ads 审计
- 作者仓库星标 5,641
- 作者仓库 claude-ads
Full Multi-Platform Ads Audit
This audit operates under the 10-Principle Thinking Framework (see
ads/references/thinking-framework.md). OBSERVE (External + Internal)
dominates data collection, THINK + CONNECT (Lateral) dominate analysis,
CONNECT (System) + ACCEPT dominate synthesis and prioritization. If the
audit feels mechanical, you are skipping a principle.
Process
- Collect account data: request exports, screenshots, or API access
- Validate: confirm at least one platform's data is available before proceeding
- Detect business type: analyze account signals per ads orchestrator
- Identify active platforms: determine which platforms are in use
- Delegate to subagents (if available, otherwise run inline sequentially):
audit-google: Conversion tracking, wasted spend, structure, keywords, ads, settings (80 checks; G01-G61 + 19 hyphenated v1.5+ IDs incl. AI Max)audit-meta: Pixel/CAPI health, creative fatigue, structure, audience (50 checks; M01-M40 + 10 hyphenated v1.5+ IDs incl. Andromeda)audit-creative: LinkedIn, TikTok, Microsoft creative checks + cross-platform synthesisaudit-tracking: LinkedIn, TikTok, Microsoft tracking + cross-platform tracking healthaudit-budget: LinkedIn, TikTok, Microsoft budget/bidding + cross-platform allocationaudit-compliance: All-platform compliance, settings, performance benchmarks
- Validate: verify each subagent returned valid scores with required fields before aggregating
- Score: calculate per-platform and aggregate Ads Health Score (0-100)
- Report: generate prioritized action plan with Quick Wins
Data Collection
Ask the user for available data. Accept any combination:
- Google Ads: account export, Change History, Search Terms Report
- Meta Ads: Ads Manager export, Events Manager screenshot, EMQ scores
- LinkedIn Ads: Campaign Manager export, Insight Tag status
- TikTok Ads: Ads Manager export, Pixel/Events API status
- Microsoft Ads: account export, UET tag status, import validation results
If no exports available, audit from screenshots or manual data entry.
Scoring
Read ads/references/scoring-system.md for full algorithm.
Per-Platform Weights
| Platform | Category Weights |
|---|---|
| Conversion 25%, Waste 20%, Structure 15%, Keywords 15%, Ads 15%, Settings 10% | |
| Meta | Pixel/CAPI 30%, Creative 30%, Structure 20%, Audience 20% |
| Tech 25%, Audience 25%, Creative 20%, Lead Gen 15%, Budget 15% | |
| TikTok | Creative 30%, Tech 25%, Bidding 20%, Structure 15%, Performance 10% |
| Microsoft | Tech 25%, Syndication 20%, Structure 20%, Creative 20%, Settings 15% |
Aggregate Score
Aggregate = Sum(Platform_Score x Platform_Budget_Share)
Grade: A (90-100), B (75-89), C (60-74), D (40-59), F (<40)
Output Files
ADS-AUDIT-REPORT.md: Comprehensive multi-platform findingsADS-ACTION-PLAN.md: Prioritized recommendations (Critical > High > Medium > Low)ADS-QUICK-WINS.md: Items fixable in <15 minutes with high impact
Report Structure
Executive Summary
- Aggregate Ads Health Score (0-100) with grade
- Per-platform scores
- Business type detected
- Active platforms identified
- Top 5 critical issues across all platforms
- Top 5 quick wins across all platforms
Per-Platform Sections
Each platform section includes:
- Platform Health Score with grade
- Category breakdown with pass/warning/fail per check
- Platform-specific Quick Wins
- Detailed findings with remediation steps
Cross-Platform Analysis
- Budget allocation assessment (actual vs recommended)
- Tracking consistency (are all platforms tracking the same events?)
- Creative consistency (is messaging aligned across platforms?)
- Attribution overlap (are platforms double-counting conversions?)
