LLM Evaluation Registry is a backend-led quality layer for AI workflows. It tracks prompts, models, reusable test cases, evaluation runs, validation results, regressions, and human review notes so AI behavior can be measured instead of guessed.
npx add-skill iamalimaybe/llm-evaluation-registryLLM Evaluation Registry is a backend-led quality layer for AI workflows. It tracks prompts, models, reusable test cases, evaluation runs, validation results, regressions, and human review notes so AI behavior can be measured instead of guessed.
My opinionated list of agent skills, commands, and rules I use for work, personal projects, and openclaw agent.
Personal collection of specialized Claude skills for Nordic nRF Connect SDK development, debugging, and workflow automation
CodexFlow is a unified desktop workbench for AI coding agents (Codex/Claude/Gemini) across Windows and WSL. Organize chats by project, run parallel tasks via Git worktrees, build rich prompts with files/@refs, and resume any session in one click.
Run Claude Code with persistent memory, skill layers, privacy hooks, and Codex-aware project integration inside your CLI
Lightweight multi-agent development workflow plugin for Claude Code
A minimal Claude Code workflow kit for spec-driven development with verification. 12 hooks + 12 commands + 8 agents + 1 skill.