Reflect

This is an automated reflection layer that critiques Claude's previous response before you see it. It runs a self-evaluation checklist covering completeness, correctness, dependencies, and fact-checking. The approach is interesting: it uses an aggressive "ruthless gatekeeper" persona to force stricter scrutiny, with complexity triage so simple edits get a quick pass while architecture changes trigger deep analysis requiring 4.5/5.0 confidence. The dependency verification checks are solid, making sure nothing gets removed that's still referenced elsewhere. Worth noting it can add latency to every response, and the overwrought "you will be killed" framing is театральный but the underlying checklist is genuinely useful for catching mistakes in complex tasks.

Install to Claude Code

npx -y skills add neolabhq/context-engineering-kit --skill reflect --agent claude-code