The Agent Skills Directory

[SAFE]: The skill contains no executable code, scripts, or subprocess calls. It consists entirely of natural language instructions for the agent to follow during code analysis.
[NO_CODE]: No scripts or configuration files are included in the skill. It operates solely as an instructional prompt for reviewing repository-local content.
[SAFE]: No network activity, data exfiltration patterns, or attempts to access sensitive system files (such as credentials or SSH keys) were identified.
[SAFE]: The instructions do not attempt to bypass safety filters or override core agent guidelines; instead, they establish a specific rubric for architectural evaluation.

code-review