Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From recursive-reasoning
Orchestrates recursive outer-loop refinement with multi-model arena battles each round to iteratively improve task outputs. Use for recursive arena, multi-LLM consensus with refinement, or model-battle workflows.
npx claudepluginhub lollipopkit/cc-plugins --plugin recursive-reasoningHow this skill is triggered — by the user, by Claude, or both
Slash command
/recursive-reasoning:recursive-arenaThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use the orchestrator:
Orchestrates parallel analysis of coding problems across AI models (Claude, GPT, Gemini, Grok) via CLI tools or APIs, collects recommendations, and synthesizes optimal solution.
Runs 3 AI models in parallel (gpt-5.2-pro, gemini-3-pro-preview, claude-opus-4-5-20251101) for diverse perspectives on code queries. Invoke via /ask-council or auto-activates.
Multi-LLM deliberation with three phases: independent responses, anonymized ranking, chairman synthesis. Supports OpenAI, Anthropic, Fireworks, OpenRouter, or custom endpoints. For high-stakes reviews, plan critique, or consensus-building.
Share bugs, ideas, or general feedback.
Use the orchestrator:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py".
python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py" \
--prompt "<task>" --iters 4 --arena-iters 3 --json
Common flags: --max-judges, --temperature, --max-tokens, --timeout.
For each outer iteration:
multi-model to generate a best candidate.Reuses multi-model .env configuration:
ARENA_MODELSARENA_OPENAI_BASE_URL or ARENA_PROVIDER_<NAME>_BASE_URLARENA_OPENAI_API_KEY, ARENA_PROVIDER_<NAME>_API_KEY)Optional orchestration env:
RLM_ARENA_ARENA_ITERS default inner arena iterationsRLM_ARENA_MAX_JUDGES default judge capiterationwinner_model_id (numeric ID only)avg_judge_scorerefinement_applied.env.