llm-as-judge
LLM-as-Judge
Overview
Some quality criteria are inherently subjective — tone of voice, visual aesthetics, UX feel, documentation clarity, code readability. These cannot be verified by deterministic tests. The LLM-as-judge pattern provides structured, repeatable evaluation using an LLM reviewer with defined rubrics, ensuring subjective quality is measured consistently.
Announce at start: "I'm using the llm-as-judge skill to evaluate subjective quality."
Phase 1: Determine Evaluation Method
Goal: Decide whether LLM-as-judge is the right tool.
Decision Table: LLM-as-Judge vs Deterministic Tests
More from pixel-process-ug/superkit-agents
ui-ux-pro-max
>
784frontend-ui-design
Use when designing UI components, creating component architectures, implementing responsive layouts, setting up design systems, or selecting state management solutions for frontend applications
43reverse-engineering-specs
Use when onboarding to an existing codebase that lacks specifications — exhaustively traces code paths and produces implementation-free behavioral specifications for safe refactoring, feature addition, or legacy modernization
40senior-fullstack
Use when the user needs end-to-end TypeScript development — from database schema through API layer to UI — with tRPC, Prisma, Next.js, authentication, and deployment. Triggers: full-stack feature implementation, database-to-UI pipeline, tRPC router creation, Prisma schema design, auth setup, deployment configuration.
35ux-researcher-designer
>
35clean-code
Use when the user needs code quality review, refactoring guidance, SOLID principles application, or help identifying and fixing code smells. Triggers: code smell detection, refactoring planning, naming convention review, complexity reduction, DRY analysis, error handling improvement.
35