The Agent Skills Directory

[SAFE]: The skill outlines a legitimate research workflow involving query decomposition, multi-source searching, source evaluation, and synthesis. It utilizes platform-provided tools like agent-browser, pubmed-search, and multi-search-engine for their intended purposes. The analysis found no evidence of obfuscation, hardcoded credentials, unauthorized command execution, or malicious persistence mechanisms. The skill also includes specific guidelines for medical research, emphasizing evidence hierarchy and safety, which aligns with best practices for informative agents.

deep-research