How does it determine tipping points?

It analyzes where CTR declines and CPA rises as Frequency increases, then selects the lower tipping point to ensure safety.

What if CTR and CPA tipping points differ?

The agent adopts the safety-first approach and uses the lower tipping point to produce the final weekly cap.

Where is the output stored and how is it applied?

The recommended cap is written to frequency_recommendation.txt; apply this per-week cap in your campaigns to enforce the limit.

Ad Frequency Capper

Scanned

npx machina-cli add skill akhilkannur/marketing-agent-blueprints/ad-frequency-capper --openclaw

Files (1)

SKILL.md

1.4 KB

The Ad Frequency Capper

Core Instructions

You are a highly specialized AI agent focusing on Paid Media. Your mission is: Ad fatigue kills ROI. This agent tracks the relationship between 'Frequency' (Avg times seen) and 'CTR' or 'CPA' in your campaign data, identifying the exact tipping point where performance degrades so you can set a cap.

Implementation Workflow

Phase 1: Initialization & Seeding

Check: Does frequency_data.csv exist?
If Missing: Create frequency_data.csv using the sampleData provided in this blueprint.

Phase 2: The Curve Analysis

Read: frequency_data.csv.
Analyze CTR: When does it drop? (e.g., after Freq 2).
Analyze CPA: When does it spike? (e.g., after Freq 3).

Phase 3: The Cap Output

Select: The lower of the two tipping points (Safety first).
Output: Save frequency_recommendation.txt.
Summary: "Performance degrades after 2.5 views. Set Frequency Cap to 3 per week to save budget."

Blueprint ID: ad-frequency-capper Source: Real AI Examples

Source

git clone https://github.com/akhilkannur/marketing-agent-blueprints/blob/main/skills/ad-frequency-capper/SKILL.mdView on GitHub

Overview

Ad Frequency Capper analyzes how Frequency (average exposures) relates to CTR and CPA to identify the exact tipping point where performance degrades. It seeds frequency_data.csv if missing, analyzes the data, and outputs a safe cap recommendation to preserve ROI so you don’t overspend on fatigued audiences.

How This Skill Works

The agent loads frequency_data.csv (creating it from sampleData if absent), evaluates where CTR declines and CPA spikes as Frequency rises, and determines the lower tipping point for safety. It then writes the recommended cap to frequency_recommendation.txt and provides a concise summary for implementation.

When to Use It

You see CTR decline as Frequency increases beyond a couple of impressions.
CPA starts to rise after Frequency reaches the higher exposure level.
You need a data-backed weekly cap to protect ROI across campaigns.
You’ve launched a new creative or audience and want to balance exposure with fatigue.
You want an automated, reproducible cap policy that can be re-calibrated over time.

Quick Start

Step 1: Ensure frequency_data.csv exists; if missing, seed it from the provided sampleData.
Step 2: Run the Ad Frequency Capper to analyze CTR and CPA tipping points.
Step 3: Open frequency_recommendation.txt and apply the recommended per-week cap in your campaigns (e.g., 3/week).

Best Practices

Use up-to-date campaign data for analysis.
Consider both CTR decline and CPA spike when identifying tipping points.
Favor the lower tipping point to introduce a safety buffer.
Automate periodic runs to adjust caps as performance shifts.
Validate the recommended cap with a controlled test before full rollout.

Example Use Cases

CTR dips after 2 impressions; cap recommended at 3 per week to maintain engagement.
CPA spikes after 3 exposures; cap set to 3 per week to protect cost.
Both CTR and CPA indicate tipping points near 2.5 exposures; safety-first cap is 3/week.
Campaign shows no CTR gains beyond 3 exposures; apply a 3/week cap to preserve ROAS.
New creative data suggests cap can be 3/week as a budget-saving measure.

Frequently Asked Questions

Add this skill to your agents