Stats
Actions
Tags
From multi-model-debate
Resume an interrupted multi-model debate from the last completed round. Use when the user invokes /debate:resume to continue a previously started debate.
How this skill is triggered — by the user, by Claude, or both
Slash command
/multi-model-debate:debate-resumeThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Resume an interrupted multi-model debate from its last completed checkpoint.
Resume an interrupted multi-model debate from its last completed checkpoint.
ls -1dt .debate/*/ 2>/dev/null | head -1 || echo "No debates found"cat $(ls -1t .debate/*/state.json 2>/dev/null | head -1) 2>/dev/null || echo "No active debate state"Locate debate state:
debate-dir argument provided, use that path directlyValidate state:
"completed" (if completed, inform user and stop)lastCompletedPhase and currentRoundResume from next phase:
Execute the debate-orchestration skill with resume parameters:
/debate:resume
/debate:resume .debate/20260315-143022-rest-vs-graphql
npx claudepluginhub jaebit/claudemate --plugin multi-model-debateOrchestrates structured multi-provider AI debates between Claude and available advisors (Gemini, Codex, etc.) for critical decisions. Dispatches real providers via orchestrate.sh for diverse perspectives.
Orchestrates structured multi-round adversarial debates with Pro/Contra agents and judge verdict. Supports binary/tetralemma/polarity modes, brief format, and user-joining roles.
Orchestrates multi-agent debates with 2-5 dynamic agents in Challenge (select best variant), Strategy (deep analysis with proposals), or Critic (find weaknesses) modes. Triggers on debate, challenge, compare, critique prompts.