← All creators

zhjai

User

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.

2 indexed · 0 Featured · 21 stars · avg score 87
View on GitHub →

Categories

AI & Automation (2)

Indexed Skills (2)

AI & Automation Solid

agent-arena

Use when complex AI agent work needs heterogeneous multi-agent debate, red teaming, evidence checking, judging, or synthesis across Codex, Claude Code, Hermes, OpenClaw, and other coding agents.

21 Updated today
zhjai
AI & Automation Solid

deliberative-analysis

Use when design analysis, experiment planning, architecture choices, research synthesis, or strategy decisions risk overconfidence, tunnel vision, path dependence, premature convergence, or shallow A/B framing.

21 Updated today
zhjai

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.