Last commit on July 14, 2026·Created on June 30, 2026
Archive228/loopkit
“A collection of battle-tested skills and a minimal harness for coding agents”
Combined rank
#260
across all skills
Stars
749
7d change unavailable
Forks
130
Watchers
3
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
Loopkit provides a structured set of skills designed to standardize AI coding workflows. It helps developers using agents like Claude Code, Cursor, and Gemini CLI maintain higher output quality through specialized passes for accessibility auditing and session memory management.
The toolkit focuses on the gaps in AI-generated code, offering specific routines to catch UI accessibility failures and a machine-readable decision tracking system to preserve context across sessions.
WHO IT'S FOR
AI agent power users
standardize AI coding workflows with battle-tested skills
Frontend engineers
audit AI-generated UI for accessibility failures
Backend / infrastructure engineers
verify authorization and ownership on API endpoints
Technical leads / architects
implement adversarial verification for AI code changes
Want to install it?
Claude Plugin · Clone to Claude · Manual Copy · NPX Skills AddRepository instructions