What problem does it solve? Recurring marketing work — weekly SEO scans, ad-fatigue checks, churn watches — gets forgotten or done inconsistently when handled manually. This Skill turns those tasks into repeatable loops an AI agent runs on a schedule, each with a defined trigger, self-check, state handling, and stop condition. ## Core Features & Use Cases - Loop catalog: 43 ready-to-adapt loop specs covering SEO, paid ads, social, activation, retention, revenue, and referrals, each defined with a nine-part anatomy (cadence, action condition, self-check, state/idempotency, stop condition, and more). - Guardrails and compliance: A two-tier action model that keeps drafting autonomous while gating anything that spends money, sends messages, or publishes behind human approval, plus CAN-SPAM/GDPR/FTC rules and a kill switch. - State and scheduling guidance: Patterns for durable loop state (cursors, dedupe keys, cooldowns) and scheduling options including cron, Claude Code primitives, or manual cadence. - Use Case: A B2B SaaS team wants a weekly SEO watch. The Skill selects the keyword-gap and ranking-drop loops from the catalog, sets a weekly cadence matched to how slowly rankings move, defines dedupe state so gaps aren't re-briefed, and stages content briefs for human review. ## Quick Start Ask the agent to set up a weekly marketing loop that watches your SEO rankings and stages recommended actions for review.
