The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions (SKILL.md) and metadata. It contains no Python scripts, Node.js packages, or shell commands that could be executed at runtime.- [SAFE]: No external network requests or remote dependencies are referenced. The skill explicitly states that it requires no network access and that sensitive data should remain local or be de-identified before interacting with other tools.- [SAFE]: The core logic of the skill mandates a human-in-the-loop confirmation step ('Confirm, then execute'), ensuring that the user reviews the agent's planned actions and assumptions before work begins, which acts as a safeguard against misinterpretation and accidental execution.- [SAFE]: No obfuscated content, hardcoded credentials, or persistence mechanisms were detected in the files provided.

task-brief