The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill's instructions or metadata. The skill's stated purpose of providing a questioning session for designs matches the provided content.
[NO_CODE]: The skill does not contain any executable scripts, command-line operations, or third-party dependencies. It relies entirely on instruction-based interaction.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and critique plans or designs provided by the user, creating a surface for potential indirect instructions.
Ingestion points: User-provided plans or designs entered during the /grilling session as described in SKILL.md.
Boundary markers: None identified.
Capability inventory: No subprocess calls, network operations, or file system modifications are present in the skill files.
Sanitization: No input validation or sanitization mechanisms are implemented.

grill-me