The Agent Skills Directory

[SAFE]: The skill is composed exclusively of markdown documentation and instructional prompts. It does not include any Python or Node.js scripts, binary executables, or environment configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill suggests an ingestion point for external data by instructing the agent to source "random stimulus" from sources such as "a URL the user has open." While this introduces an indirect prompt injection surface, the risk is mitigated by the instruction to only extract a noun or concept for creative use, and the absence of any hardcoded tools to automate this fetch.
[SAFE]: All external links target trusted or well-known academic and informational domains, including Wikipedia, arXiv, and official methodology sites, for the purpose of citing the history and theory of lateral thinking.

generative-thinking