通用文生图

通用文生图技能。使用 MiniMax、OpenAI、DALL-E、Stability 等模型生成图片。用户需要配置自己的 API Key（MINIMAX_API_KEY、OPENAI_API_KEY 等）。当用户需要生成图片、AI绘图时使用此技能。

Security Scan

The skill's behavior (asking you to provide multiple provider API keys) matches an image-generation purpose, but the package metadata does not declare those required credentials and the runtime instructions are vague — this mismatch and lack of provenance merit caution.

Purpose & Capability

The SKILL.md clearly describes an image-generation skill that uses Minimax, OpenAI (DALL·E), and Stability — requiring corresponding API keys. However, the registry metadata lists no required environment variables or primary credential. That mismatch is an incoherence between the claimed purpose and the declared requirements.

Instruction Scope

Runtime instructions are simple: tell the agent what to draw and set one of MINIMAX_API_KEY, OPENAI_API_KEY, or STABILITY_API_KEY. The instructions do not ask the agent to read unrelated files or credentials. They are, however, fairly high-level and vague about how API calls are made (no endpoint, no rate or billing guidance), giving the agent broad discretion in implementation.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is downloaded or written to disk by the skill itself.

Credentials

The SKILL.md instructs users to set MINIMAX_API_KEY, OPENAI_API_KEY, and/or STABILITY_API_KEY. Requesting those keys is proportionate for a multi-provider image generator, but the registry metadata does not declare any required env vars or a primary credential — the omission makes it unclear what secrets the platform will ask the agent to read at runtime. Users should treat any request for API keys as sensitive.

Persistence & Privilege

The skill does not request always:true and is user-invocable only. There is no install-time persistence or cross-skill configuration indicated.

What to consider before installing

This skill appears to be a straightforward multi-provider image generator, but the package metadata omits the API keys that the SKILL.md asks for — a mismatch you should not ignore. Before installing: (1) verify the skill's source or author (there's no homepage or repo listed); (2) only provide API keys with minimal scope and billing limits (create separate keys for this skill if possible); (3) avoid pasting long-lived master keys—use scoped/limited keys or tokens; (4) ask the publisher for clarification or an updated registry manifest that declares required env vars; (5) monitor usage/billing after first use in case of unexpected API calls. If you cannot verify the source or cannot create limited-scope keys, consider not installing or running this skill.

通用文生图技能 (xiaoxia-image-gen)

支持多种文生图模型，用户可根据需要配置不同的 API Key。

支持的模型

模型	环境变量	说明
MiniMax image-01	MINIMAX_API_KEY	推荐，性价比高
OpenAI DALL-E 3	OPENAI_API_KEY	质量高
Stability AI	STABILITY_API_KEY	写实风格

使用方法

1. 配置 API Key

根据你想使用的模型，设置对应的环境变量：

# MiniMax (推荐)
set MINIMAX_API_KEY=sk-cp-xxxxx

# OpenAI
set OPENAI_API_KEY=sk-xxxxx

# Stability AI
set STABILITY_API_KEY=sk-xxxxx

2. 生成图片

在 OpenClaw 中，直接告诉我想生成什么图片，例如：

• "帮我生成一只可爱的小龙虾"
• "画一幅日落风景图"

示例提示词

• 可爱小龙虾：cute cartoon lobster mascot, kawaii style, orange color, big eyes
• 风景：beautiful sunset over ocean, golden hour, photorealistic
• 人物：portrait of a young woman, natural lighting, professional photography

技术实现

技能会根据用户配置的 API Key 自动选择可用的模型。优先顺序：MiniMax > OpenAI > Stability。

---

🦞 虾虾团队出品