The Agent Skills Directory

[SAFE]: No malicious code, obfuscated content, or unauthorized network operations were detected. The skill maintains a legitimate workflow focused on design and planning.
[COMMAND_EXECUTION]: The skill instructions include standard development operations such as reading project context (files and commits) and committing design documentation to the repository via git.
[PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters, override system prompts, or manipulate agent behavior. It includes a guardrail (HARD-GATE) that prevents code implementation until a design is approved.
[EXTERNAL_DOWNLOADS]: No external resources or dependencies are downloaded or executed. The skill operates entirely within the local project environment.

brainstorming