skills.rest
oabdelmaksoud
oabdelmaksoudCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agentic-engineering

Decompose AI engineering tasks into verifiable units with eval-first execution.

3|1|Updated Mar 4, 2026
Search Tags:#quality control#AI development#task decomposition#agentic engineering#model routing#eval-first
One-click install
npx skills add https://github.com/oabdelmaksoud/AGI-FARM-PLUGIN --skill agentic-engineering-oabdelmaksoud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentic-engineering
Source: https://github.com/oabdelmaksoud/AGI-FARM-PLUGIN/tree/main/ecc-resources/skills/agentic-engineering
Command: npx skills add https://github.com/oabdelmaksoud/AGI-FARM-PLUGIN --skill agentic-engineering-oabdelmaksoud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines the process of engineering AI systems by enabling agents to perform most of the implementation work, with humans providing quality and risk controls.

Core Features & Use Cases

  • Eval-First Execution: Define completion criteria and measure results with evals before and after implementation.
  • Task Decomposition: Breaks down complex tasks into smaller, verifiable, agent-sized units.
  • Cost-Aware Model Routing: Selects the appropriate AI model tier (Haiku, Sonnet, Opus) based on task complexity to optimize cost and performance.
  • Use Case: An AI team can be tasked with refactoring a codebase. This skill ensures that the refactoring is broken down into manageable parts, each evaluated for correctness and security before proceeding, and uses the most cost-effective model for each sub-task.

Quick Start

Use the agentic-engineering skill to decompose the task of implementing a new user authentication module into verifiable units.

Frequently Asked Questions about agentic-engineering

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

FAQPage Schema
What is eval-first execution in AI development?▼

Task decomposition breaks complex AI development tasks into smaller, verifiable, agent-sized units. This allows agents to perform implementation work while humans provide quality and risk controls across manageable, phased execution steps.

How do I optimize AI model routing costs during agentic workflows?▼

Cost-aware model routing selects the appropriate AI model tier, such as Haiku, Sonnet, or Opus, based on task complexity. This optimizes resource utilization and cost management by matching model capabilities to specific sub-task requirements.

Can I use agentic engineering for codebase refactoring?▼

Agentic engineering supports codebase refactoring by breaking down the process into manageable parts. Each unit is evaluated for correctness and security before proceeding, ensuring structured implementation and effective risk management.

How do I implement task decomposition for complex AI development projects?▼

Task decomposition breaks complex AI development tasks into smaller, verifiable, agent-sized units. This allows agents to perform implementation work while humans provide quality and risk controls across manageable, phased execution steps.

What are the limitations of using automated agents for software engineering?▼

Automated agents require human oversight for quality and risk controls. While agents perform implementation, limitations include the need for phased execution, continuous evaluation, and structured task decomposition to ensure correctness and security.

Related Skills

Explore More Software Engineering Skills→
multiplex-aimultiplex-ai
2

agentic-engineering

Coordinate engineering tasks with eval-first execution and cost-aware model routing.

Official
Advanced
atomicinnovationatomicinnovation
30

validate-plan

Validate implementation plans against git history and test results.

Official
Advanced
AgriciDanielAgriciDaniel
204

cybersecurity

Audit codebases for vulnerabilities, secrets, dependencies, and compliance issues.

Community
Advanced
Sake-TeamSake-Team

agentic-engineering

Automates engineering workflows with AI agents via task decomposition and cost-aware model routing.

Official
Advanced