The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill follows best practices by requiring manual human approval for its recommendations.
[DATA_EXPOSURE]: The skill reads project documentation files such as README.md and ARCHITECTURE.md. This access is confined to the local filesystem and is used exclusively for generating the tool routing report.
[COMMAND_EXECUTION]: All operations described in the workflow are limited to reading and writing markdown files. No shell commands, subprocesses, or external scripts are executed.

routing