The Agent Skills Directory

[SAFE]: The skill functions as a procedural guide for orchestrating a multi-agent review loop. It defines roles such as Primary Designer, Skeptic, and Constraint Guardian to ensure design robustness. The skill contains no shell commands, file system operations, or network calls.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external designs, which represents a potential attack surface for indirect prompt injection. However, because the skill lacks any high-privilege capabilities or dangerous tools (such as network access or file writing), the risk of exploitation is negligible and inherent to its primary function as a design analyzer.

multi-agent-brainstorming