agent-sdlc

Guide AI agent design and implementation with evidence-based lifecycle knowledge.

Updated Jul 5, 2026
One-click install
npx skills add https://github.com/kwcantrell/rusty-agent --skill agent-sdlc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-sdlc
Source: https://github.com/kwcantrell/rusty-agent/tree/main/.agents/skills/agent-sdlc
Command: npx skills add https://github.com/kwcantrell/rusty-agent --skill agent-sdlc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the complexities of building, evaluating, deploying, and operating AI agents by providing a structured knowledge base and workflow guidance.

Core Features & Use Cases

  • Comprehensive Knowledge Base: Includes 36 first-party sources on AI software development lifecycle.
  • Concept Pages: Features 23 concept pages with citation links.
  • Evaluation and Verification: Facilitates design decisions through evidence-backed knowledge.
  • Integration with Playbooks: Works alongside harness-engineering playbooks for practical applications.

Quick Start

Load the agent-sdlc skill for research or design work on agent architecture within the rusty-agent repository.

Frequently Asked Questions about agent-sdlc

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

FAQPage Schema
What is the AI agent development lifecycle and how do I structure it?

The AI agent development lifecycle encompasses building, evaluating, deploying, and operating AI software. This Skill provides a structured knowledge base of 36 first-party sources and 23 concept pages to guide your architecture design and implementation decisions.

How do I design and implement AI agents using evidence-backed guidance?

You can design AI agents using 23 concept pages with citation links that facilitate design decisions through evidence-backed knowledge. This integrates directly with practical workflows and harness-engineering playbooks for enhanced decision-making.

Does this AI agent architecture knowledge base work with existing engineering playbooks?

Yes, this knowledge base integrates with harness-engineering playbooks for practical applications. It works alongside your existing workflows to deliver evidence-based insights when researching or designing agent architecture.

What's the best way to evaluate and verify AI agent design decisions?

The best way to evaluate AI agent design decisions is leveraging a curated knowledge base of 36 first-party sources. It facilitates design decisions through evidence-backed knowledge and citation links for comprehensive verification.

Can I use this for researching agent architecture within a specific repository?

Yes, you can load this Skill for research or design work on agent architecture within the rusty-agent repository. It delivers evidence-based insights tailored to your AI software development lifecycle needs.

When do I need a structured knowledge base for AI software deployment?

You need a structured knowledge base for AI software deployment when addressing the complexities of building, evaluating, deploying, and operating AI agents. It provides workflow guidance and evidence-based insights to navigate these challenges effectively.