The Agent Skills Directory

[SAFE]: The skill provides legitimate developer tooling for skill creation and follows the official specification for agent skills.
[SAFE]: File system operations are constrained to path-based scaffolding and directory zipping using standard libraries (pathlib, shutil).
[SAFE]: The skill does not perform any network operations, data exfiltration, or access to sensitive system directories (e.g., .ssh, .aws).
[SAFE]: Python scripts use yaml.safe_load() for parsing configuration, preventing unsafe deserialization vulnerabilities.
[SAFE]: No prompt injection, obfuscation, or persistence mechanisms were detected.

skill-creator