multi-model
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.
来源信息
- 仓库
- lollipopkit/cc-plugins
- 最近来源活动
- 2026年3月14日 09:53
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 7
- 分支
- 0
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
文件资源管理器
2 个文件正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- 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:*)
# Multi-Model
Use the bundled runner:
`python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py"`.
## Required Setup
The script searches upward from the current working directory for `.env`.
Required variables:
- `ARENA_MODELS`
- Either `ARENA_OPENAI_BASE_URL` (single endpoint) or `ARENA_PROVIDER_<NAME>_BASE_URL` (multi-provider)
- Optional keys: `ARENA_OPENAI_API_KEY`, `ARENA_PROVIDER_<NAME>_API_KEY`
Single-endpoint example:
`ARENA_MODELS=qwen3:8b,deepseek-r1:14b`
## How to run
```bash
python3 "${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`.
## Execution Policy
1. Rotate writer model by iteration.
2. Let other models judge and score.
3. Keep the highest average-score answer as current best.
4. Return best answer, or full transcript with `--json`.
## Safety Rules
- Never print API keys or secret values from `.env`.
- Refer to model identity only as numeric IDs (`Model 0`, `Model 1`, ...).
- Do not expose provider/model names in prompts or user-facing output.
在 GitHub 查看