Token导航 LogoToken导航

Agent Skill · 研究检索

marketing-paid-advertising(营销付费广告)

marketing-paid-advertising 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。

marketing-paid-advertising 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,权限为需要联网;许可证为 MIT,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 33,144。

总安装 2,399周安装 102GitHub Stars 60下载 840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
MIT

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:marketing-paid-advertising(营销付费广告)
来源仓库:https://github.com/vasilyu1983/ai-agents-public
仓库路径:skills/marketing-paid-advertising
安装命令:
npx skills add https://github.com/vasilyu1983/ai-agents-public --skill marketing-paid-advertising
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/vasilyu1983/ai-agents-public --skill marketing-paid-advertising

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。

用于查找、检索和筛选付费广告投放相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。通过关键词或任务场景进行信息检索与筛选。marketing-paid-advertising 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

安装前需确认权限范围和维护状态,避免触发联网或文件读写。建议结合原始 README 核验具体用法和功能边界。

来源仓库内路径:skills/marketing-paid-advertising

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/vasilyu1983/ai-agents-public --skill marketing…;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

    它需要需要联网,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

marketing-paid-advertising 怎么安装?

在终端执行 npx skills add https://github.com/vasilyu1983/ai-agents-public --skill marketing-paid-adve…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

marketing-paid-advertising 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。

marketing-paid-advertising 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

marketing-paid-advertising 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

marketing-paid-advertising 用的人多吗?

公开数据是累计安装 2,399 次,近一周安装 102 次,下载 840 次,GitHub 60 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。

marketing-paid-advertising 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
marketing-paid-advertising

营销付费广告 · 本页

2,39960需要联网MIT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 ADVERTISING — ACQUISITION OS (OPERATIONAL)

No-fluff execution skill for paid acquisition across Google, Meta, TikTok, LinkedIn.

References: Google Ads, Meta Business, TikTok Ads, LinkedIn Campaign Manager


Modern Best Practices (January 2026)

  • Algorithmic buying wins when you provide strong signals: clean conversion events, value, and enough volume per campaign to learn.
  • Creative is the main lever on social: plan for volume and refresh cadence; treat creative like a product pipeline.
  • Default measurement: server-side signals where possible (Enhanced Conversions / Conversions API / Events API), consistent UTMs, and closed-loop revenue in CRM.
  • Use attribution as directional; use incrementality tests to answer budget questions (geo-lift/holdouts) when stakes are high.
  • Optimize to profit and payback (not just CPL/ROAS) when margins, refunds, or LTV vary materially.
  • Compliance is non-negotiable: platform policies, privacy consent, and avoiding sensitive targeting/claims.

When to Use

  • New campaigns: structure, audiences, bidding, creative
  • Scaling spend: budget allocation, ROAS targets
  • Platform selection: which channels for which goals
  • Unit economics: CAC/LTV modeling, payback period
  • Revenue attribution: multi-touch, incrementality

When NOT to Use

ScenarioUse Instead
Organic socialmarketing-social-media
SEO/contentmarketing-seo-complete
Landing pagesmarketing-cro

Quick Start (What I Need From You)

  • Goal: revenue, pipeline, leads, trials, purchases (pick 1 primary)
  • ICP/offer: who, pain, positioning, price/ACV, gross margin, refund rate (if relevant)
  • Geo/language + budget horizon (test budget + monthly cap)
  • Tracking: conversion events + where they’re recorded (GA4, CRM, Shopify, app DB), attribution window expectations
  • Constraints: creative/brand limits, compliance constraints, sales capacity + SLAs (B2B)

If unknown, start with assumptions and label them; then validate with data in week 1.


Platform Selection

PlatformBest ForTypical Cost (Relative)
Google SearchHigh intent captureMedium
MetaEfficient demand creation + retargetingLow–Medium
LinkedInB2B precision, ABMHigh
TikTokLow-cost reach + creative velocityLow

*Note: Costs vary massively by industry, geo, offer, tracking quality, and seasonality. Use as directional only.*

Decision Tree

HIGH INTENT?
├─ YES → Google Search (always include)
└─ NO → What's your goal?
    ├─ Awareness → Meta, TikTok, YouTube
    ├─ B2B/Enterprise → LinkedIn, Google
    └─ E-commerce → Meta, Google Shopping

Measurement & Tracking (2026 Default)

Minimum viable measurement before scaling:

  • Conversion events defined (lead, SQL, purchase, subscription) with dedupe and clear “source of truth”
  • UTMs standardized across every platform
  • Server-side signals where feasible:

- Google: Enhanced Conversions + offline conversion imports (B2B) - Meta: Pixel + Conversions API - TikTok: Pixel + Events API - LinkedIn: Insight Tag + offline conversions (when available)

  • Reporting views: spend → conversions → revenue/pipeline (weekly), incrementality tests (quarterly or when budgets materially change)

For deep dives: references/revenue-attribution-guide.md, references/sales-alignment-guide.md.


