The Agent Skills Directory

[SAFE]: The skill is composed strictly of Markdown documentation providing guidance on board game design, mechanics, and balance. It does not include any scripts, binaries, or automated tool invocations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of user-provided game designs, rules, and mechanics. While it lacks internal tools or scripts that could be exploited (e.g., file writing or network requests), the ingestion of complex, user-supplied text creates a theoretical surface for indirect prompt injection if the processing agent interprets malicious instructions embedded within the game rules.
Ingestion points: User-supplied game mechanics, resource economy descriptions, and rulebooks (SKILL.md, 'When This Skill Activates' section).
Boundary markers: None present in the instructions.
Capability inventory: None. The skill does not define any script execution or tool use.
Sanitization: None provided in the instructional text.
[SAFE]: The external links provided in the reference files (references/balance-methodology.md, references/eurogame-principles.md) are standard educational resources for game design and are not used for automated data fetching or execution.

boardgame-design