ads
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAds — Multi-Platform Paid Advertising Audit & Optimization
Ads — 多平台付费广告审计与优化
Comprehensive ad account analysis across all major platforms (Google, Meta,
LinkedIn, TikTok, Microsoft). Orchestrates 12 specialized sub-skills and
6 subagents.
覆盖所有主流平台（Google、Meta、LinkedIn、TikTok、Microsoft）的全面广告账户分析。可协调12项专业子技能和6个子代理。
Quick Reference
快速参考
| Command | What it does |
|---|---|
| Full multi-platform audit with parallel subagent delegation |
| Google Ads deep analysis (Search, PMax, YouTube) |
| Meta Ads deep analysis (FB, IG, Advantage+) |
| YouTube Ads specific analysis |
| LinkedIn Ads deep analysis (B2B, Lead Gen) |
| TikTok Ads deep analysis (Creative, Shop, Smart+) |
| Microsoft/Bing Ads deep analysis (Copilot, Import) |
| Cross-platform creative quality audit |
| Landing page quality assessment for ad campaigns |
| Budget allocation and bidding strategy review |
| Strategic ad plan with industry templates |
| Competitor ad intelligence analysis |
| 命令 | 功能 |
|---|---|
| 全多平台审计，并行委派子代理执行 |
| Google Ads深度分析（搜索、PMax、YouTube） |
| Meta Ads深度分析（FB、IG、Advantage+） |
| YouTube Ads专项分析 |
| LinkedIn Ads深度分析（B2B、线索生成） |
| TikTok Ads深度分析（创意、店铺、Smart+） |
| Microsoft/Bing Ads深度分析（Copilot、导入功能） |
| 跨平台创意质量审计 |
| 广告系列落地页质量评估 |
| 预算分配与出价策略审核 |
| 基于行业模板的广告战略规划 |
| 竞品广告情报分析 |
Orchestration Logic
协调逻辑
When the user invokes , delegate to subagents in parallel:
/ads audit- Collect account data (exports, screenshots, or API access details)
- Detect business type and identify active platforms
- Spawn subagents: audit-google, audit-meta, audit-creative, audit-tracking, audit-budget, audit-compliance
- Collect results and generate unified report with Ads Health Score (0-100)
- Create prioritized action plan with Quick Wins
For individual commands (, , etc.), load the relevant
sub-skill directly.
/ads google/ads meta当用户调用时，并行委派给子代理执行：
/ads audit- 收集账户数据（导出文件、截图或API访问详情）
- 检测业务类型并识别活跃平台
- 生成子代理：audit-google、audit-meta、audit-creative、audit-tracking、audit-budget、audit-compliance
- 收集结果并生成带有Ads健康评分（0-100）的统一报告
- 创建包含快速优化项的优先级行动计划
对于单个命令（如、等），直接加载对应的子技能。
/ads google/ads metaIndustry Detection
行业检测
Detect business type from ad account signals:
- SaaS: trial_start/demo_request events, pricing page targeting, long attribution windows
- E-commerce: purchase events, product catalog/feed, Shopping/PMax campaigns
- Local Service: call extensions, location targeting, store visits, directions events
- B2B Enterprise: LinkedIn Ads active, ABM lists, high CPA tolerance ($50+), long sales cycle
- Info Products: webinar/course funnels, lead gen forms, low-ticket offers
- Mobile App: app install campaigns, in-app events, deep linking
- Real Estate: listing feeds, property-specific landing pages, geo-heavy targeting
- Healthcare: HIPAA compliance flags, healthcare-specific ad policies
- Finance: Special Ad Categories declared, financial products compliance
- Agency: multiple client accounts, white-label reporting needs
通过广告账户信号检测业务类型：
- SaaS：trial_start/demo_request事件、定价页面定向、长归因窗口
- 电商：购买事件、商品目录/商品源、购物/PMax广告系列
- 本地服务：电话扩展、地理位置定向到店、到店访问/导航事件
