The Agent Skills Directory

[SAFE]: The skill's primary content consists of markdown-based templates and evaluation frameworks. No malicious patterns such as prompt injection, obfuscation, or data exfiltration were detected.
[NO_CODE]: There are no scripts, binaries, or automated tool invocations within the skill. The logic relies entirely on the natural language processing capabilities of the agent to fill out the provided templates.
[EXTERNAL_DOWNLOADS]: No external resources, dependencies, or remote scripts are downloaded or executed. All content is contained within the provided markdown files.

cofounder-evaluator