The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions guiding the agent to act as a 'whiteboard peer' for research tasks. It contains no scripts, shell commands, or external dependencies.
[SAFE]: No evidence of prompt injection or attempts to bypass safety filters was found. The instructions focus on maintaining a specific collaborative persona.
[SAFE]: No network operations, file system access, or credential usage were detected in the provided files.
[SAFE]: The metadata and evaluation files are consistent with the stated purpose of the skill and contain no malicious payloads.

whiteboard-peer