Strategic Recommendations
- Platform prioritization based on business type
- Budget reallocation recommendations
- Scaling opportunities (platforms/campaigns ready to scale)
- Kill list (campaigns/ad groups to pause immediately)
Priority Definitions
- Critical: Revenue/data loss risk (fix immediately)
- High: Significant performance drag (fix within 7 days)
- Medium: Optimization opportunity (fix within 30 days)
- Low: Best practice, minor impact (backlog)
Quick Wins Criteria
IF severity == "Critical" OR severity == "High"
AND estimated_fix_time < 15 minutes
THEN flag as Quick Win
SORT BY (severity_multiplier x estimated_impact) DESC- 流狐分类
- 安全
- 作者声明 Agent
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 作者 / 版本 / 许可
- @AgriciDaniel · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 需简单配置
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。 Collect account data: request exports, screenshots, or API access Validate: confirm at least one platform's data is available before proceeding Detect business type: analyze account signals per ads orchestrator
Ask the user for available data. Accept any combination: Google Ads: account export, Change History, Search Terms Report Meta Ads: Ads Manager export, Events Manager screenshot, EMQ scores
Read ads/references/scoring-system.md for full algorithm.
Platform · Category Weights Google · Conversion 25%, Waste 20%, Structure 15%, Keywords 15%, Ads 15%, Settings 10% Meta · Pixel/CAPI 30%, Creative 30%, Structure 20%, Audience 20%
Aggregate Score
ADS-AUDIT-REPORT.md: Comprehensive multi-platform findings ADS-ACTION-PLAN.md: Prioritized recommendations (Critical > High > Medium > Low) ADS-QUICK-WINS.md: Items fixable in <15 minutes with high impact
# Full Multi-Platform Ads Audit
This audit operates under the **10-Principle Thinking Framework** (see
`ads/references/thinking-framework.md`). OBSERVE (External + Internal)
dominates data collection, THINK + CONNECT (Lateral) dominate analysis,
CONNECT (System) + ACCEPT dominate synthesis and prioritization. If the
audit feels mechanical, you are skipping a principle.
## Process
1. **Collect account data**: request exports, screenshots, or API access
2. **Validate**: confirm at least one platform's data is available before proceeding
3. **Detect business type**: analyze account signals per ads orchestrator
4. **Identify active platforms**: determine which platforms are in use
5. **Delegate to subagents** (if available, otherwise run inline sequentially):
- `audit-google`: Conversion tracking, wasted spend, structure, keywords, ads, settings (80 checks; G01-G61 + 19 hyphenated v1.5+ IDs incl. AI Max)
- `audit-meta`: Pixel/CAPI health, creative fatigue, structure, audience (50 checks; M01-M40 + 10 hyphenated v1.5+ IDs incl. Andromeda)
- `audit-creative`: LinkedIn, TikTok, Microsoft creative checks + cross-platform synthesis
- `audit-tracking`: LinkedIn, TikTok, Microsoft tracking + cross-platform tracking health
- `audit-budget`: LinkedIn, TikTok, Microsoft budget/bidding + cross-platform allocation
- `audit-compliance`: All-platform compliance, settings, performance benchmarks
6. **Validate**: verify each subagent returned valid scores with required fields before aggregating
7. **Score**: calculate per-platform and aggregate Ads Health Score (0-100)
8. **Report**: generate prioritized action plan with Quick Wins
## Data Collection
Ask the user for available data. Accept any combination:
… 作者原文负责流程事实;流狐只索引当前章节、要点、文件与命令。
章节 -> Process → Data Collection → Scoring → Per-Platform Weights → Aggregate Score → Output Files
要点 -> 10-Principle Thinking Framework · Collect account data · Validate · Detect business type · Identify active platforms · Delegate to subagents · Score · Report
文件/命令 -> ads/references/thinking-framework.md · audit-google · audit-meta · audit-creative · audit-tracking · audit-budget · audit-compliance · ads/references/scoring-system.md
内容 SHA-256 -> 336b720d002e
方法与流程
适用与边界
原文中的明确线索
ads/references/thinking-framework.md、audit-google、audit-meta、audit-creative、audit-tracking、audit-budget、audit-compliance、ads/references/scoring-system.md