Skip to content

Claude Skills by erezweinstein5

github.com/erezweinstein5

1 skillA× 10 installs2 views

eval-layerAGenerate an evaluation layer from an agent's code, instructions, domain context, tools, and memory, using Jev or an LLM judge. Use to create agent-specific rubrics, test cases, execution checks, and reproducible judge comparisons for existing agents or Codex coding workflows.ai-agentspythonrustVotes: 0GitHub stars: 13

Claude Skills by erezweinstein5 — 1 skill, security-graded | Skills Directory