads per competitor use each hook type. This reveals their primary messaging strategy.

Format Distribution

FormatMetaGoogle
Static image[N]N/A
Video[N][N]
Carousel[N]N/A
Search textN/A[N]
Display bannerN/A[N]

CTA Taxonomy

List all unique CTAs found. Common patterns:

  • Urgency: "Start free", "Try now", "Get started today"
  • Low-friction: "See how it works", "Watch demo", "Learn more"
  • Outcome: "Book a demo", "Get your free audit", "Calculate your ROI"

Landing Page Analysis

For top-traffic ads (those running longest), note:

  • What angle does the landing page reinforce?
  • Is the LP general or campaign-specific?
  • What's the primary conversion goal?

Phase 4: Gap Analysis & Recommendations

Identify:

  1. Angles nobody is running — Hook types absent from competitor ads = white space
  2. Overcrowded angles — If everyone leads with "save time", avoid it or be more specific
  3. Format opportunities — If no one is running video in your space, it may stand out
  4. Underutilized proof — Are competitors avoiding specific proof points you could own?
  5. CTA patterns to test — What CTAs do the longest-running ads use?

Phase 5: Output Format

# Ad Creative Intelligence Report — [DATE]

## Coverage
- Competitors analyzed: [list]
- Meta ads collected: [N]
- Google ads collected: [N]

---

## Meta Ad Analysis

### Hook Distribution
| Hook Type | [Comp1] | [Comp2] | [Comp3] |
|-----------|---------|---------|---------|
| Fear/Loss | 40% | 10% | 0% |
| Outcome | 30% | 50% | 60% |
...

### Top Performing Ads (Longest Running)
**[Competitor] — [Ad Title/Hook]**
> [Ad copy excerpt]
- Format: [type]
- CTA: [text]
- Running since: [date]
- Why it likely works: [analysis]

---

## Google Ad Analysis

### Headline Patterns
[Top headline structures with examples]

### Most Common CTAs
[ranked list]

---

## Creative Gap Analysis

### Angles Nobody Is Running
1. [Angle] — Why it could work for you: [reasoning]
2. [Angle] — ...

### Overcrowded Angles (Avoid or Differentiate)
- [Angle] — [N] of [N] competitors use this

### Format White Space
- [Format] is not being used by competitors on [platform]

---

## Recommended Creative Experiments

### Experiment 1: [Name]
- Platform: [Meta/Google]
- Format: [type]
- Hook angle: [type]
- Proposed headline: "[headline]"
- Proposed body: "[copy]"
- Why test this: [rationale]

### Experiment 2: ...

Save to clients/<client-name>/intelligence/ad-creative-intel-[YYYY-MM-DD].md.

Cost

ComponentCost
Meta ad scraper (per competitor)~$0.20-0.50 (Apify)
Google ad scraper (per competitor)~$0.20-0.50 (Apify)
Total for 3 competitors~$1-3

Tools Required

  • Apify API token — APIFY_API_TOKEN env var
  • Upstream skills: meta-ad-scraper, google-ad-scraper

Trigger Phrases

  • "What ads are [competitor] running?"
  • "Audit the ad landscape for [product category]"
  • "Run ad creative intel for [client]"
  • "Find new paid ad angles we haven't tried"

平台分布

Codex

35.17%
按下载量换算32

Claude

33.35%
按下载量换算30

Cursor

18.65%
按下载量换算17

Gemini CLI

10.71%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills