菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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
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.
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 | multi-model |
| description | 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. |
| allowed-tools | Read, Bash(python:*) |
Use the bundled runner:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py".
The script searches upward from the current working directory for .env.
Required variables:
ARENA_MODELSARENA_OPENAI_BASE_URL (single endpoint) or ARENA_PROVIDER_<NAME>_BASE_URL (multi-provider)ARENA_OPENAI_API_KEY, ARENA_PROVIDER_<NAME>_API_KEYSingle-endpoint example:
ARENA_MODELS=qwen3:8b,deepseek-r1:14b
python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py" \
--prompt "<task>" --iters 5 --max-judges 3 --json
Useful flags: --out, --temperature, --max-tokens, --timeout.
--json..env.Model 0, Model 1, ...).