Muralikrishna Dudaka publishes skills that help an AI agent improve the quality of its output through iteration, most notably Review Loop, which runs a worker-and-critic cycle in which a subagent scores work from 1 to 10, gives actionable feedback, and revises until a quality gate is met. The skill is aimed at feature implementation, specification writing, and code review, where thoroughness matters more than speed.
Review Loop Skill
1 skills · 7 stars
Review Loop Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide acti…