agentic-engineering-workflow
CommunityDiscipline-driven AI agent development workflow.
Software Engineering#workflow#ai#agentic#software-engineering#context-management#harness#review-loops
Authormanjunathva2018
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill provides a structured, end-to-end workflow for building software with AI agents, keeping humans in control, saturating context discipline, and maintaining tight feedback loops to reduce drift and misalignment.
Core Features & Use Cases
- Harness selection and environment discipline for reliable AI coding sessions.
- Guided iterative development with small, reviewable units and built-in cleanup passes.
- Security guardrails and risk mitigation baked into the workflow for safer AI-assisted engineering.
Quick Start
Set up a minimal end-to-end agentic workflow with a chosen harness and strict context discipline.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agentic-engineering-workflow Download link: https://github.com/manjunathva2018/urban-invention/archive/main.zip#agentic-engineering-workflow Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.