The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses allowed-tools to restrict access to a specific marketing status command (Bash(mktg status *)). This is a restrictive configuration that limits the agent's capability to a safe, read-only status check.
[DATA_EXPOSURE]: The skill reads local brand files (brand/positioning.md, brand/audience.md, brand/voice-profile.md) to inform script generation. Access is restricted to the local project directory for the intended purpose of content creation.
[SAFE]: The skill generates structured YAML files (marketing/content-specs/*.yaml) according to a documented schema to facilitate downstream design tasks. No network exfiltration, prompt injection, or obfuscation patterns were detected.

slideshow-script