跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
营销与销售

ad-campaign-analyzer

Use this skill to grade running ads as Red (stop), Yellow (hold), or Green (scale), detect creative fatigue, analyze LTV:CAC, and recommend scaling actions. Trigger it when reviewing campaign exports or deciding what to kill, keep, or scale.

superamped · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add superamped/ai-marketing-skills --skill ad-campaign-analyzer

技能说明


name: ad-campaign-analyzer description: "Use this skill to grade running ads as Red (stop), Yellow (hold), or Green (scale), detect creative fatigue, analyze LTV:CAC, and recommend scaling actions. Trigger it when reviewing campaign exports or deciding what to kill, keep, or scale." license: MIT compatibility: "No special requirements. Accepts campaign data as CSV, table, or pasted text." metadata: author: superamped version: "1.0" website: "https://superamped.com"

Ad Campaign Analyzer

Usage

Use when reviewing a running campaign to decide what to kill, keep, or scale. Works for daily 15-minute ad reviews, weekly creative refresh planning, and monthly performance trend reviews.

Process

Step 1: Gather Inputs

Ask the user for:

  1. Campaign data — one of:
    • CSV or table with columns: ad/ad set name, impressions, clicks, conversions, spend, CPA
    • Pasted text from ads manager
    • Structured list of metrics per ad
  2. Target CPA — the maximum they're willing to pay per acquisition
  3. AOV (Average Order Value) — what they earn per conversion on the front end
  4. Product/pricing info — what they sell, offer details, known conversion benchmarks
  5. Daily budget per ad set (optional) — for scaling calculations
  6. Days running (optional) — for statistical significance judgment
  7. Historical data (optional) — from previous review for trend comparison

Step 2: Parse Campaign Data

Normalize the input into a consistent table structure:

Ad / Ad SetImpressionsClicksCTRConversionsSpendCPADays Running

Calculate any missing derived metrics:

  • CTR = clicks / impressions × 100
  • CPA = spend / conversions (∞ if 0 conversions)
  • Conversion rate = conversions / clicks × 100

Step 3: Grade Each Ad — Red / Yellow / Green

🔴 RED = STOP

Kill this ad. It's burning money.

Criteria (any one triggers Red):

  • Spent 1.5–2x target CPA with zero conversions
  • CPA is 2x+ target CPA with statistically significant spend
  • Consistently worsening metrics over multiple days with no improvement signs
  • CTR below 0.5% after 1,000+ impressions (the creative isn't connecting)

Action: Turn off immediately. Redirect budget to greens.

🟡 YELLOW = LEAVE ALONE

Don't touch it. It needs more data or is borderline.

Criteria:

  • CPA is close to target (within 0.5–1.5x) but not enough data to be confident
  • Fewer than 1,000 impressions or fewer than 20 clicks — too early to judge
  • Spend is under 1x target CPA — hasn't had a fair chance yet
  • Metrics are mixed (good CTR but low conversion, or vice versa)

Action: Do nothing. Check again tomorrow. Resist the urge to tweak.

🟢 GREEN = SCALE

This ad is working. Give it more budget.

Criteria:

  • CPA is consistently at or below target CPA
  • Has statistically significant data (generally 10+ conversions)
  • Metrics are stable or improving over time
  • CTR is healthy for the targeting type

Action: Scale using the 20% Rule — increase daily budget by 20% every 48 hours.

Step 4: Benchmark Comparison

Compare each ad's metrics against industry benchmarks:

CTR Benchmarks (by targeting type):

TargetingExpected CTR
Broad / run-of-network1–3%
Interest-based targeting2–4%
Lookalike / community-targeted3–5%

CPA Targets by Offer Price:

Offer Price RangeExpected CPA Range
$7–27 (low ticket)$20–40
$37–97 (mid ticket)$40–120
$97+ (high ticket)Varies — must model LTV

Step 4b: Funnel Debugging — Find the Leak

Before changing creative, check whether the ad is actually the problem. Work from the surface inward:

  1. Creative — Is the CTR acceptable? Low CTR = the ad isn't connecting. Test new hooks, visuals, or headlines.
  2. Landing page — CTR is fine but conversions are flat? The LP is the problem.
  3. Messaging — LP structure looks okay but still no conversions? The fundamental message may not be resonating.
  4. Product and pricing — Different angles all fail? The offer itself may be the issue.
  5. Market — Everything above looks solid but the right people still aren't converting? The segment may be wrong.

Work from #1 → #5 in order. Most founders jump to #3 or #4 when the actual problem is #1 or #2.

Data thresholds — don't debug on noise:

  • < 1,000 impressions per ad variant: Too early to judge CTR.
  • < 100 LP visitors: Too early to judge landing page conversion.
  • < 10 conversions on a green ad: Scale cautiously — the trend may not hold.

Step 5: Flag Creative Fatigue

Check for fatigue signals across the data:

  • Declining CTR over time (even if still "okay" in absolute terms)
  • Rising CPA despite no changes to targeting or budget
  • Dropping conversion rate with stable traffic quality
  • Frequency above 3 (same people seeing the ad too many times)

If fatigue is detected, flag which ads are affected and recommend:

  • New creative variation (different angle, format, or style)
  • Audience refresh (new targeting or exclusions)
  • Copy refresh (same visual, new headline)

Step 6: Profitability Check

The North Star: Is AOV > CPA?

For each green ad, calculate:

  • Profit per conversion = AOV − CPA
  • ROAS = AOV / CPA (must be > 1.0 to be profitable)
  • Break-even CPA = AOV (you make $0 at this point)
  • Margin at current CPA = (AOV − CPA) / AOV × 100

Step 6b: LTV:CAC Health Check

If LTV data is available, assess the pricing-level health of the campaign:

LTV:CAC Ratio Benchmarks:

Pricing FunctionAverage LTV:CAC
No pricing function1.68
Yearly pricing review3.23
Continuous optimization11.09

Interpret the ratio:

  • < 1:1 — Losing money on every customer. Stop spending until unit ec
阅读完整来源 ↗