Model Recommender
An intelligent model selection assistant that dynamically analyzes your OpenCLAW configuration and recommends the most suitable AI model for your specific task.
Overview
This skill reads your local OpenCLAW configuration to determine available models, then applies keyword-based capability matching to provide intelligent recommendations based on the task at hand.
Supported Models
Global Providers
| Provider | Models |
|---|
| OpenAI | gpt-5-pro, gpt-4o, gpt-4o-mini, o3, o1 |
| Anthropic Claude |
claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5 |
| Google Gemini | gemini-3.1-pro, gemini-3.1-flash, gemini-2.5-flash |
| Mistral | mistral-large, mistral-small |
| xAI | grok-4.20-beta, grok-4-fast |
Domestic (China) Providers
| Provider | Models |
|---|
| Alibaba Qwen | qwen3-max, qwen3-vl, qwen3.5-plus, qwen3-coder-plus |
| MiniMax |
minimax-m2.5, minimax-m2.1 |
| DeepSeek | deepseek-v3.2, deepseek-chat, deepseek-coder |
| Moonshot (Kimi) | kimi-k2.5, kimi-k2 |
| Zhipu GLM | glm-5, glm-4.7-flash, glm-4.6v |
| Baidu ERNIE | ernie-4.5-thinking, ernie-4.5-vl |
| ByteDance Seed | seed-2.0-lite, seed-2.0-mini |
Capability Mapping
The skill uses keyword-based pattern matching to infer model capabilities:
| Keyword | Capability | Primary Use Case |
|---|
INLINECODE0 , vision, image, 4v, INLINECODE4 | Vision/Multimodal | Image analysis, OCR, chart interpretation |
INLINECODE5 , coder, INLINECODE7 |
Code Generation | Programming, debugging, refactoring |
|
o1,
o3,
o4,
reasoning,
thinking | Advanced Reasoning | Mathematical reasoning, complex logic |
|
max,
pro,
premium,
large,
opus | Premium/Tier-1 | High-quality output, complex tasks |
|
mini,
small,
lite,
flash,
haiku,
nano | Lightweight | Fast response, simple tasks, cost-sensitive |
Recommendation Logic
CODEBLOCK0
Usage Examples
User: "Which model should I use for coding?"
→ Recommend: minimax-m2.5, deepseek-coder, qwen3-coder-plus
User: "I need to analyze an image"
→ Recommend: qwen3-vl, glm-4.6v, gpt-4o, gemini-1.5-pro
User: "For complex reasoning tasks"
→ Recommend: o3, claude-opus-4.6, qwen3-max, gemini-3.1-pro
Notes
- - Automatically adapts to your specific configuration
- Prioritizes models that are actually available in your setup
- Falls back gracefully when exact capability matches aren't found
- Supports both global (OpenAI, Claude, Gemini) and domestic (Chinese) model providers
技能名称: local-config-model-recommender
详细描述:
模型推荐器
一个智能模型选择助手，能够动态分析您的 OpenCLAW 配置，并为您的特定任务推荐最合适的 AI 模型。
概述
此技能读取您的本地 OpenCLAW 配置以确定可用模型，然后应用基于关键词的能力匹配，根据手头任务提供智能推荐。
支持的模型
全球提供商
| 提供商 | 模型 |
|---|
| OpenAI | gpt-5-pro, gpt-4o, gpt-4o-mini, o3, o1 |
| Anthropic Claude |
claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5 |
| Google Gemini | gemini-3.1-pro, gemini-3.1-flash, gemini-2.5-flash |
| Mistral | mistral-large, mistral-small |
| xAI | grok-4.20-beta, grok-4-fast |
国内（中国）提供商
| 提供商 | 模型 |
|---|
| 阿里通义千问 | qwen3-max, qwen3-vl, qwen3.5-plus, qwen3-coder-plus |
| MiniMax |
minimax-m2.5, minimax-m2.1 |
| 深度求索 | deepseek-v3.2, deepseek-chat, deepseek-coder |
| 月之暗面（Kimi） | kimi-k2.5, kimi-k2 |
| 智谱GLM | glm-5, glm-4.7-flash, glm-4.6v |
| 百度文心 | ernie-4.5-thinking, ernie-4.5-vl |
| 字节跳动豆包 | seed-2.0-lite, seed-2.0-mini |
能力映射
该技能使用基于关键词的模式匹配来推断模型能力：
| 关键词 | 能力 | 主要用例 |
|---|
| vl, vision, image, 4v, 4o | 视觉/多模态 | 图像分析、OCR、图表解读 |
| code, coder, codex |
代码生成 | 编程、调试、重构 |
| o1, o3, o4, reasoning, thinking | 高级推理 | 数学推理、复杂逻辑 |
| max, pro, premium, large, opus | 高级/一级 | 高质量输出、复杂任务 |
| mini, small, lite, flash, haiku, nano | 轻量级 | 快速响应、简单任务、成本敏感 |
推荐逻辑
- 1. 解析 ~/.openclaw/openclaw.json 以提取已配置的模型
- 分析用户的任务需求
- 通过关键词检测将任务与模型能力匹配
- 从可用配置中返回最佳匹配的模型
- 若未找到特定匹配，则回退到默认模型
使用示例
用户： 我应该用哪个模型来写代码？
→ 推荐： minimax-m2.5, deepseek-coder, qwen3-coder-plus
用户： 我需要分析一张图片
→ 推荐： qwen3-vl, glm-4.6v, gpt-4o, gemini-1.5-pro
用户： 对于复杂的推理任务
→ 推荐： o3, claude-opus-4.6, qwen3-max, gemini-3.1-pro
备注
- - 自动适应您的特定配置
- 优先选择您设置中实际可用的模型
- 当无法找到精确能力匹配时，优雅地回退
- 同时支持全球（OpenAI、Claude、Gemini）和国内（中国）模型提供商