Campaign Structure

Google Ads

├─ Campaign: Brand (Search)
├─ Campaign: Non-Brand (Search)
├─ Campaign: Retargeting (Display)
└─ Campaign: Performance Max

Meta Ads

├─ Campaign: Prospecting
│   ├─ Ad Set: Lookalike 1%
│   └─ Ad Set: Broad (Advantage+)
├─ Campaign: Retargeting
└─ Campaign: Testing

Bidding Strategy

StrategyWhen to Use
Manual CPC<50 conversions/month
Target CPA50-100 conversions
Target ROAS>100 conversions

Budget Allocation

Stage% of Budget
Brand10-20%
Prospecting40-60%
Retargeting20-30%
Testing10-15%

Unit Economics

LTV:CACStatusAction
< 1:1Losing moneyStop spending
3:1HealthyMaintain/scale
> 5:1Under-investingScale aggressively

Payback Targets:

  • B2C SaaS: < 6 months
  • B2B SaaS: < 12 months
  • E-commerce: < 3 months

Decision Tree (Triage)

CPL too high?
├─ Check audience size
├─ Check creative CTR (<1% = new creative)
├─ Check landing page CVR (<2% = landing issue)
└─ Check bid strategy

ROAS below target?
├─ Check conversion tracking
├─ Check audience quality
└─ Check offer strength

Metrics

MetricTarget
CTR>1% (creative health)
CVR>2% (landing health)
Frequency<3 (fatigue)
Quality Score>6 (Google)

Anti-Patterns

  • Changing bids daily → Wait 2-4 weeks
  • Too many audiences → Use 3-5 max
  • Single creative → Use 3-5 variants
  • No negative keywords → Build weekly

Resources

ResourcePurpose
data/sources.jsonAuthoritative sources (platform docs, measurement, privacy)
references/google-ads-guide.mdGoogle specifics
references/meta-ads-guide.mdMeta specifics
references/tiktok-ads-guide.mdTikTok specifics
references/linkedin-ads-guide.mdLinkedIn specifics
references/unit-economics-guide.mdCAC/LTV deep dive
references/revenue-attribution-guide.mdAttribution models
references/sales-alignment-guide.mdPipeline + CRM alignment
references/operational-sops.mdWeekly/monthly SOPs
references/programmatic-display.mdProgrammatic buying, DSPs, DOOH
references/remarketing-retargeting.mdRetargeting strategy + windows
references/youtube-ads-guide.mdYouTube + Shorts specifics
references/creative-testing-ads.mdCreative testing methodology
references/privacy-cookieless-ads.mdPrivacy-first advertising
references/amazon-ads-guide.mdAmazon Sponsored Products/Brands/Display, DSP
references/microsoft-ads-guide.mdBing/Microsoft Ads, LinkedIn targeting, Copilot

Templates

TemplatePurpose
assets/campaign-structure.mdCampaign hierarchy
assets/budget-allocation.mdBudget planning
assets/unit-economics-calculator.mdCAC/LTV calculator
assets/creative-brief.mdAd creative spec
assets/google-rsa-asset-pack.mdRSA copy + asset pack
assets/creative-test-plan.mdCreative testing cadence
assets/performance-review.mdWeekly/monthly review doc

International Markets

This skill covers US-centric platforms. For regional advertising:

NeedSee Skill
China platforms (Baidu, WeChat, Douyin)marketing-geo-localization
Japan/Korea (Yahoo Japan, Naver, Kakao)marketing-geo-localization
Russia/CIS (Yandex, VK)marketing-geo-localization
Regional CAC benchmarksmarketing-geo-localization

Tip: If your query mentions regional platforms or specific countries, also use marketing-geo-localization.


Related Skills

SkillPurpose
marketing-geo-localizationInternational markets
marketing-leads-generationLead capture
marketing-croLanding optimization
startup-go-to-marketChannel strategy

平台分布

Claude Code

27.02%
按下载量换算227

Gemini CLI

24.71%
按下载量换算208

Codex

19.03%
按下载量换算160

Cursor

13.11%
按下载量换算110

Antigravity

8.1%
按下载量换算68

OpenCode

3.42%
按下载量换算29

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

继续浏览同类 Skills