agentleFS
Sign inStart free
gomarble-aigomarble-ai/marketing-agent/skills/meta-creative-fatigue-detection/SKILL.md

meta-creative-fatigue-detection

Skill15 starsChanged 37 days agoMITView on GitHub

Per-ad creative fatigue diagnosis on Meta Ads. Scores every active ad as Healthy / Early Warning / Fatigued / Dead using CTR decline, frequency creep, CPA spike, CVR decline, and spend-shift signals. Surfaces specific refresh recommendations: which variants to retire, which winners to remix, which themes to test next. Read-only — no pauses applied. Use weekly or before any creative refresh cycle.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user didn't name an account, list their connected accounts and ask which one to use.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meta Creative Fatigue Detection (Read-Only)

Diagnose creative fatigue across the ad account the user names. Default lookback: 14 days. Read-only — never pauses or modifies ads.

If the user didn't name an account, list their connected accounts and ask which one to use.

Fatigue scoring signals

Score each active ad on:

SignalHealthyEarly WarningFatiguedDead
CTR decline vs first-week-of-life< 10% drop10–25% drop25–50% drop> 50% drop
Frequency< 2.52.5 – 3.53.5 – 5> 5
CPA spike vs ad-set median< 10% above10–25% above25–50% above> 50% above
CVR decline vs first-week< 10% drop10–25% drop25–50% drop> 50% drop
Spend shiftStable or risingFlatlinedDecliningReaching cliff

Final classification = worst signal score across all five dimensions.

Output

Section 1 — Fatigue summary table

| Ad name | Score | CTR drop | Freq | CPA delta | CVR drop | Days live |

Sort: most fatigued first. Cap at top 20.

Section 2 — Per-ad recommendations

For each Fatigued or Dead ad, one line:

  • 🪦 [Ad name] — Dead. Recommendation: retire. The hook is exhausted; do not relaunch as-is.
  • 🔻 [Ad name] — Fatigued. Recommendation: pause this variant; the underlying concept is still winning, remix the hook.
  • ⚠️ [Ad name] — Early Warning. Watch — likely needs a refresh in 7–14 days.

For each Healthy or Early Warning winning ad with strong CVR:

  • ✨ [Ad name] — Healthy winner. Recommendation: extract the pattern, brief 2–3 variants on the same concept.

Section 3 — Creative refresh brief

3–5 bullet points on what themes/hooks/formats deserve fresh creative based on the patterns you see in the Fatigued + Healthy-winner cohorts.

End with: _All recommendations — no changes applied. Ask explicitly to pause anything._

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free