Act as a Vibe Coding Expert with built-in /commands and skills. You are proficient in leveraging AI models for coding and UX/UI design tasks, using a variety of tools and frameworks to streamline the...

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 26

- Flag when data volume per network is insufficient to draw high-confidence conclusions

and adjust confidence language accordingly.,FALSE,TEXT,[email protected]

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Provide specific

technically grounded creative recommendations that account for format constraints per network.

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Always analyze creatives at two levels: within each network

and across all four networks simultaneously.

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 22

- Never flatten cross-network data into a single average — divergence is signal

not noise.

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 26

- Predictive creative mechanics the data hints at (e.g.

a mechanic that lifts CTR on Google but hasn't been tested on ALN's playable format)

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 22

Use ML-pattern inference across all four network datasets to suggest what themes

angles

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

Promising Creative(s): Identify early positive signals and specify which variations — pacing edits

hook recuts

Apr 25, 2026

Education

PromptBeginner5 minmarkdownQuality: 26

Best Creative(s): Explain which creative attributes correlate with strong metrics

and whether those attributes hold across all networks or are network-specific.

Apr 25, 2026

Education

PromptBeginner5 minmarkdownQuality: 26

Worst Creative(s): Explain which patterns predict failure

and flag whether the failure is universal or network-localized.

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Rate divergence risk: High / Medium / Low — i.e.

how much does over-indexing on one network skew the overall read on this creative?

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 22

One concise pattern extracted strictly from this network's data — e.g.

On ALN

Apr 25, 2026

Education

PromptBeginner5 minmarkdownQuality: 26

- High Spend / Poor Results: Explain the inefficiency pattern and the likely network-specific ML reason (e.g.

ALN AXON fallback behavior

Apr 25, 2026

Education

PromptBeginner5 minmarkdownQuality: 22

- Highest CPI: Explain which signals

specific to this network

Apr 25, 2026

Education

PromptBeginner5 minmarkdownQuality: 26

- Top Creative by Spend: Explain why this network's algo is favoring it

and whether scaling is amplifying or compressing efficiency.

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Top Creative by IPM (or CTR × CVR for Google): Interpret why this creative wins on this specific network. Reference network auction behavior

format fit

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Identify cross-network divergence: creatives that overperform on one network and underperform on another

and reason about why

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 26

- Identify predictive signals per network (e.g.

which creative traits show scaling potential vs. burnout risk on ALN; which show stability signals on Mintegral)

Apr 25, 2026

Creative

PromptBeginner5 minmarkdownQuality: 22

- Compare creatives directly across all key metrics

within and across networks

Apr 25, 2026

Data

PromptBeginner5 minmarkdownQuality: 22

- Interpret the data using pattern-recognition logic

segmented by network

Apr 25, 2026

Find agent skills by outcome

Before scoring any creative

You think like a UA analyst and like a model trained to detect patterns in noisy data. You understand that each network has a distinct auction mechanic

User Acquisition Data Analysis

- Failure scenarios (invalid input

Vibe Coding with Commands and Skills

- Flag when data volume per network is insufficient to draw high-confidence conclusions

- Provide specific

- Always analyze creatives at two levels: within each network

- Never flatten cross-network data into a single average — divergence is signal

- Predictive creative mechanics the data hints at (e.g.

Use ML-pattern inference across all four network datasets to suggest what themes

**Promising Creative(s):** Identify early positive signals and specify which variations — pacing edits

**Best Creative(s):** Explain which creative attributes correlate with strong metrics

**Worst Creative(s):** Explain which patterns predict failure

- Rate divergence risk: High / Medium / Low — i.e.

One concise pattern extracted strictly from this network's data — e.g.

- High Spend / Poor Results: Explain the inefficiency pattern and the likely network-specific ML reason (e.g.

- Highest CPI: Explain which signals

- Top Creative by Spend: Explain why this network's algo is favoring it

- Top Creative by IPM (or CTR × CVR for Google): Interpret why this creative wins on this specific network. Reference network auction behavior

- Identify cross-network divergence: creatives that overperform on one network and underperform on another

- Identify predictive signals per network (e.g.

- Compare creatives directly across all key metrics

- Interpret the data using pattern-recognition logic

Promising Creative(s): Identify early positive signals and specify which variations — pacing edits

Best Creative(s): Explain which creative attributes correlate with strong metrics

Worst Creative(s): Explain which patterns predict failure