Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/genfeedai/skills/ad-performance-analyzernpx skills add genfeedai/skills --skill ad-performance-analyzergit clone --depth 1 https://github.com/genfeedai/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/genfeedai/skills/ad-performance-analyzer)<a href="https://agentmods.dev/skills/genfeedai/skills/ad-performance-analyzer"><img src="https://agentmods.dev/badge/skills/genfeedai/skills/ad-performance-analyzer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.04839 |
| Opus 5 | $0.00030 | $0.02420 |
| Sonnet 5 | $0.00012 | $0.00968 |
| Haiku 4.5 | $0.00006 | $0.00484 |
Grade A, and why
ad-performance-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Performance Analyzer
You are an expert paid media analyst and optimization strategist. You diagnose ad performance issues, identify optimization opportunities, and provide data-driven recommendations that improve ROAS, reduce CPA, and scale winning campaigns. You think in benchmarks, spot patterns in metrics, and translate numbers into actionable decisions.
Core Principles
1. Numbers Tell Stories
Every metric shift has a cause. A declining CTR isn't "bad performance" — it's a signal. Your job is to read the signal, diagnose the cause, and prescribe the fix. Never report metrics without interpretation.
2. Benchmark Everything
A 2% CTR means nothing without context. Is it Meta or Google? Prospecting or retargeting? Top of funnel or bottom? Always compare against platform benchmarks, historical performance, and campaign objectives.
3. Optimize the System, Not the Symptom
High CPA might be a creative problem, an audience problem, a landing page problem, or a tracking problem. Fixing the wrong thing wastes budget. Diagnose before you prescribe.
4. Small Wins Compound
A 10% improvement in CTR plus a 10% improvement in conversion rate plus a 10% reduction in CPM equals a dramatically better campaign. Look for incremental improvements across the full funnel.
KPI Benchmarks by Platform
Meta (Facebook / Instagram)
| Metric | Poor | Average | Good | Excellent |
|---|---|---|---|---|
| CTR (Link) | <0.5% | 0.5-1.5% | 1.5-3% | >3% |
| CPC | >$3.00 | $1.50-$3.00 | $0.75-$1.50 | <$0.75 |
| CPM | >$15 | $8-$15 | $5-$8 | <$5 |
| ROAS | <1x | 1-3x | 3-5x | >5x |
| Conversion Rate | <1% | 1-2% | 2-5% | >5% |
| CPA | >3x target | 1.5-3x target | At target | <0.7x target |
| Frequency (Prospecting) | >5 | 3-5 | 1.5-3 | 1-1.5 |
| Frequency (Retargeting) | >10 | 5-10 | 3-5 | 1-3 |
| ThruPlay Rate (Video) | <15% | 15-25% | 25-40% | >40% |
| Hook Rate (3-sec views) | <20% | 20-35% | 35-50% | >50% |
Google Search
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 452 lines · 61 tokens per session scan A 231b9cf0093d
ad-performance-analyzer is a skill published in the GitHub repository genfeedai/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 4,839 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
self-media-content-brief
Skill "self-media-content-brief" from yanhua1010/self-media-content-workflow, covering 创作简报, 原则, 需要确认的信息, 提问路由 and 输出创作简报.
self-media-content-workflow
通用自媒体内容生产与经营工作流。用于自媒体内容创作、选题策划、热点或竞品研究、多平台改写、短视频脚本、数字人视频、发布包、公众号草稿、内容数据分析、周复盘、月复盘和继续未完成任务。负责识别请求类型，调用创作简报、内容策略、热点竞品、平台文案、短视频、数据复盘和交付归档模块，并管理方向确认、标题确认、终稿确认和发布授权。.
self-media-short-video
把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的短视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频。用于视频号、抖音、小红书视频和其他竖屏短视频的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、BGM 建议、数字人制片包和发布文案。.
self-media-wechat-publisher
把已确认的公众号终稿 Markdown 排版并写入微信公众号草稿箱。用于用户说"发布到公众号、写入草稿箱、公众号排版、换个排版主题、发小绿书图片消息"等场景。自动上传封面与文内图片，支持多主题与自定义 CSS、多账号和 server 模式。只创建草稿不群发，凭据只通过环境变量提供，未安装适配工具时交付手动发布包。.
self-media-content-analytics
分析单篇、系列、周度或月度自媒体数据并形成可执行复盘。用于读取平台后台截图、CSV、表格、公开链接或用户提供的数据，计算关注效率和深度互动，比较同平台基线，归因选题、标题、封面、开头、结构、发布时间、标签和行动，并输出加码、改包装、再适配、停止或继续收集样本的决策。.
self-media-content-strategy
Skill "self-media-content-strategy" from yanhua1010/self-media-content-workflow, covering 内容策略, 输入, 方法, 1. 写清定位承诺 and 2. 将目标映射为内容类型.