← 返回 Skills 市场
Text to Image API
作者
wondershare-boop
· GitHub ↗
· v1.0.2
· MIT-0
159
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install mediaio-text-to-image-api
功能描述
Generate AI images from text descriptions using Media.io OpenAPI. Provide a text prompt and receive a high-quality AI-generated image. Supports multiple mode...
安全使用建议
This skill is internally consistent with a Media.io text-to-image integration, but do two quick checks before installing: (1) Confirm the SKILL.md requirement for API_KEY is accurate — the registry metadata currently omits it (likely an oversight). (2) Only provide a Media.io API key you control and trust; the key will be sent as X-API-KEY to https://openapi.media.io. If possible, use a key with limited scope/credits for testing. Review the included c_api_doc_detail.json to verify endpoints match Media.io documentation and monitor network usage when first using the skill. If you don't recognize the skill owner, treat the API key as sensitive and consider creating a dedicated test key rather than reusing a high-privilege/production key.
功能分析
Type: OpenClaw Skill
Name: mediaio-text-to-image-api
Version: 1.0.2
The skill provides a legitimate interface for the Media.io Text-to-Image API. The implementation in `scripts/skill_router.py` includes a security check that restricts outbound network requests specifically to the `openapi.media.io` domain, effectively preventing unauthorized data exfiltration or SSRF. All files, including the API definitions in `scripts/c_api_doc_detail.json` and instructions in `SKILL.md`, align with the stated purpose of image generation without any evidence of malicious intent or hidden backdoors.
能力评估
Purpose & Capability
Name, description, README examples, JSON API manifest, and code all consistently target Media.io text-to-image endpoints. The only mismatch is registry metadata that lists no required env vars while SKILL.md (and the code) require an API_KEY; otherwise requested capabilities align with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to set API_KEY, install the 'requests' package, and call Media.io endpoints. The instructions and included code only reference the shipped c_api_doc_detail.json and the API host; they do not instruct reading unrelated files or exfiltrating arbitrary data.
Install Mechanism
No install spec is provided (instruction-only), and SKILL.md recommends 'pip install requests' — a reasonable, low-risk dependency. No downloads from arbitrary URLs or archive extraction are present.
Credentials
Functionally the skill only needs a single Media.io API key (X-API-KEY), which is proportional. However, registry metadata shows 'required env vars: none' and 'primary credential: none' while SKILL.md and the code require API_KEY. This inconsistency should be resolved before trusting the skill.
Persistence & Privilege
The skill does not request persistent 'always' inclusion, does not modify other skills or system-wide settings, and does not declare config paths. It only reads the included JSON doc and an API_KEY from environment (or passed argument).
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install mediaio-text-to-image-api - 安装完成后，直接呼叫该 Skill 的名称或使用
/mediaio-text-to-image-api触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
- Added homepage field to metadata, linking to https://developer.media.io/
- No functional or behavioral changes to the skill’s logic or usage.
v1.0.1
- No user-facing changes in this release.
- Version update with no detected modifications to documentation or features.
v1.0.0
- Initial release of the MediaIO Text to Image API skill.
- Generate high-quality AI images from text prompts using Media.io's OpenAPI (supports models like Imagen 4 and Soul Character).
- Includes API usage documentation, environment variable setup, and code examples.
- Supports multiple image aspect ratios and provides detailed guidance and error handling.
- Requires a Media.io API key for access.
元数据
常见问题
Text to Image API 是什么？
Generate AI images from text descriptions using Media.io OpenAPI. Provide a text prompt and receive a high-quality AI-generated image. Supports multiple mode... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 159 次。
如何安装 Text to Image API？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mediaio-text-to-image-api」即可一键安装，无需额外配置。
Text to Image API 是免费的吗？
是的，Text to Image API 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text to Image API 支持哪些平台？
Text to Image API 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Text to Image API？
由 wondershare-boop（@wondershare-boop）开发并维护，当前版本 v1.0.2。
推荐 Skills