- B2B企业：LinkedIn Ads活跃、ABM名单、高CPA容忍度（≥50美元）、长销售周期
- 信息产品： webinar/课程漏斗、线索生成表单、低价产品
- 移动应用：应用安装广告系列、应用内事件、深度链接
- 房地产：房源信息源、房产专属落地页、重度地理位置定向
- 医疗健康：HIPAA合规标记、医疗健康专属广告政策
- 金融：已声明特殊广告类别、金融产品合规性
- 代理机构：多客户账户、白标报告需求
Quality Gates
质量准则
Hard rules — never violate these:
- Never recommend Broad Match without Smart Bidding (Google)
- 3x Kill Rule: flag any ad group/campaign with CPA >3x target for pause
- Budget sufficiency: Meta ≥5x CPA per ad set, TikTok ≥50x CPA per ad group
- Learning phase: never recommend edits during active learning phase
- Compliance: always check Special Ad Categories for housing/employment/credit/finance
- Creative: never run silent video ads on TikTok (sound-on platform)
- Attribution: default to 7-day click / 1-day view (Meta), data-driven (Google)
硬性规则——绝不能违反：
- 绝不推荐在未使用智能出价（Google）的情况下使用广泛匹配
- 3倍淘汰规则：标记任何CPA超过目标3倍的广告组/广告系列以暂停
- 预算充足性：Meta每个广告组预算≥5倍CPA，TikTok每个广告组预算≥50倍CPA
- 学习阶段：在活跃学习阶段绝不推荐进行编辑
- 合规性：始终检查住房/就业/信贷/金融相关的特殊广告类别
- 创意：TikTok上绝不投放无声音频的视频广告（该平台以有声内容为主）
- 归因：默认采用7天点击/1天展示（Meta），数据驱动型归因（Google）
Reference Files
参考文件
Load these on-demand as needed — do NOT load all at startup.
Path resolution: All references are installed at .
When sub-skills or agents reference , resolve to
.
~/.claude/skills/ads/references/ads/references/*.md~/.claude/skills/ads/references/*.md- — Weighted scoring algorithm and grading thresholds
references/scoring-system.md - — Industry benchmarks by platform (CPC, CTR, CVR, ROAS)
references/benchmarks.md - — Bidding decision trees per platform
references/bidding-strategies.md - — Platform selection matrix, scaling rules, MER
references/budget-allocation.md - — Creative specifications across all platforms
references/platform-specs.md - — Pixel, CAPI, EMQ, ttclid implementation
references/conversion-tracking.md - — Regulatory requirements, ad policies, privacy
references/compliance.md - — 74-check Google Ads audit checklist
references/google-audit.md - — 46-check Meta Ads audit checklist
references/meta-audit.md - — 25-check LinkedIn Ads audit checklist
references/linkedin-audit.md - — 25-check TikTok Ads audit checklist
references/tiktok-audit.md - — 20-check Microsoft Ads audit checklist
references/microsoft-audit.md
按需加载这些文件——切勿在启动时全部加载。
路径解析：所有参考文件均安装在路径下。
当子技能或代理引用时，解析为。
~/.claude/skills/ads/references/ads/references/*.md~/.claude/skills/ads/references/*.md- — 加权评分算法及分级阈值
references/scoring-system.md - — 各平台行业基准数据（CPC、CTR、CVR、ROAS）
references/benchmarks.md - — 各平台出价策略决策树
references/bidding-strategies.md - — 平台选择矩阵、扩容规则、MER
references/budget-allocation.md - — 全平台创意规格
references/platform-specs.md - — Pixel、CAPI、EMQ、ttclid实施指南
references/conversion-tracking.md - — 监管要求、广告政策、隐私规范
references/compliance.md - — 74项检查的Google Ads审计清单
references/google-audit.md - — 46项检查的Meta Ads审计清单
references/meta-audit.md - — 25项检查的LinkedIn Ads审计清单
references/linkedin-audit.md - — 25项检查的TikTok Ads审计清单
references/tiktok-audit.md - — 20项检查的Microsoft Ads审计清单
references/microsoft-audit.md
Scoring Methodology
评分方法
Ads Health Score (0-100)
Ads健康评分（0-100）
Per-platform score using weighted algorithm from .
