Token导航 LogoToken导航

Agent Skill · 研究检索

ads-audit(广告审核)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

ads-audit 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 64,698。

总安装 294周安装 12GitHub Stars 公开资料未说明下载 95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:ads-audit(广告审核)
来源仓库:https://github.com/ideola-ai/marketing-ads-skills
仓库路径:skills/ads-audit
安装命令:
npx skills add https://github.com/ideola-ai/marketing-ads-skills --skill ads-audit
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/ideola-ai/marketing-ads-skills --skill ads-audit

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。

用于辅助安全审计、权限检查和凭据风险排查。适合梳理敏感配置或分析鉴权逻辑。使用时不能把工具输出直接当最终结论。

安装命令:npx skills add https://github.com/ideola-ai/marketing-ads-skills --skill ads-audit 涉及用户数据时应先确认最小权限和脱敏方式。

来源仓库内路径:skills/ads-audit

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/ideola-ai/marketing-ads-skills --skill ads-aud…;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

ads-audit 怎么安装?

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

ads-audit 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。

ads-audit 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。

ads-audit 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。

ads-audit 用的人多吗?

公开数据是累计安装 294 次,近一周安装 12 次,下载 95 次。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。

ads-audit 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。

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。

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
ads-audit

广告审核 · 本页

294—需要联网未明确通过

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

Ads Audit System

Purpose: Audit and optimize existing ad campaigns across all major platforms.

This skill focuses exclusively on performance analysis and optimization recommendations - not campaign planning or strategy (use /marketing-campaign for that).

Marketing OS Workflow Position

brand-voice → content-brief → content-planning → content-creation
                                          ↓
                                        marketing-campaign
                                          ↓
                                          ads-audit

This skill is LAST - Audit and optimize existing campaigns after they've been planned and launched.

Input from:

  • /marketing-campaign - Campaign structure, KPIs, and benchmarks to compare against
  • /content-creation - Creative quality reference for ad audit

Output for:

  • Optimization recommendations (loop back to campaign planning or content creation)

Command Reference

CommandDescription
/ads auditFull multi-platform audit with parallel subagent delegation
/ads googleGoogle Ads deep analysis (Search, PMax, Display, YouTube, Demand Gen)
/ads metaMeta Ads deep analysis (FB, IG, Advantage+ Shopping)
/ads youtubeYouTube Ads specific analysis (Skippable, Shorts, Demand Gen)
/ads linkedinLinkedIn Ads deep analysis (B2B, Lead Gen, TLA)
/ads tiktokTikTok Ads deep analysis (Creative, Shop, Smart+)
/ads microsoftMicrosoft/Bing Ads deep analysis (Copilot, Import validation)
/ads creativeCross-platform creative quality audit and fatigue detection
/ads landingLanding page quality assessment for ad campaigns
/ads budgetBudget allocation and bidding strategy review

Universal Audit Workflow

All commands follow this core structure. See rules/workflow.md for detailed step-by-step procedure.

1. Data Collection

  • Campaign structure and objectives
  • Key metrics (spend, impressions, CTR, CPC, CPA, ROAS)
  • Targeting parameters
  • Creative inventory
  • Time period analyzed

2. Performance Analysis

Compare against platform benchmarks (see references/benchmarks.md):

  • CTR vs. channel average
  • CPA vs. target
  • ROAS vs. goal
  • Frequency vs. fatigue threshold

3. Issue Identification

Systematic diagnosis across:

  • Creative (fatigue, format, quality)
  • Targeting (audience, exclusions, overlap)
  • Budget/Bidding (strategy, caps, pacing)
  • Technical (tracking, landing pages)

For detailed diagnosis process: See rules/diagnosis.md

4. Recommendations

Prioritized action plan with:

For priority framework: See rules/priority.md

5. Output Format

# [Platform] Ads Audit Report

## Executive Summary
- Overall Score: X/10
- Key Finding: [Top insight]
- Quick Impact: [Estimated improvement potential]

