The Agent Skills Directory

[SAFE]: The skill's workflow is centered around analyzing local project files, specifically transcript.json, and using domain-specific tools like probe and transcribe to perform its tasks.
[SAFE]: No network communication, external data exfiltration, or credential harvesting patterns were detected in the instructions or the associated test script.
[SAFE]: The skill does not attempt to execute arbitrary shell commands or perform remote code execution; its operations are restricted to the provided candidate management tools.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found within the skill's content or metadata.
[SAFE]: The test file uses the standard vitest framework to verify instructional defaults, which is a benign and expected development practice.

shorts-from-longform