image-config

Community

Unified image config and model control

AuthorAcosmi
Version1.0.0
Installs0

System Documentation

What problem does it solve?

图像理解配置管理:统一读取、更新、验证和枚举图像模型,确保在图像分析任务中拥有一致且可控的配置。

Core Features & Use Cases

  • 管理图像理解配置:通过 Gateway action 执行 get、set、test、models、ollama_models 等操作,确保对图像模型和相关参数的可追溯控制。
  • 字段级配置与安全性:支持 provider、model、baseUrl、apiKey、prompt、maxTokens 等字段,并通过受控的工作流确保安全与一致性。
  • Use Case: 当需要在多模型环境中切换 Ollama/OpenAI 模型、调整提示词或连接设置时,快速读取当前配置、验证连通性并应用新的配置。

Quick Start

通过 image_config(action="get") 读取当前配置,并在需要时通过 image_config(action="models", provider="openai") 查看可用模型,然后通过 image_config(action="set", baseHash="<最新hash>", provider="openai", model="your-model", baseUrl="https://api.openai.com") 更新配置。

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: image-config
Download link: https://github.com/Acosmi/CrabClaw/archive/main.zip#image-config

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.