Menu
Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
修复, 等待 AI 代码审查评论并处理它们并不断迭代直到可以合并
Run multi-model battle with rotating writer and judge models via OpenAI-compatible endpoints. Use when users ask to battle or compare models, run multi-LLM critique, or iteratively improve an answer across models.
Recursive master-orchestration for complex multi-step tasks. Decompose work, delegate execution to sub-agents, and iterate until verified. Use when users request recursive reasoning, multi-pass refinement, or explicit plan-execute-verify loops.
This skill should be used when the user asks to "analyze a large log", "summarize a big file", "read the whole repository", "process long tool output", "avoid context window overflow", "use sub-agents for preprocessing", "add evidence with line numbers", "verify claims with locators", or mentions "TaskSpec", "SubResult", "Evidence Contract", "Context Firewall", "Map-Reduce", "FileWorker", "Aggregator", "Critic".
| name | recursive-arena |
| description | Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows. |
| allowed-tools | Read, Bash(python:*) |
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.