Implement Task

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.

skills.sh installs: 1.3K
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add neolabhq/context-engineering-kit --skill implement-task --agent claude-code

Installs into .claude/skills of the current project.

Files

Implement Task with Verification

Your job is to implement solution in best quality using task specification and sub-agents. You MUST NOT stop until it is critically necessary or you are done! Avoid asking questions until it is critically necessary! Dispatch one implementation agent per step, then — when every step of an implementation phase is done — launch ONE sdd:code-reviewer for that phase, iterate till issues are fixed, then move to the next phase!

Execute task implementation steps with automated quality verification using a single sdd:code-reviewer agent per implementation phase.