# Diagnose ad fatigue and choose the next action

Campaign metrics can decline for different reasons, which makes budget decisions difficult. This skill compares frequency, CTR, CVR, and reach trends to recommend rotating creative, widening an audience, or holding.

## Install

```bash
npx skillstore add aaron-he-zhu/fatigue-frequency-manager
```

## Metadata

- Status: approved
- Slug: aaron-he-zhu-fatigue-frequency-manager
- Version: 19.0.0
- Author version: 19.0.0
- Skillstore revision: r2
- Version status: valid
- Tree hash: 9dc4c433a0eb8f5a7fcfe8d88191295cccabb3d8dd587893bfc8e1336be0c3de
- Author: aaron-he-zhu
- GitHub username: aaron-he-zhu
- License: Apache-2.0
- Repository: https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/ad/scale/fatigue-frequency-manager
- Ref: adcb3549b15782055d0beb6d29f113d20de08f92
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network, filesystem
- Quality score: 81
- Quality tier: silver
- Public page: https://skillstore.pages.dev/skills/aaron-he-zhu-fatigue-frequency-manager
- Manifest: https://skillstore.pages.dev/api/skills/aaron-he-zhu-fatigue-frequency-manager/manifest

## Capabilities

- Compares current frequency, CTR, CVR, and reach with an early-flight baseline.
- Distinguishes creative fatigue from audience saturation using trend signals.
- Returns one Rotate-creative, Widen-audience, or Hold recommendation per ad set.
- Identifies when a short data window or learning phase prevents a reliable decision.
- Flags conversion measurement uncertainty before relying on CVR changes.

## Use Cases

- Review a declining prospecting campaign: Compare two weeks of campaign data to determine whether falling CTR requires a creative rotation or audience expansion.
- Set a frequency decision rule: Use an early-flight baseline and objective-specific ceiling to define when an ad set needs intervention.
- Validate a client performance report: Separate a real conversion decline from incomplete tracking before presenting a campaign recommendation.

## Prompt Templates

### Check a simple fatigue signal

```
Frequency reached 6.2 and CTR fell by half over two weeks. Explain whether this looks like creative fatigue or audience saturation.
```

### Review one ad set

```
Review this ad-set time series. Compare it with the first stable week and return frequency, CTR, CVR, reach trends, and one recommended trigger.
```

### Compare campaign segments

```
Analyze these prospecting and retargeting ad sets separately. Use appropriate frequency ceilings, identify the dominant cause for each, and state caveats.
```

### Validate data before action

```
Assess this campaign export with GA4 and order totals. Do not recommend rotation or expansion if the CVR decline may be caused by tracking errors.
```

## Limitations

- Requires a daily or weekly time-series export; a single-day snapshot is insufficient.
- Does not create replacement ads or build new audience segments.
- Does not calculate the RQS score or make final measurement veto decisions.
- Recommendations depend on the accuracy of the provided platform and order data.

## Best Practices

- Provide a stable early-flight baseline and a daily or weekly metric export.
- Label estimates separately from exported and user-provided metrics.
- Verify conversion tracking with order data before acting on a CVR decline.

## Anti Patterns

- Do not diagnose fatigue from a single-day dashboard snapshot.
- Do not use one universal frequency threshold for every campaign objective.
- Do not treat a CVR decline as saturation before checking tracking quality.

## Security Audit

- Audited at: 2026-07-26T10:19:45.335\+00:00
- Summary: Most static findings are false positives caused by Markdown formatting, fixed documentation links, and metadata URLs. One command template is confirmed: it places a user-controlled ad-set placeholder directly in a shell command, creating a command-injection risk if executed literally. The skill otherwise instructs agents to treat campaign exports as untrusted data and requires confirmation before saving results.

## Stats

- Views: 0
- Downloads: 6
- Favorites: 0
- Popularity score: 0