Token导航 LogoToken导航

Agent Skill · 研究检索

google-ads(Google Ads 搜索)

google-ads 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。

google-ads 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,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 7,951。

总安装 17,582周安装 740GitHub Stars 409下载 6,157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:google-ads(Google Ads 搜索)
来源仓库:https://github.com/kostja94/marketing-skills
仓库路径:skills/google-ads
安装命令:
npx skills add https://github.com/kostja94/marketing-skills --skill google-ads
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/kostja94/marketing-skills --skill google-ads

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。

google-ads 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。适用于 Google Ads 策略、广告文案优化和投放效果分析等营销研究场景。

通过 npx skills add 命令从 GitHub 仓库安装,需确认权限范围和维护状态。使用前建议核对是否会触发联网、命令执行或文件读写操作。google-ads 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/google-ads

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/kostja94/marketing-skills --skill google-ads;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

google-ads 怎么安装?

在终端执行 npx skills add https://github.com/kostja94/marketing-skills --skill google-ads。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

google-ads 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。

google-ads 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

google-ads 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。

google-ads 用的人多吗?

公开数据是累计安装 17,582 次,近一周安装 740 次,下载 6,157 次,GitHub 409 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。

google-ads 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 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
google-ads

Google Ads 搜索 · 本页

17,582409只读未明确通过

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

Paid Ads: Google Ads

Guides Google Ads setup, campaign structure, keyword targeting, and optimization. Google Ads excels at high-intent search traffic; use when people actively search for your solution.

When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Two Modes: PMF Testing vs Conversion-Driven

ModeWhenBudgetLanding pageMetrics
PMF testingPre-PMF; validate idea before building$47–500; start smallSimple LP: headline, benefits, problem solved, CTA ("Join Waitlist," "Get Early Access")CTR, sign-up rate, bounce rate; low CTR/high bounce = messaging/positioning issue
Conversion-drivenPMF validated; commercializationScale; ROAS targetFull funnel; ad-to-page alignmentROAS, CAC, conversion rate

PMF testing: No full product needed. Build landing page with Unbounce, Carrd, or Webflow. Run ads to relevant search terms; measure clicks, engagement, signups. Test messaging (e.g., "Fastest App for Freelancers" vs "Simplest Time Tracker for Teams"), pricing (different price points in ads/LP), and audiences (keyword targeting, in-market). Allow 4–6 weeks for PMax learning phase. Use as learning tool, not just marketing channel.

Reference: Marketing Cactus – Using Google Ads to Test Product-Market Fit

Campaign Structure

Account
├── Campaign: Brand (Search)
├── Campaign: Non-Brand (Search)
├── Campaign: Competitor (Search) — optional; bid on competitor brand + "alternative"/"vs"
├── Campaign: Retargeting (Display)
└── Campaign: Performance Max

Competitor Brand Keywords

When: Bid on "[Competitor] alternative," "[Competitor] vs [You]" to intercept high-intent traffic. Google allows competitor terms as keywords; you cannot use competitor names in ad copy without permission.

Landing page: Use a dedicated landing page (comparison/alternatives page), not a blog article. Users searching competitor brands expect direct alternatives—a blog increases bounce; a comparison page matches intent and converts better. See alternatives-page-generator for structure.

Best practices:

  • Separate campaign; exact/phrase match; add your brand as negative
  • H1 mirrors search intent (e.g., "[Competitor] vs [You]")
  • Feature comparison table; one-line differentiator; strong CTA
  • Expect lower Quality Score, higher CPC than non-brand; optimize LP relevance

Naming: GOOG_[Objective]_[Audience]_[Offer]_[Date] (e.g., GOOG_Search_Brand_Demo_Ongoing)

Campaign Types

TypeBest for
SearchHigh-intent queries; keyword-targeted; landing page critical
DisplayAwareness; retargeting; broader reach
YouTubeVideo; awareness; consideration
Performance MaxAutomated; cross-channel; feed + search + display

Performance Max (PMax) Optimization

Learning period: Run at least 6 weeks for algorithm ramp-up. Works best as complement to Search, not replacement.

Asset groups: Organize by *audience intent* (e.g., high-intent searchers, cart abandoners, category researchers), not product category alone. Audience signals improve CPA and ROAS vs. no signals.

Asset requirements (per asset group):

  • ≥5 images (include 1200×1200)
  • ≥5 text assets (4 headlines, 5 descriptions)
  • Video when possible
  • Refresh creative regularly to maintain performance

Signals: Add remarketing lists and Customer Match to accelerate learning.

Weekly health check: Flag if brand terms >30% of conversions; unexpected geo conversions; any placement >15% of total spend; asset group performance below "Good."

Keyword Strategy

  • Brand: Protect brand terms; exclude from non-brand campaigns
  • Negative keywords: Build weekly; avoid irrelevant queries. Add support terms (login, forum, pricing, help) from keyword-research—these are existing customers, not prospects.
  • Match types: Broad (discovery) → Phrase → Exact (control)

Keyword sources: Use keyword-research for keyword list, clusters, and intent. Map each cluster to a dedicated landing page; relevance improves Quality Score and lowers CPC.

Quality Score Levers

FactorAction
Expected CTRImprove ad relevance; test headlines
Ad relevanceAlign ad copy to keyword intent
Landing pageAd-to-page alignment; fast load; mobile-friendly

Target: Quality Score ≥6; higher = lower CPC, better ad rank. Benchmark: Improving Quality Score from 5 to 7 can reduce CPC by 30–50%.

Bidding Strategy

Conversions/monthStrategy
<30Manual CPC (smart bidding needs volume to optimize)
30–50Target CPA; minimum for effective smart bidding
50–100Target CPA
100+Target ROAS

Smart bidding: AI-powered bidding (Target CPA, Target ROAS) typically delivers better ROI than manual when conversion volume is sufficient; requires ≥30 conversions in 30 days to work effectively.

Tracking

  • Enhanced Conversions: Server-side signals for better attribution
  • Offline conversion imports: B2B; CRM → Google Ads
  • UTM: Consistent parameters for GA4 cross-check

Paid–Organic Cannibalization

When you rank organically (position 4+) for a keyword and also run PPC, paid ads can absorb clicks that would go to organic. Audit: Cross-reference GSC organic rankings with Search Terms report. If organic ranks well, test pausing PPC on those terms to free budget for higher-impact keywords.

Reference: Backlinko – SEO and PPC: 8 Smart Ways to Align

Pre-Launch Checklist

  • Conversion tracking tested with real conversion
  • Landing page loads <3s; mobile-friendly
  • UTM parameters working
  • Negative keyword list built (include support terms from keyword-research)
  • Budget set; targeting matches audience

Related Skills

  • pmf-strategy: PMF validation framework; when to use PMF testing vs conversion-driven
  • paid-ads-strategy: Channel selection; budget allocation; ad-to-page alignment; competitor brand bidding
  • alternatives-page-generator: Competitor brand keyword ads → dedicated LP (not blog); comparison page structure
  • keyword-research: Keyword list, clusters, intent; support terms for negative keywords; PPC data feeds back SEO priority
  • traffic-analysis: UTM for attribution; paid–organic cannibalization audit
  • landing-page-generator: LP structure for paid traffic; PAA → FAQ
  • analytics-tracking: Conversion tracking; ROAS measurement

平台分布

Codex

32.4%
按下载量换算1,995

Claude

31.05%
按下载量换算1,912

Cursor

18.86%
按下载量换算1,161

Gemini CLI

9.41%
按下载量换算579

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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