skills.rest
ryasrk
ryasrkCOMMUNITY
Explore all skills by this author →
GitHub

agentic-engineering

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

Updated Mar 12, 2026
Search Tags:#code review#AI agents#task decomposition#agentic engineering#model routing#cost management#eval-first
One-click install
npx skills add https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion --skill agentic-engineering-ryasrk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentic-engineering
Source: https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion/tree/main/.github/skills/agentic-engineering
Command: npx skills add https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion --skill agentic-engineering-ryasrk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables AI agents to perform complex engineering tasks by providing a structured framework for execution, evaluation, and cost management.

Core Features & Use Cases

  • Eval-First Execution: Define and measure success before implementation.
  • Task Decomposition: Break down large tasks into manageable, verifiable units.
  • Model Routing: Optimize AI model usage based on task complexity and cost.
  • Use Case: Use this skill to architect a new microservice, ensuring that the design is evaluated against requirements, broken down into implementable components, and that the most cost-effective AI models are used for each stage.

Quick Start

Use the agentic-engineering skill to decompose the task of building a user authentication service into smaller, verifiable units.

Frequently Asked Questions about agentic-engineering

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

FAQPage Schema
How do I manage AI model routing costs for complex software engineering tasks?▼

Manage AI model routing costs by tracking token estimates, model usage, retries, and execution time. This enforces cost discipline by routing lower-complexity subtasks to cheaper models and reserving expensive tiers for harder operations.

What is eval-first execution in AI agent software engineering?▼

Eval-first execution in AI agent engineering defines and measures success criteria before writing implementation code. This ensures the agent's output is continuously verified against the target requirements throughout the development process.

How do I break down large software engineering tasks for AI agents?▼

Break down large software engineering tasks for AI agents through task decomposition, splitting work into manageable, verifiable units. This allows each component to be individually routed, executed, and evaluated.

What should AI code review focus on for agent-generated code?▼

AI code review for agent-generated code should focus on invariants, edge cases, error boundaries, security vulnerabilities, and hidden coupling. This ensures structural integrity beyond basic functional correctness.

Can I use this agentic engineering framework to architect a new microservice?▼

You can use this agentic engineering framework to architect a new microservice by evaluating the design against requirements, decomposing it into implementable components, and applying cost-aware model routing for each stage.

Related Skills

Explore More Software Engineering Skills→
shafibabarshafibabar
1

nfr-specification

Formalizes measurable non-functional requirements for the Ideate phase of the SDLC.

Community
Advanced
j4xiej4xie

integration-testing

Run end-to-end integration tests for API and UI interactions in the Cretas food traceability system.

Community
Advanced
sakamoto-family-smilesakamoto-family-smile

agentic-engineering

Coordinate engineering tasks with eval-first loops and tiered model routing.

Community
Advanced
richardnpaulrichardnpaul

agentic-engineering

Decompose engineering tasks into verifiable units with eval-first evaluation and tiered model routing.

Community
Advanced