Explore in MochiBot. Install in chat.Hosted workspaces and MochiBot lightweight setups include the Skills assistant. Choose a Skill and ask for installation in chat. Other OpenClaw setups can follow the first-install guide.
How to use Skills →
MOCHILAB / AI SKILL
Ad Creative Trend Review
Compare weighted performance across two declared windows and expose missing observations and confounding changes.
What it helps with
Compare weighted performance across two declared windows and expose missing observations and confounding changes.
Say it like this
Compare these creatives across the recent and baseline windows.
Flag missing days and changed audiences before interpreting falling CTR.
What you receive
Ask for a comparison_key identifying stable audience, placement and attribution definition, a date/timezone, currency and explicit reporting completeness for each ad/day. Aggregate numerators and denominators before ratios. Show review candidates and change flags, without claiming creative fatigue caused a trend.
Give the assistant your actual files or records and confirmed rules. It asks for missing facts rather than inventing records; you do not need to hand-fill JSON. Receive a traceable report and detailed review rows for download.
Scope
Descriptive supplied-export review. Ratios use weighted totals; no universal fatigue threshold, causal attribution or ad-pausing decisions.
The script reads supplied local files and creates reports without network or model calls. Your assistant still uses its configured services; this does not promise absolute privacy for a conversation. The Skill is free and needs Python3.10+. Optional AI interpretation follows your existing model service charges.
Demand and technical basis