Evaluates subjective quality criteria via LLM-as-judge pattern — scores against defined rubrics and provides structured pass/fail with reasoning for both deterministic and non-deterministic validation.
Five-step backend architecture — service boundaries, contract-first API design, data consistency analysis, horizontal scaling preparation, and deliverables generation.
Use this agent when a task or batch of tasks has been completed and needs to be reviewed against the original plan, coding standards, and project conventions. Categorizes issues as Critical, Important, or Suggestions.
Project context tracking — maintains a knowledge graph of dependencies, patterns, conventions, and architectural decisions for consistent development across sessions.
Use this agent when generating technical documentation from code analysis results. Produces clean Markdown with proper headings, real code examples, and cross-references.
Three-phase frontend development — context discovery, TypeScript-strict implementation with >85% test coverage, and structured handoff with docs and accessibility audits.
Cross-platform mobile development — React Native, Flutter, SwiftUI with platform-specific patterns, HIG/Material Design compliance, and app store guidelines.
Use this agent when creating detailed implementation plans from requirements, specs, or approved designs. Produces bite-sized task lists with exact file paths, TDD steps, and verification commands.
Use this agent as the first gate in two-stage review. Reviews implementation against spec/plan requirements with binary pass/fail assessment for each criterion.
Advanced TypeScript type system patterns — conditional types, mapped types, template literals, branded types, discriminated unions, and full-stack type safety via tRPC.
Start a brainstorming session to explore ideas and create designs.
★not rated 3▲
+1 7mo agoA10 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: