This is a task orchestrator that runs implementation agents with automated quality gates. You give it a feature file, it breaks down the work into steps, implements each one, then runs an LLM judge to verify the output meets quality thresholds before moving on. The workflow is the interesting part: it'll iterate up to three times per step trying to fix issues the judge catches, supports continuing from where you left off, and has a refine mode that detects which files you manually edited via git diff and re-verifies only the affected steps forward. You can gate critical steps with human approval or skip judges entirely if you just want fast iteration. It's opinionated about not stopping to ask questions, which works great when your task file is detailed but might frustrate you otherwise.
npx skills add https://github.com/neolabhq/context-engineering-kit --skill implement-task