Back to directory

ArcKit

A Claude Code plugin toolkit for enterprise architects that turns architecture governance into structured, AI-assisted workflows for strategy, risk, business cases, requirements, data modeling and vendor selection.

ArcKit

ArcKit is a toolkit that walks an enterprise architect through structured strategy, design, delivery and assurance workflows instead of scattered documents, using an AI coding assistant to draft each artefact. Its workflows cover establishing architecture principles, analyzing stakeholder drivers, HM Treasury-style risk and business case justification, requirements documents, data modeling with GDPR considerations, build-versus-buy technology research, Wardley mapping, Mermaid architecture diagrams, vendor RFP management, formal design reviews and requirements traceability, with inline citations back to source documents.

It explicitly produces draft artefacts for a qualified person to review, and states that it does not give legal, regulatory, clinical or security advice.

It installs as a Claude Code plugin from a dedicated marketplace, which hosts a core plugin plus regional, sector and framework-specific overlays such as TOGAF ADM and AI agent architecture, each requiring the core plugin to be installed first.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.