Analyzes your conversion lag data to determine the optimal retargeting window for each audience segment. Tells you whether your 30-day retargeting window should actually be 7 days, 14 days, or 60 days based on when people actually convert after their first visit. Platform: Meta.
npx skills add https://github.com/irinabuht12-oss/marketing-skills --skill retargeting-window-analysis
Analyzes your conversion lag data to determine the optimal retargeting window for each audience segment. Tells you whether your 30-day retargeting window should actually be 7 days, 14 days, or 60 days based on when people actually convert after their first visit.
Claude looks at time-to-conversion data across your retargeting audiences — how many days between first site visit and conversion. It segments this by traffic source, product category, and audience type to find the window where most conversions happen and where retargeting spend stops producing returns.
Your default retargeting window is 30 days for all audiences. Claude's analysis shows that 78% of conversions from Meta prospecting traffic happen within 7 days, and only 4% happen after day 14. But for Google Search traffic, conversions are spread more evenly with 35% happening between days 14-30. Claude recommends splitting your retargeting: a 7-day high-bid window for Meta traffic (where urgency is highest), a 14-day standard window for search traffic, and cutting the 14-30 day window for Meta-sourced visitors entirely — saving $1,900/month in retargeting spend on users who weren't going to convert.
This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:
https://connector.get-ryze.ai/mcpclaude mcp add ryze --transport http https://connector.get-ryze.ai/mcpSetup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Take irinabuht12-oss/retargeting-window-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.