The Agent Skills Directory

[SAFE]: The skill package consists entirely of Markdown-based documentation, templates, and guidelines for product discovery workflows. No executable scripts, binaries, or configuration files that trigger system actions are present.
[SAFE]: No evidence of data exfiltration or credential harvesting was found. The templates use descriptive placeholders for generic project data and explicitly recommend using test environments and dummy data for payment/PII scenarios.
[SAFE]: The instructions are clear and follow industry best practices for usability research. There are no attempts at prompt injection, safety filter bypasses, or behavior overrides.
[SAFE]: All external URLs point to legitimate project documentation or the author's upstream repository on a known platform (refoundai.com). No obfuscated or malicious links were detected.
[SAFE]: The skill does not utilize dynamic context injection (shell execution at load time) or any form of remote code execution.

usability-testing