Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap. Use when gating publishing, production deploys, compliance or brand-sensitive content, or hallucination-prone claims before they ship.
安装
npx skills add affaan-m/ECC --skill santa-methodnpx skills add affaan-m/ECC --skill santa-method -a claude-code -gnpx skills add affaan-m/ECC --skill santa-method -a codex -ggemini skills install https://github.com/affaan-m/ECC.git --path skills/santa-methodgh skill install affaan-m/ECC santa-methodgit clone --depth 1 https://github.com/affaan-m/ECC /tmp/affaan-m__ECC
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/affaan-m__ECC/skills/santa-method ~/.claude/skills/santa-method # Claude Code
cp -R /tmp/affaan-m__ECC/skills/santa-method ~/.agents/skills/santa-method # Codex, Cursor, Gemini CLI, Copilot, OpenCode