Full architecture review of an implemented feature or module. Evaluates against clean design principles — single responsibility, dependency direction, layer separation, and interface quality — and produces actionable findings.
Assesses the true cost a change introduces — added complexity, new infrastructure (a database, a queue, a service), new dependencies, and ongoing operational and maintenance burden. Works on a pull request, a branch, or a described feature idea, and ends with a blunt bottom-line list of what the change costs. Asks which case to assess first.
Analyzes a module or codebase for coupling quality. Distinguishes intentional from accidental coupling, identifies problematic dependencies, and recommends concrete improvements.
Creates an Architecture Decision Record (ADR) for a significant design decision. Captures context, considered alternatives, the chosen option, and consequences — so future engineers understand why, not just what.
Saves the current agent state to HANDOFF.md so another agent can take over seamlessly. Captures completed work, open tasks, changed files, and next steps.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Custom skills for Claude Code — reusable instruction units that extend Claude's behavior for specific tasks.
Each skill lives in its own directory with a SKILL.md file containing the instructions and metadata Claude uses to determine when and how to apply it.
/plugin marketplace add janmarkuslanger/skills
Install all skills:
/plugin install janmarkuslanger-skills
Or install only what you need:
/plugin install janmarkuslanger-engineering
/plugin install janmarkuslanger-website
/create-architecture-docs
Replace create-architecture-docs with any skill name from the list below.
Note: Requires Claude Code 2.1.119 or later. Update with
npm update -g @anthropic-ai/claude-code.
| 🔧 Skill | 📝 Description |
|---|---|
| audit | Performs a comprehensive SEO & GEO audit for a given URL — technical SEO, on-page SEO, and LLM/AI-search readiness. Usage: /audit <url> |
| 🔧 Skill | 📝 Description |
|---|---|
| create-spec | Generates docs/SPEC.md — requirements, constraints, interfaces, data model, and success criteria before implementation |
| create-architecture-proposal | Generates docs/SYSTEM_DESIGN.md upfront — bounded contexts, layer strategy, architectural patterns, and quality attributes |
| create-design-proposal | Generates docs/DESIGN.md for a feature before implementation — components, interface contracts, coupling decisions, and test approach |
| create-adr | Creates an Architecture Decision Record at docs/adr/NNNN-title.md — context, alternatives considered, and consequences |
| create-architecture-docs | Analyzes the project and generates ARCHITECTURE.md covering structure, components, data flow, tech stack, and design decisions |
| create-agents-md | Analyzes the project and generates AGENTS.md — architecture, clean code rules, testing strategy, coupling, and conventions — so AI agents have clear guardrails |
| create-agent-handoff | Writes current agent state to HANDOFF.md — completed work, changed files, open tasks, and next steps — for seamless agent handover |
| create-pr | Drafts a PR title and description (what / why / how to verify, breaking changes) from the branch's commits; asks before pushing or opening |
| architecture-review | Generates docs/reviews/ARCHITECTURE_REVIEW.md — evaluates code across six dimensions: SRP, dependency direction, layer separation, interface quality, coupling, and testability |
| coupling-review | Generates docs/reviews/COUPLING_REVIEW.md — maps all dependencies, distinguishes intentional from accidental coupling, and flags issues with file-level evidence |
| testability-review | Generates docs/reviews/TESTABILITY_REVIEW.md — identifies hidden dependencies, missing seams, and untestable constructs with concrete fix recommendations |
| write-tests | Writes tests for existing code following Arrange/Act/Assert — happy path, edge cases, and error paths; mocks only at I/O boundaries |
| refactor-plan | Generates docs/REFACTOR_PLAN.md — characterization tests first, then small reversible behavior-preserving steps with verification gates |
| debug | Systematic root-cause analysis — reproduce, test hypotheses one at a time, isolate the cause with evidence, then propose a minimal fix |
| cost-review | Assesses the true cost of a PR, branch, or feature idea — added complexity, new infrastructure, dependencies, and ongoing operational/maintenance burden — ending with a blunt bottom-line of what it costs. Asks which case first |
| diff-commit | Validates the current git diff for common issues (debug code, secrets, conflict markers, build artifacts) and generates a Conventional Commits title |
npx claudepluginhub janmarkuslanger/skills --plugin janmarkuslanger-engineeringUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.