The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses strong imperative language, such as 'ABSOLUTELY MUST', 'Iron Law', and 'Creed skills override', to enforce its specific methodology. While assertive, these instructions are used to steer engineering judgment and process workflow within a workspace rather than attempting to bypass the agent's core safety filters or extract sensitive information.
[SAFE]: No network operations, external code downloads, or file system access were detected in the skill instructions. The content is purely instructional and metadata-driven.

using-creed