Agent Claude Code
Generates comprehensive eval reports with quality, semantic (LLM-as-Judge), accuracy, regression, and performance analysis for think-mcp tools. Use after think-mcp-tester completes.
Agent Claude Code
Generates comprehensive eval reports with quality, semantic (LLM-as-Judge), accuracy, regression, and performance analysis for think-mcp tools. Use after think-mcp-tester completes.
Agent Claude Code
Executes quality, regression, semantic, and performance evals for think-mcp tools. Use for ongoing validation and new mental model testing.
Skill Claude CodeCodex
Ensure WCAG 2.1 AA compliance in all frontend designs. Use this skill when building any user interface to guarantee visibility, contrast, keyboard navigation, and screen reader support.
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when building web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Skill Claude CodeCodex
Generate content strategy and component recommendations for landing pages. Analyzes implementations to create StoryBrand-structured pages with brand-aligned Shadcn component queries.
Skill Claude CodeCodex
Maslow AI brand tokens - colors, typography, interaction states. Use with any UI framework.
MCP server Claude CodeCodexCursor
A minimal MCP Server based on the Anthropic's "think" tool research. Runs locally from the think-mcp npm package.