dx-aem-flow
Enterprise AI development platform for teams shipping on Azure DevOps and Atlassian. 75+ skills that run identically across Claude Code, GitHub Copilot CLI, and VS Code Chat — from ticket to PR, fully autonomous. Deep AEM specialization built in.
Why This Exists
Enterprise teams run complex sprints across multiple repos, multiple IDEs, and multiple team members. They need a system that handles the full lifecycle — requirements analysis, implementation planning, code generation, testing, verification, documentation, and PR creation — with governance at every step. Without re-explaining the project every session.
KAI is a structured development workflow built as a plugin system for enterprise teams. It encodes your entire sprint lifecycle — requirements, planning, execution, review, PR — into skills that orchestrate multi-agent pipelines across every major AI platform. A single command like /dx-req-all pulls the ticket from Azure DevOps or Jira, validates readiness against your DoR, distills developer requirements, researches the codebase with parallel subagents, and generates a team summary. Each skill chains specialized agents (Opus for deep review, Sonnet for execution, Haiku for lookups), gathers context from multiple sources (tickets, config, codebase, Figma designs, live AEM content), and writes structured output that the next skill picks up automatically.
What makes it different:
- Every AI platform — same 75+ skills work identically in Claude Code, GitHub Copilot CLI, and VS Code Chat. Same plugins, same config, same results — regardless of which IDE your team uses.
- Enterprise governance — DoR validation, 6-phase verification gate (compile, lint, test, secret scan, architecture review, AI code review), autonomous PR review, and branch protection. Ship with confidence.
- AEM full-flow — purpose-built AEM tooling covering Figma → component → dialog inspection → JCR content → editorial QA → browser automation → demo capture. Includes the AEM MCP server for live dialog and JCR access. The complete AEM development lifecycle, config-driven for your project.
- Config-driven, not prompt-driven — your build commands, branch names, and conventions live in one config file. Every skill reads it. No hardcoded values, no repeated instructions.
- Persistent memory between steps — each skill writes structured output to local files. The next skill picks it up automatically. Sessions can end and resume without losing context.
- Autonomous mode — the same skills that run locally also run unattended as ADO pipeline agents, triggered by webhooks. Tag a ticket, get a verified bugfix with a PR.
Install
Add the marketplace, then install the plugins you need:
# Add the marketplace (once)
/plugin marketplace add easingthemes/dx-aem-flow
# Install plugins
/plugin install dx-core@dx-aem-flow # Core workflow (all projects)
/plugin install dx-hub@dx-aem-flow # Multi-repo orchestration (optional)
/plugin install dx-aem@dx-aem-flow # AEM tools (AEM projects)
/plugin install dx-automation@dx-aem-flow # Autonomous agents (24/7 pipelines)
From a local clone:
/plugin marketplace add /path/to/dx-aem-flow
/plugin install dx-core@dx-aem-flow
Plugins
dx-core — Development Workflow
Full-stack development workflow for Azure DevOps and Jira projects: requirements gathering, implementation planning, step-by-step execution with testing and review, code review, bug fixes, and PR management.
Works with any tech stack.
dx-hub — Multi-Repo Orchestration
Hub directory management for coordinating work across multiple consumer repos — init, config, status.
dx-aem — AEM Full-Flow
The complete AEM development lifecycle: component dialog inspection, JCR content, page authoring, editorial QA with browser automation, snapshot/verify lifecycle, and demo capture. Includes the AEM MCP server for live JCR and dialog access. Purpose-built for AEM Cloud and on-premise projects.
Requires dx plugin.