The Agent Skills Directory

[SAFE]: The skill is entirely instructional and data-driven, providing checklists, workflows, and cataloged references for directory submissions. All logic is focused on legitimate marketing activities.
[COMMAND_EXECUTION]: The skill contains a curl command (curl -sIL [URL] | grep -i rel=) intended for verifying HTTP headers (specifically dofollow status) of public URLs. This is a common and safe diagnostic use of the tool within the context of SEO.
[EXTERNAL_DOWNLOADS]: The skill references a vast collection of third-party domains in references/directory-list.md. These are well-known technology directories (Product Hunt, G2, Capterra) or major social/developer platforms (GitHub, Substack, LinkedIn). These references are necessary for the skill's primary purpose and do not represent a security risk.
[PROMPT_INJECTION]: Instructions include internal consistency rules (e.g., "Three Hard Rules") to ensure high-quality output. There are no attempts to override the AI agent's core safety guidelines or underlying system instructions.

directory-submissions