## Performance vs Benchmarks
| Metric | Actual | Benchmark | Gap |
|--------|--------|-----------|-----|
| CTR | X% | X% | X% |

## Issues Found (Priority Order)
### 🔴 Critical
1. [Issue] - Impact: High - Action: [Immediate step]

### 🟡 Moderate
1. [Issue] - Impact: Medium - Action: [Plan fix]

## Action Items
- [ ] [Action 1] - This week
- [ ] [Action 2] - This week
- [ ] [Test idea] - Next sprint

Platform-Specific Commands

/ads google

Analyze: Search, Performance Max, Display, YouTube, Demand Gen

Key Metrics:

  • Quality Score (search)
  • Impression Share
  • Search Terms (negative opportunities)
  • Asset performance (PMax)
  • View rate (YouTube)

Google-Specific Resources: references/google.md

/ads meta

Analyze: Facebook, Instagram, Messenger, Advantage+ Shopping

Key Metrics:

  • Relevance Score / Quality Ranking
  • Delivery Category
  • Frequency
  • CTR per placement
  • Pixel vs CAPI comparison

Meta-Specific Resources: references/meta.md

/ads youtube

Analyze: Skippable in-stream, Non-skippable, Bumpers, Shorts, Discovery

Key Metrics:

  • View rate (25%, 50%, 75%, 100%)
  • CPV efficiency
  • Audio/creative variations
  • Audience retention graphs

YouTube-Specific Resources: references/youtube.md

/ads linkedin

Analyze: Sponsored content, Message ads, Lead gen forms, Text ads

Key Metrics:

  • Engagement rate
  • Cost per send (message ads)
  • Lead form completion rate
  • Job title/industry performance

LinkedIn-Specific Resources: references/linkedin.md

/ads tiktok

Analyze: In-feed ads, Spark ads, TopView, Brand takeover

Key Metrics:

  • Video completion rate
  • 2s/6s VTR
  • TikTok pixel events
  • Creative diversity score

TikTok-Specific Resources: references/tiktok.md

/ads microsoft

Analyze: Search ads, Audience ads, Shopping, Import from Google

Key Metrics:

  • Quality Score
  • Import match rate
  • Audience expansion performance
  • Copilot bid suggestions

Microsoft-Specific Resources: references/microsoft.md

/ads creative

Cross-platform creative audit covering:

  • Visual quality and format compliance
  • Copy effectiveness (hook, CTA, clarity)
  • Ad fatigue indicators
  • A/B test coverage
  • Creative diversity score

Creative Framework: references/creative.md

/ads landing

Landing page audit covering:

  • Load time and Core Web Vitals
  • Mobile optimization
  • CTA clarity and placement
  • Form optimization
  • Trust signals and social proof
  • Technical SEO basics

Landing Page Framework: references/landing.md

/ads budget

Budget and bidding audit covering:

  • Budget allocation efficiency
  • Bid strategy appropriateness
  • Learning phase completion
  • Dayparting opportunities
  • Seasonal pacing
  • Cross-channel budget balance

Budget Framework: references/budget.md

Resources


Integration with Marketing OS Workflow

Input from:

  • /marketing-campaign - Campaign structure, KPIs, and benchmarks to compare against
  • /content-creation - Creative quality reference for ad audit

Output for:

  • Optimization recommendations (loop back to campaign planning or content creation)
  • Performance insights that inform future briefs

When to Use:

  • After campaigns have been running for 1-2 weeks
  • When performance is below expectations
  • As part of ongoing optimization (weekly/bi-weekly)
  • Before scaling budget

Note: This skill can be used independently - you don't need to go through the full workflow to audit ads. Just provide campaign data and metrics.

平台分布

Codex

37.67%
按下载量换算36

Claude

28.78%
按下载量换算27

Cursor

19.74%
按下载量换算19

Gemini CLI

8.99%
按下载量换算9

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。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