メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.