gauntlet
CommunityGAN-inspired UI refinement loop for BURNED
Design & Creative#autonomy#playwright#automated-testing#scorecard#design-improvement#gauntlet#ui-evaluation
Authormbriggsy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Orchestrates an autonomous design-improvement cycle by splitting evaluation and generation to improve a UI, ensuring critique quality gates are met before code changes.
Core Features & Use Cases
- Separate evaluator and generator to produce honest, high-signal feedback.
- Structured scoring via a 4-criteria rubric and a formal scorecard.
- One coherent improvement per cycle with iteration logging and changelog updates.
- Works against a running UI via Playwright-based exploration and screenshot capture.
- Logs results and top issues for planning and traceability.
Quick Start
Trigger the gauntlet on the current UI to start an evaluation, scoring, and a targeted improvement.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: gauntlet Download link: https://github.com/mbriggsy/ai-learning-journey/archive/main.zip#gauntlet Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.