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.
Reusable AI agent workflows that run 24/7 — issue triage, code cleanup, multi-repo orchestration. Import-ready for GitHub Copilot Agentic Workflows.
Claude Code skill for developing Clojure/babashka with tool integration and workflow.
Agent skill to sync X/Twitter bookmarks into Obsidian via bird CLI
codex_skill: ServerChan Turbo WeChat push notifications for Codex workflows
Enable collaborative coding in Claude Code with automated expert roles for test-driven, quality-checked mob and pair programming workflows.
CLI and MCP server for Voog CMS — manage Liquid templates, pages, products, redirects, and ecommerce settings from your terminal or any MCP client (Claude, etc.)