Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents perform most implementation work and humans enforce quality and risk controls.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/affaan-m/everything-claude-code/main/.kiro/skills/agentic-engineering/SKILL.mdRegistry
github (via claudemarketplaces.com)