The Agent Skills Directory

[SAFE]: The skill is composed exclusively of natural language prompts designed to guide an AI agent through a scientific reasoning process. It does not perform any sensitive operations.
[NO_CODE]: There are no scripts, shell commands, or external dependencies associated with this skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided research summaries and papers. While this represents a data ingestion surface, the skill has no dangerous capabilities (such as network access or file system modification) that could be triggered by malicious content in those inputs.

hypothesis-generation