The Agent Skills Directory

[SAFE]: The skill follows secure refactoring practices, requiring explicit user authorization (e.g., 'go', 'start', 'proceed') before any code modifications are performed.- [SAFE]: Implements a phased execution model, ensuring only one set of changes is applied at a time with a full report and confirmation step required between each phase.- [SAFE]: Explicitly instructs the agent to search for and report security vulnerabilities such as hardcoded secrets, unvalidated inputs, and unsafe dynamic execution (eval) in the target project.- [SAFE]: Restricts file analysis to relevant source code and configuration files, explicitly avoiding recursive scanning of large dependency, cache, or build directories.- [SAFE]: Protects project integrity by prohibiting the addition of new dependencies, package manager changes, or new test frameworks without explicit user permission.

refactor-project