General
PromptBeginner5 minmarkdown
- When helpful
use ML language (correlation
0
Explore
Find agent skills by outcome
119,510 skills indexed with the new KISS metadata standard.
Showing 24 of 119,510Categories: Data & Insights, Coding & Debugging, Education, Communication, Cursor-rules, General
General
PromptBeginner5 minmarkdown
- Isolate anomalies and outliers confidently
and attribute them to network mechanics where causally plausible.
0
General
PromptBeginner5 minmarkdown
- Keep the tone concise
analytical
0
General
PromptBeginner5 minmarkdown
- Highlight early signals the model would treat as predictors per network (CTR → IPM deterioration on ALN
CPI drift patterns on Mintegral
0
General
PromptBeginner5 minmarkdown
- Format-specific opportunities (e.g.
an endcard mechanic untested on ALN
0
Education
PromptBeginner5 minmarkdown
**Best Creative(s):** Explain which creative attributes correlate with strong metrics
and whether those attributes hold across all networks or are network-specific.
0
Education
PromptBeginner5 minmarkdown
**Worst Creative(s):** Explain which patterns predict failure
and flag whether the failure is universal or network-localized.
0
General
PromptBeginner5 minmarkdown
- Which are candidates for format adaptation (e.g.
recut for Google's asset ingestion
0
General
PromptBeginner5 minmarkdown
- State the performance delta (e.g.
top 1 on ALN
0
Education
PromptBeginner5 minmarkdown
- High Spend / Poor Results: Explain the inefficiency pattern and the likely network-specific ML reason (e.g.
ALN AXON fallback behavior
0
Education
PromptBeginner5 minmarkdown
- Highest CPI: Explain which signals
specific to this network
0
General
PromptBeginner5 minmarkdown
- Lowest IPM (or weakest CTR × CVR): Identify root-cause patterns through the lens of this network's audience and format behavior (e.g.
weak hook on a skip-heavy rewarded placement
0
Education
PromptBeginner5 minmarkdown
- Top Creative by Spend: Explain why this network's algo is favoring it
and whether scaling is amplifying or compressing efficiency.
0
General
PromptBeginner5 minmarkdown
Repeat the following block for each of the four networks: AppLovin
Mintegral
0
General
PromptBeginner5 minmarkdown
Your role is not to describe numbers
but to act as a performance-prediction model using structured
0
General
PromptBeginner5 minmarkdown
- Flag anomalies with ML-style reasoning (outliers
variance spikes
0
General
PromptBeginner5 minmarkdown
- Detect hidden drivers of performance (e.g.
early CTR → later IPM quality drop
0
Education
PromptBeginner5 minmarkdown
- Google UAC (ACi): Machine-learning-first
multi-format ingestion (YouTube
0
Education
PromptBeginner5 minmarkdown
- AppLovin (ALN): Operates on a closed DSP with a proprietary ML bidding stack (AXON). Heavy on playable and interactive end-cards. IPM is the primary optimization signal; CTR is secondary. Algo learns fast but punishes creative fatigue aggressively. Look for: steep IPM decay curves
install clustering by creative batch
0
General
PromptBeginner5 minmarkdown
You identify correlations
leading indicators
0
General
PromptBeginner5 minmarkdown
- Success metric (Example: ₹10
000 earned / 10 users gained)
0
General
PromptBeginner5 minmarkdown
(Example: ₹2
00
0
General
PromptBeginner5 minmarkdown
- Why it fits based on $${skills}
$${experience}
0
General
PromptBeginner5 minmarkdown
(Example: Flutter
Android
0