Agentic Engineering
affaan-m/eccAgentic engineering helps you work with AI agents that handle most of the coding work. You set the rules and check the results. This method uses an eval-first loop to test before and after changes.
Tasks are broken into small independent units that take about 15 minutes each. Different AI models are chosen based on task difficulty. Easy jobs use a fast model. Hard problems use a smarter one.
You track costs and only upgrade models when needed. This keeps work fast and safe. The focus is on checking important things like security and errors, not just code style.
Add Agentic Engineering skill to your workflow
Global
mkdir -p ~/.claude/skills/agentic-engineeringProject
mkdir -p .claude/skills/agentic-engineeringSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling