The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions designed to guide an AI agent through a code review process. It does not attempt to execute shell commands, perform network operations, or access sensitive files. The configuration disable-model-invocation: true acts as a security restriction by limiting tool use. While the skill is designed to analyze external code changes (an indirect prompt injection surface), the absence of capabilities to write files or communicate externally minimizes potential risks associated with untrusted data processing.

thermo-nuclear-code-quality-review