ads by agricidaniel/claude-ads
npx skills add https://github.com/agricidaniel/claude-ads --skill ads跨所有主要平台(Google、Meta、LinkedIn、TikTok、Microsoft)的综合广告账户分析。协调 12 个专业子技能和 6 个子代理。
| 命令 | 功能说明 |
|---|---|
/ads audit | 完整的多平台审计,并行委托子代理 |
/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 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| LinkedIn Ads 深度分析(B2B、潜在客户开发) |
/ads tiktok | TikTok Ads 深度分析(创意、商店、Smart+) |
/ads microsoft | Microsoft/Bing Ads 深度分析(Copilot、导入) |
/ads creative | 跨平台创意质量审计 |
/ads landing | 广告活动落地页质量评估 |
/ads budget | 预算分配和出价策略审查 |
/ads plan <business-type> | 使用行业模板的战略广告计划 |
/ads competitor | 竞争对手广告情报分析 |
当用户调用 /ads audit 时,并行委托给子代理:
对于单个命令(/ads google、/ads meta 等),直接加载相关的子技能。
根据广告账户信号检测业务类型:
硬性规则 — 绝不违反以下规则:
按需加载这些文件 — 不要在启动时加载所有文件。
路径解析: 所有参考文件都安装在 ~/.claude/skills/ads/references/。当子技能或代理引用 ads/references/*.md 时,解析为 ~/.claude/skills/ads/references/*.md。
references/scoring-system.md — 加权评分算法和分级阈值references/benchmarks.md — 按平台划分的行业基准(CPC、CTR、CVR、ROAS)references/bidding-strategies.md — 每个平台的出价决策树references/budget-allocation.md — 平台选择矩阵、扩展规则、MERreferences/platform-specs.md — 所有平台的创意规格references/conversion-tracking.md — Pixel、CAPI、EMQ、ttclid 实施references/compliance.md — 法规要求、广告政策、隐私references/google-audit.md — 74 项检查的 Google Ads 审计清单references/meta-audit.md — 46 项检查的 Meta Ads 审计清单references/linkedin-audit.md — 25 项检查的 LinkedIn Ads 审计清单references/tiktok-audit.md — 25 项检查的 TikTok Ads 审计清单references/microsoft-audit.md — 20 项检查的 Microsoft Ads 审计清单使用 references/scoring-system.md 中的加权算法计算每个平台的分数。跨平台聚合分数按预算份额加权:
聚合分数 = 求和(平台分数 x 平台预算份额)
| 等级 | 分数 | 所需行动 |
|---|---|---|
| A | 90-100 | 仅需轻微优化 |
| B | 75-89 | 存在一些改进机会 |
| C | 60-74 | 需要注意的显著问题 |
| D | 40-59 | 存在重大问题 |
| F | <40 | 需要紧急干预 |
此技能协调 12 个专业子技能:
用于完整审计期间的并行分析:
audit-google — Google Ads 检查(G01-G74)audit-meta — Meta Ads 检查(M01-M46)audit-creative — LinkedIn、TikTok、Microsoft 的创意质量audit-tracking — 所有平台的转化跟踪健康状况audit-budget — LinkedIn、TikTok、Microsoft 的预算、出价、结构audit-compliance — 所有平台的合规性、设置、性能每周安装次数
64
仓库
GitHub 星标数
852
首次出现
2026年2月16日
安全审计
安装于
codex61
opencode60
gemini-cli60
github-copilot60
cursor60
amp59
Comprehensive ad account analysis across all major platforms (Google, Meta, LinkedIn, TikTok, Microsoft). Orchestrates 12 specialized sub-skills and 6 subagents.
| Command | What it does |
|---|---|
/ads audit | Full multi-platform audit with parallel subagent 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 (B2B, Lead Gen) |
/ads tiktok | TikTok Ads deep analysis (Creative, Shop, Smart+) |
/ads microsoft | Microsoft/Bing Ads deep analysis (Copilot, Import) |
/ads creative | Cross-platform creative quality audit |
/ads landing | Landing page quality assessment for ad campaigns |
/ads budget | Budget allocation and bidding strategy review |
/ads plan <business-type> | Strategic ad plan with industry templates |
/ads competitor | Competitor ad intelligence analysis |
When the user invokes /ads audit, delegate to subagents in parallel:
For individual commands (/ads google, /ads meta, etc.), load the relevant sub-skill directly.
Detect business type from ad account signals:
Hard rules — never violate these:
Load these on-demand as needed — do NOT load all at startup.
Path resolution: All references are installed at ~/.claude/skills/ads/references/. When sub-skills or agents reference ads/references/*.md, resolve to ~/.claude/skills/ads/references/*.md.
references/scoring-system.md — Weighted scoring algorithm and grading thresholdsreferences/benchmarks.md — Industry benchmarks by platform (CPC, CTR, CVR, ROAS)references/bidding-strategies.md — Bidding decision trees per platformreferences/budget-allocation.md — Platform selection matrix, scaling rules, MERreferences/platform-specs.md — Creative specifications across all platformsreferences/conversion-tracking.md — Pixel, CAPI, EMQ, ttclid implementationreferences/compliance.md — Regulatory requirements, ad policies, privacyreferences/google-audit.md — 74-check Google Ads audit checklistPer-platform score using weighted algorithm from references/scoring-system.md. Cross-platform aggregate weighted by budget share:
Aggregate = Sum(Platform_Score x Platform_Budget_Share)
| 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 |
This skill orchestrates 12 specialized sub-skills:
For parallel analysis during full audits:
audit-google — Google Ads checks (G01-G74)audit-meta — Meta Ads checks (M01-M46)audit-creative — Creative quality for LinkedIn, TikTok, Microsoftaudit-tracking — Conversion tracking health across all platformsaudit-budget — Budget, bidding, structure for LinkedIn, TikTok, Microsoftaudit-compliance — Compliance, settings, performance across all platformsWeekly Installs
64
Repository
GitHub Stars
852
First Seen
Feb 16, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex61
opencode60
gemini-cli60
github-copilot60
cursor60
amp59
营销心理学与心智模型应用指南 | 提升营销决策与客户行为理解
42,600 周安装
references/meta-audit.md — 46-check Meta Ads audit checklistreferences/linkedin-audit.md — 25-check LinkedIn Ads audit checklistreferences/tiktok-audit.md — 25-check TikTok Ads audit checklistreferences/microsoft-audit.md — 20-check Microsoft Ads audit checklist