An adversarial autonomous coding harness (GAN + anvil) — plan → generate ↔ evaluate, sprint by sprint. A Claude Code plugin.
Skill Claude CodeCodex
Guidelines for building AI-powered features into applications. Covers tool-use agent patterns, Anthropic API integration, prompt engineering for app-internal agents, and best practices. Referenced by planner and generators. Not directly user-invocable.
Skill Claude CodeCodex
A set of rules for reproducing an administrative interface from reference screenshots with high visual accuracy.
Skill Claude CodeCodex
Evaluate existing code using the ganvil evaluation framework. Automatically determines if the project is frontend, backend, or fullstack and applies the appropriate evaluator with four-dimension scoring. Use to QA-check any existing project or codebase.
Skill Claude CodeCodex
Frontend design standards and aesthetic guidelines. Provides grading criteria for visual design quality, originality, craft, and functionality. Referenced by the planner and frontend evaluator. Not directly user-invocable.
Skill Claude CodeCodex
Generate a product specification from a brief description. Classifies the project as frontend/backend/fullstack, defines features, creates a visual design language (for frontend), and decomposes into sprints with testable acceptance criteria. Use when you only need a product spec without building the application.
Skill Claude CodeCodex
A workflow for rebuilding a working admin dashboard from reference screenshots and written specifications. It coordinates planning, code generation and checking for visual accuracy.