agentic-engineering

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

2|1|Updated Feb 27, 2026

Search Tags:#decomposition #quality-assurance #risk-management #agentic #ai-workflows #model-routing #eval-first

Ready to run

npx skills add https://github.com/spideynolove/claude-code-in-action --skill agentic-engineering-spideynolove

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agentic-engineering
Source: https://github.com/spideynolove/claude-code-in-action/tree/main/29-skill-authoring/.claude/skills/agentic-engineering
Command: npx skills add https://github.com/spideynolove/claude-code-in-action --skill agentic-engineering-spideynolove

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates engineering workflows by enabling AI agents to perform implementation work while humans enforce quality and risk controls to reduce handoffs and drift.

Core Features & Use Cases

Eval-first loop with capability evaluation, regression checks, baseline capture, and delta comparison.
Task decomposition into independently verifiable units with clear done criteria and single dominant risk.
Model routing by task complexity (Haiku, Sonnet, Opus) to balance speed and safety.
Session strategy for multi-phase work and milestone-driven closure.
Review focus for AI-generated code emphasizing invariants, error handling, security, and risk management.

Quick Start

Provide an initial agentic plan to implement a small module using an eval-first approach.

Frequently Asked Questions about agentic-engineering

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

FAQPage Schema

How do I decompose multi-step software tasks for AI agents?▼

You decompose multi-step software tasks by breaking them into independently verifiable units with clear done criteria and a single dominant risk. This allows AI agents to execute implementation while humans enforce quality and risk controls to reduce drift.

What is an eval-first loop in agentic engineering?▼

An eval-first loop is a workflow that runs capability evaluation, regression checks, baseline capture, and delta comparison before implementation. It ensures AI-assisted software development maintains strict quality assurance and safety guardrails throughout the process.

How do I route AI models by task complexity in software development?▼

You route AI models by task complexity using a tiered strategy: Haiku for simple tasks, Sonnet for moderate complexity, and Opus for critical work. This balances speed and safety across modular AI-assisted software development workflows.

How do I review AI-generated code for risk management?▼

You review AI-generated code by focusing on invariants, error handling, security, and risk management. This review focus ensures the code meets strict safety guardrails and passes the quality assurance checks required by the agentic workflow.

Can I use agentic engineering for evolving production projects?▼

Yes, agentic engineering supports risk-aware production planning across evolving projects. It uses a session strategy for multi-phase work and milestone-driven closure to ensure stable, verifiable implementation as your project scales.

What is the best way to plan AI-assisted module implementation?▼

The best way to plan AI-assisted module implementation is to provide an initial agentic plan using an eval-first approach. This enforces task decomposition, tiered model routing, and strict code review from the very beginning of the workflow.