Evaluates AI agent performance through comprehensive metrics, benchmarking, and systematic analysis of response quality, accuracy, and contextual understanding.

🎯

do-and-judge🎯Skill

Executes complex tasks with built-in self-evaluation, providing step-by-step reasoning and quality assessment of the generated output.

🎯

create-command🎯Skill

Generates structured CLI commands with intelligent parsing, validation, and interactive prompts for complex command-line tool development

🎯

worktrees🎯Skill

Manages Git worktrees to efficiently handle multiple branches and parallel development workflows without switching contexts

🎯

attach-review-to-pr🎯Skill

Automatically links code reviews to pull requests, streamlining collaboration and tracking feedback across GitHub repositories.

🎯

create-ideas🎯Skill

Rapidly brainstorm and generate innovative concepts across domains by leveraging structured ideation techniques and creative prompting strategies.

🎯

software-architecture🎯Skill

Designs scalable system architectures, evaluates design patterns, and provides architectural recommendations for complex software projects.

🎯

why🎯Skill

Provides deep contextual reasoning and explanation generation for complex problems, breaking down root causes and logical connections.

🎯

do-in-steps🎯Skill

Breaks down complex tasks into manageable, sequential steps with clear instructions and error handling for systematic problem-solving.