The Agent Skills Directory

[SAFE]: The skill provides strategic guidelines for designing cancel flows, dunning sequences, and churn prediction models. All content is educational or instructional, with no scripts or system-level commands identified.- [SAFE]: The skill mentions reading local context files like .agents/product-marketing-context.md to personalize advice. While this constitutes an ingestion surface for external data, the skill possesses no exploitable capabilities (such as file-writing, code execution, or network exfiltration) that would allow for indirect prompt injection attacks.- [SAFE]: References to third-party services like Stripe, PostHog, and Customer.io are provided for implementation guidance. These are well-known technology services and are documented neutrally for their intended purpose.

churn-prevention