The Agent Skills Directory

[SAFE]: The skill consists of two files: SKILL.md (which defines the instructions) and evals/evals.json (which defines the evaluation criteria). The content is purely instructional and aimed at brand strategy tasks.- [SAFE]: No external network operations, remote code downloads, or executable scripts are present in the skill package.- [SAFE]: The instructions do not contain any prompt injection patterns, obfuscation, or persistence mechanisms.- [SAFE]: The skill processes user-provided brand information but does not request access to sensitive file paths, environment variables, or credentials. Standard placeholders for user input are used during the questionnaire phase.- [SAFE]: The skill follows a predictable, two-step workflow (information gathering followed by report generation) without any dynamic code execution or privilege escalation vectors.

brand-strategy