The Agent Skills Directory

[SAFE]: The skill provides strategic and tactical guidance for optimizing product flows (signup, onboarding, and upgrade). No malicious patterns, command executions, or data exfiltration attempts were identified in either SKILL.md or references/experiments.md.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external context from .claude/product-marketing-context.md and user-provided product details. However, since the skill does not possess dangerous capabilities (such as file writing, network requests, or shell execution), this represents a standard operational surface with no identified path to exploitation.
[NO_CODE]: The skill consists entirely of Markdown instructions and reference documentation. There are no scripts, binaries, or automated tasks associated with the skill's execution environment.

product-flow-cro