Publish Skill

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 purpose (image generation) matches its instructions, but there are transparency gaps and a metadata/instruction mismatch: the SKILL.md requires API keys (MINIMAX_API_KEY, OPENAI_API_KEY, STABILITY_API_KEY) while the registry metadata declares no required environment variables or primary credential and the skill has no provenance (no homepage, unknown source).

Purpose & Capability

The skill's declared purpose (text-to-image via MiniMax, OpenAI, Stability) aligns with the runtime instructions which tell users to set service API keys. However the registry metadata lists no required env vars or primary credential despite the instructions explicitly requiring MINIMAX_API_KEY, OPENAI_API_KEY, and STABILITY_API_KEY — a transparency/inconsistency issue.

Instruction Scope

SKILL.md stays within the stated purpose (generate images) and only instructs users to set API keys and send prompts. It does not instruct reading unrelated files or system state. However the instructions are high-level and vague about endpoints, how the agent calls the APIs, and how it chooses/rotates keys; that grants the agent discretion and reduces clarity about what data will be sent to external services.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is written to disk by an installer.

Credentials

Requesting API keys for image-generation services is proportionate to the task. But the registry metadata did not declare these required environment variables, and the skill's source/homepage is missing, which reduces transparency about where those keys will be sent and how they are used. The unknown provider 'MiniMax' should be verified before supplying credentials.

Persistence & Privilege

Skill does not request permanent presence (always:false) and does not indicate it will modify other skills or system config. Normal agent invocation autonomy remains (disable-model-invocation:false).

What to consider before installing

What to consider before installing: - The skill asks you to provide API keys (MINIMAX_API_KEY, OPENAI_API_KEY, STABILITY_API_KEY) in SKILL.md, but the registry metadata did not declare any required env vars—this mismatch is a transparency gap. - Only provide keys if you trust the skill author; there is no homepage or known publisher. Prefer creating limited-scope or throwaway API keys for testing. - Ask the maintainer: which endpoints are called, does the skill send prompts/attachments or metadata, and does it store logs? Confirm the provider 'MiniMax' and its privacy policy. - Avoid including sensitive personal data in prompts sent to third-party image APIs. - If you need more assurance: request the skill's exact API call implementation or a homepage/source repository before supplying secrets. - If you are uncomfortable or cannot verify the provider, do not set global environment keys; instead use per-task temporary keys or a vetted provider integration.

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