The Agent Skills Directory

[SAFE]: The analyzed files (README.md, SKILL.md, and QUICK_REFERENCE.md) contain exclusively instructional content and structured templates for scientific manuscript review. No malicious patterns or behaviors were identified in the text.\n- [NO_CODE]: This skill is composed entirely of markdown documentation and does not include any executable scripts, binaries, or system commands, significantly reducing the potential for malicious execution.\n- [PROMPT_INJECTION]: The skill instructions do not contain any patterns associated with bypassing safety guidelines, overriding agent constraints, or extracting system prompts. While the skill processes external research documents, the provided framework focuses on objective scientific critique and does not include directives to execute embedded content.

scientific-reviewer