ad-fatigue-check

Solid

Detect creative fatigue across active ads — rising frequency, declining CTR week-over-week, and CPM drift — score each ad FATIGUED / WATCH / FRESH, and hand the evidence to a creative refresh. Use when the user asks whether creatives are worn out, why CTR is falling, if frequency is too high, when to rotate or refresh ads, or requests クリエイティブ疲弊チェック / 広告の疲弊を確認 / フリークエンシーが高い / CTRが落ちてきた / そろそろ差し替え時か. Reads active ads per platform, applies documented fatigue thresholds with noise guards, and routes fatigued ads to /creative-generate or /creative-refresh.

AI & Automation 44 stars 6 forks Updated yesterday Apache-2.0

Install

View on GitHub

Quality Score: 87/100

Stars 20%
55
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Ad Fatigue Check > PREREQUISITE: Read `../_mureo-shared/SKILL.md` for auth, security rules, output format, and **Tool Selection** (Read/Write on Code, `mureo_strategy_*` / `mureo_state_*` MCP on Desktop / Cowork). Find the ads whose audience has seen them too many times. Creative fatigue is a slow leak — the same creative keeps spending while frequency climbs, CTR erodes, and CPM drifts up as the algorithm works harder to place a tiring ad. This skill reads active ads per platform, measures the fatigue signals the tools genuinely expose, scores each ad against documented thresholds (with noise guards so a single slow day never triggers a rotation), and hands the fatigued ones to a creative refresh with the evidence attached. ## Prerequisites - STRATEGY.md and STATE.json must exist (run the `onboard` skill first) ## Steps **Before you start**: Run the **Diagnostic preamble** from ../_mureo-shared/SKILL.md — load learning insights (mureo_learning_insights_get) and consult advisors (mureo_consult_advisor) before drawing conclusions. 0. **Establish today**: call `mureo_state_get` **first, on every host** (including Claude Code, where you would otherwise `Read` the file) and take `server_now` from its response — ISO 8601 with UTC offset, e.g. `2026-07-28T10:12:33+09:00`. Its date is the **only source of the current date** for this run: the `observation_due` you write in step 9 is `server_now`'s date + 14 days. (The week-over-week windows in step 3 are platform-side period ...

Details

Author
logly
Repository
logly/mureo
Created
5 months ago
Last Updated
yesterday
Language
Python
License
Apache-2.0

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

ad-fatigue

Decides whether an ad is genuinely fatigued or its owner is impatient, using a two-condition rule, frequency above four and click-through down thirty percent against that ad's own baseline and never another ad's, then returns a refresh-or-retire call per ad. Use when a previously working ad suddenly got expensive, and before killing anything. Boundary: `anomaly-detection` tests any metric series against its own trailing variability; this applies one fixed creative rule.

1 Updated today
sidchaudhary
AI & Automation Listed

ad-fatigue-detector

Diagnoses whether an ad is genuinely fatigued, never worked in the first place, is a victim of an account-wide or seasonal shift, or simply hasn't had enough data yet — and says which, with the evidence. Use whenever someone mentions creative fatigue, ad fatigue, frequency, "my ads stopped working", declining CTR or CPM creep, "should I refresh this creative", performance dropping off, or asks why a Meta / TikTok / YouTube / display ad that used to work no longer does. On Google or Microsoft Search, use this only for ad-copy decay on a specific ad — a broader search decline is usually query mix, bids, or Quality Score, so search-term-miner or quality-score-fixer fits better.

0 Updated 4 weeks ago
riz1k9
AI & Automation Listed

creative-health

Assess ad creative fatigue across active campaigns — scores each creative 0-100 via creative-fatigue-predictor.py (CTR, CPM, and engagement vs baseline, frequency saturation, time running), predicts days until fatigue, and delivers refresh briefs, A/B test plans, and a priority list ranked by estimated spend waste. Triggers on "/digital-marketing-pro:creative-health", "are our ads fatiguing", "CTR is dropping on our ads", "when should we refresh creatives", "which ads are wasting spend". Needs per-creative performance data (exported or from connected ad platform MCPs). Analysis and recommendations only — it does not pause or launch ads. Reads the brand profile and visual-identity restrictions for refresh constraints.

0 Updated 3 weeks ago
teachskillofskills-ai