The Agent Skills Directory

[SAFE]: The skill consists entirely of architectural documentation and instructions for agent behavior. It does not include any executable scripts, binaries, or network operations.
[NO_CODE]: No executable code or scripts were found in the skill package. All files are Markdown or YAML configuration.
[INDIRECT_PROMPT_INJECTION]: The skill outlines a process for analyzing codebases to provide design recommendations. While this involves reading user-provided code, the skill itself does not possess capabilities that would enable a high-impact attack such as file-writing or command execution. 1. Ingestion points: User codebase files referenced in design briefs (DESIGN-IT-TWICE.md). 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Limited to generating design recommendations and spawning sub-agents for discussion. 4. Sanitization: No specific sanitization or escaping logic is identified for user-provided codebase content.

codebase-design