Sandbox
3 repos for llm-evaluation · Claude Code · TestingClear
MrZoyo/
deslop-GPT

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

125
skillberry-ai/
cap-evolve

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

56
Q00/ouroborosHarnesses

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

5.8k