The Agent Skills Directory

[COMMAND_EXECUTION]: The skill orchestrates complex development workflows by executing system commands such as git, gh, tmux, and timeout. The associated bash scripts are implemented with defensive programming techniques, specifically using printf %q for escaping and array-based command construction to mitigate shell injection risks.
[EXTERNAL_DOWNLOADS]: Diagnostic scripts and documentation reference official installation procedures for well-known developer tools, including OpenAI's Codex CLI and Anthropic's Claude Code, exclusively from the official NPM registry.
[SAFE]: The skill's operations are transparently documented and aligned with its primary purpose. It incorporates mandatory safety gates, such as branch requirements and explicit approval prompts, ensuring the AI agent operates under strict human supervision.

coding-router