skills.rest
YosefHayim
YosefHayimCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agentic-engineering

Decompose software tasks into agent-sized units with eval-first execution.

Updated Aug 23, 2026
Search Tags:#code generation#AI development#evaluations#task decomposition#agentic engineering#model routing
One-click install
npx skills add https://github.com/YosefHayim/Template --skill agentic-engineering-yosefhayim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentic-engineering
Source: https://github.com/YosefHayim/Template/tree/main/.cursor/skills/agentic-engineering
Command: npx skills add https://github.com/YosefHayim/Template --skill agentic-engineering-yosefhayim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines software development by leveraging AI agents for implementation, guided by human oversight for quality and risk management.

Core Features & Use Cases

  • Eval-First Development: Enforces defining completion criteria and running evaluations before and after implementation.
  • Task Decomposition: Breaks down complex tasks into smaller, manageable, and verifiable units.
  • Model Tier Routing: Intelligently selects the appropriate AI model (Haiku, Sonnet, Opus) based on task complexity.
  • Use Case: Use this skill to refactor a legacy codebase by first defining success metrics, decomposing the refactoring into small, testable units, and then having the agent implement the changes, followed by re-evaluation.

Quick Start

Use the agentic-engineering skill to refactor the user authentication module according to the defined evals.

Frequently Asked Questions about agentic-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement AI-driven engineering workflows with human oversight?▼

AI agentic engineering streamlines software development by enforcing eval-first execution, decomposing tasks into verifiable units, routing models by complexity, and measuring outcomes with evals before and after implementation.

How do I break down complex software development tasks for AI agents?▼

Task decomposition breaks down complex tasks into smaller, manageable, and verifiable agent-sized units, allowing the AI agentic engineer to implement changes incrementally while maintaining human quality and risk controls.

How does cost-aware model routing work for AI code generation?▼

Cost-aware model routing intelligently selects the appropriate AI model tier—Haiku, Sonnet, or Opus—based on task complexity, optimizing resource allocation for AI code generation and agentic engineering workflows.

What is eval-first development and when do I need it for refactoring?▼

Eval-first development enforces defining completion criteria and running evaluations before and after implementation. It is needed when refactoring a legacy codebase to ensure changes are measured against predefined success metrics.

Can I use AI agentic engineering to refactor a legacy codebase?▼

Yes, you can refactor a legacy codebase by defining success metrics, decomposing the refactoring into small testable units, having the AI agent implement changes, and then re-evaluating the results against the initial criteria.

Related Skills

Explore More Software Engineering Skills→
oxgeneraloxgeneral
134

orch

Coordinate teams of AI agents for parallel codebase tasks.

Community
Advanced
paxlabs-incpaxlabs-inc
7

spike

Prototype and test technical feasibility through disposable experiments.

Community
Intermediate
agentmattersagentmatters
3

agentic-engineering

Coordinates agent missions with prioritized workflows, adaptive escalation, and integrated guardrails for efficient task completion.

Official
Advanced
EwallywEwallyw

writing-plans

Develop detailed implementation plans for multi-step engineering tasks.

Community
Intermediate