Cross-platform aggregate weighted by budget share:
references/scoring-system.mdAggregate = Sum(Platform_Score x Platform_Budget_Share)采用中的加权算法计算各平台得分。跨平台总得分按预算占比加权计算：
references/scoring-system.md总得分 = Σ(平台得分 × 平台预算占比)Grading
评级
| Grade | Score | Action Required |
|---|---|---|
| A | 90-100 | Minor optimizations only |
| B | 75-89 | Some improvement opportunities |
| C | 60-74 | Notable issues need attention |
| D | 40-59 | Significant problems present |
| F | <40 | Urgent intervention required |
| 评级 | 得分 | 行动要求 |
|---|---|---|
| A | 90-100 | 仅需小幅优化 |
| B | 75-89 | 存在部分优化机会 |
| C | 60-74 | 存在显著问题需关注 |
| D | 40-59 | 存在严重问题 |
| F | <40 | 需紧急干预 |
Priority Levels
优先级等级
- 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)
- Critical（紧急）：存在收入/数据损失风险（立即修复）
- High（高优先级）：严重影响投放效果（7天内修复）
- Medium（中优先级）：优化机会（30天内修复）
- Low（低优先级）：最佳实践建议，影响较小（列入待办）
Sub-Skills
子技能
This skill orchestrates 12 specialized sub-skills:
- ads-audit — Full multi-platform audit with parallel delegation
- ads-google — Google Ads deep analysis (Search, PMax, YouTube)
- ads-meta — Meta Ads deep analysis (FB, IG, Advantage+)
- ads-youtube — YouTube Ads specific analysis
- ads-linkedin — LinkedIn Ads deep analysis
- ads-tiktok — TikTok Ads deep analysis
- ads-microsoft — Microsoft/Bing Ads deep analysis
- ads-creative — Cross-platform creative quality audit
- ads-landing — Landing page quality for ad campaigns
- ads-budget — Budget allocation and bidding strategy
- ads-plan — Strategic ad planning with industry templates
- ads-competitor — Competitor ad intelligence
本技能可协调12项专业子技能：
- ads-audit — 全多平台审计，并行委派执行
- ads-google — Google Ads深度分析（搜索、PMax、YouTube）
- ads-meta — Meta Ads深度分析（FB、IG、Advantage+）
- ads-youtube — YouTube Ads专项分析
- ads-linkedin — LinkedIn Ads深度分析
- ads-tiktok — TikTok Ads深度分析
- ads-microsoft — Microsoft/Bing Ads深度分析
- ads-creative — 跨平台创意质量审计
- ads-landing — 广告系列落地页质量评估
- ads-budget — 预算分配与出价策略
- ads-plan — 基于行业模板的广告战略规划
- ads-competitor — 竞品广告情报分析
Subagents
子代理
For parallel analysis during full audits:
- — Google Ads checks (G01-G74)
audit-google - — Meta Ads checks (M01-M46)
audit-meta - — Creative quality for LinkedIn, TikTok, Microsoft
audit-creative - — Conversion tracking health across all platforms
audit-tracking - — Budget, bidding, structure for LinkedIn, TikTok, Microsoft
audit-budget - — Compliance, settings, performance across all platforms
audit-compliance
全审计过程中用于并行分析：
- — Google Ads检查（G01-G74）
audit-google - — Meta Ads检查（M01-M46）
audit-meta - — LinkedIn、TikTok、Microsoft平台创意质量检查
audit-creative - — 全平台转化追踪健康检查
audit-tracking - — LinkedIn、TikTok、Microsoft平台预算、出价、结构检查
audit-budget - — 全平台合规性、设置、效果检查
audit-compliance