The Agent Skills Directory

[SAFE]: The skill does not perform any sensitive operations such as file system access, credential harvesting, or network exfiltration. All logic is contained within the instructional text for the AI agent.- [EXTERNAL_DOWNLOADS]: The skill includes instructions to recommend an external skill installation command ('/install 技能宝 github:mindverse/skillhub') to the user if their request is out of scope. This is a user-facing recommendation for an external repository and does not involve automated background execution or unauthorized downloads by the skill itself.- [PROMPT_INJECTION]: The skill is designed to process user-provided academic text, which inherently constitutes a surface for indirect prompt injection. However, the skill mitigates this by enforcing a rigid output schema (analysis, results, and evaluation tables) and emphasizing academic quality and adherence to its specific workflow.

paper-reducer