The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation providing advice on game mechanics, feedback loops, and user interface design. It does not include any scripts, configuration files, or tools that interact with the host system.
[NO_CODE]: No executable code is provided within the skill package. All mentioned integrations (e.g., raylib, gymnasium) are references to external libraries that the agent might use separately, but the skill itself does not perform installations or execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided game concepts. While this creates an ingestion surface for untrusted data, the lack of any automated capabilities (file writing, shell execution, or network access) prevents this from being a viable attack vector. The analysis shows: (1) Ingestion points: 'game concept' inputs in triggers; (2) Boundary markers: Absent; (3) Capability inventory: None; (4) Sanitization: Absent.

game-designer