The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a shell script scripts/verify.sh used for linting HTML and JSON-LD files. The script performs read-only operations using standard Unix tools like grep, awk, find, and tr. It uses python3 only to validate JSON formatting and structure without executing any external or untrusted code.
[SAFE]: The skill instructs the agent to analyze SEO metadata, structured data (JSON-LD), and robots.txt configurations. All recommendations are based on publicly documented industry standards and academic studies (e.g., Princeton GEO study).
[SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The instructions are well-scoped and emphasize hand-offs to other skills for tasks outside its primary SEO auditing purpose.

seo-geo