Thomas Klok Rohde

A curated collection of Claude Code plugins by Thomas Klok Rohde

Create production-ready DrawIO diagram files with comprehensive XML knowledge for flowcharts, architecture diagrams, UML, network diagrams, and more

Commands and skills for jArchi scripting: automate Archi models, views, and exports

ArchiMate enterprise architecture modeling assistance - element selection, relationships, patterns, and model quality guidance

Generate self-contained, agent-executable Execution Plans (ExecPlans) from PRD files

Create, scaffold, and configure GitHub Copilot customizations for VS Code projects, including instructions, prompts, agents, skills, hooks, and MCP integration

Analyze and improve existing Claude Code skills using research-backed SkillsBench findings — audit, score, and optimize skills for maximum effectiveness

Package standalone skills into properly structured plugins and register them in the Claude Code plugin marketplace

Create new skills, modify and improve existing skills, and measure skill performance with iterative eval-driven development loops

Write enterprise-ready, agent-executable Product Requirements Documents (PRDs) through interactive guided sessions with ambiguity tracking

Augment existing Execution Plans with agent-first CLI design requirements and project scaffolding guidance

Approximate Danske Bank's Sapphire design system using plain CSS and HTML — no @danske/sapphire-* packages required. Includes complete design tokens, 20+ component patterns, and 700+ icons.

Run isolated blackbox tests of any CLI tool — a zero-knowledge subagent explores, stress-tests, and reports bugs without reading source code

Generate enterprise-ready, agent-first CLIs from OpenAPI/Swagger specs with normalized commands, enterprise auth profiles, structured output contracts, and multi-layered validation

Discover, audit, reconcile, modify, and delete GitHub Copilot customizations across both Copilot IDE (VS Code) and Copilot CLI environments

Autonomous agent-driven optimization loop — iteratively modify an artifact, evaluate against a scalar metric, and keep improvements. Works with any domain: code performance, prompt engineering, config tuning, SQL, builds, and more.

Create architecture evaluation rubrics (profiles and overlays) conforming to the Enterprise Architecture Rubric Operational Standard (EAROS) through structured interviews with ambiguity reduction

Author and run deterministic, resumable agent workflows with checkpointflow — two skills for writing workflow YAML and running it interactively with pause/resume

Apply EAROS rubrics to architecture artifacts using the three-pass agent evaluation pattern (Extractor, Evaluator, Challenger) with optional parallel evaluators for comprehensive artifacts