← 返回 Skills 市场
Media.io AI Image & Video Generation API
作者
wondershare-boop
· GitHub ↗
· v1.0.14
· MIT-0
403
总下载
1
收藏
0
当前安装
14
版本数
在 OpenClaw 中安装
/install mediaio-aigc-generate
功能描述
Generate and edit AI images and videos with Media.io OpenAPI. Supports text-to-image, image-to-image, text-to-video, and image-to-video, plus task status and...
安全使用建议
This skill appears to be a straightforward wrapper around Media.io's OpenAPI and only needs your Media.io API key. Before installing: (1) verify the publisher or use a throwaway/least-privilege API key (do not reuse broad platform credentials); (2) be aware the key will be sent to https://openapi.media.io when the skill runs; (3) note the package metadata incorrectly omits the API_KEY requirement — prefer skills whose registry metadata and SKILL.md match and whose publisher/homepage are verified. If you need higher assurance, ask the publisher for a canonical homepage or an official release, or inspect the bundled c_api_doc_detail.json to confirm the exact endpoints and parameters.
功能分析
Type: OpenClaw Skill
Name: mediaio-aigc-generate
Version: 1.0.14
The skill bundle is a well-structured API router for Media.io AIGC services. The core logic in `scripts/skill_router.py` includes a security check that restricts outbound network requests exclusively to the 'openapi.media.io' domain, effectively preventing SSRF or data exfiltration to unauthorized endpoints. The documentation in `SKILL.md` and `references/mediaio-aigc-api-reference.md` is consistent with the provided API definitions in `scripts/c_api_doc_detail.json` and includes proactive security advice regarding the use of least-privilege API keys.
能力评估
Purpose & Capability
The skill name/description (Media.io image/video generation) match the included API definitions, SKILL.md, and the router code which calls https://openapi.media.io endpoints. However the registry metadata at the top of the package claims no required env vars while SKILL.md and the code clearly require an API_KEY; the package also lacks a verified homepage/publisher entry (SKILL.md points to developer.media.io as a reference).
Instruction Scope
Runtime instructions and examples only describe calling Media.io endpoints, installing the 'requests' library, and providing an API_KEY. The SKILL.md does not instruct the agent to read unrelated files or exfiltrate data. The code reads the bundled c_api_doc_detail.json and only allows requests to openapi.media.io.
Install Mechanism
No install spec or external downloads are present; the skill is instruction- and code-bundle only. All code is included in the package (no remote resources).
Credentials
The only secret the skill uses is an API_KEY (sent as X-API-KEY) which is proportionate to a cloud API wrapper. That said, the registry metadata incorrectly lists 'Required env vars: none' while SKILL.md and the code require API_KEY — this inconsistency should be resolved before trusting the package.
Persistence & Privilege
The skill does not request permanent 'always' inclusion, does not modify other skills or system-wide settings, and does not persist credentials beyond using the provided API_KEY for outbound requests to openapi.media.io.
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-aigc-generate - 安装完成后，直接呼叫该 Skill 的名称或使用
/mediaio-aigc-generate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
v1.0.14
- Cleaned up the skill metadata by removing the pip install instructions and bins from the requirements.
- All functionality and user guidance remain unchanged.
- No code changes; documentation and metadata improvement only.
v1.0.13
No changes detected in this version.
- No updates or modifications were made in this release.
v1.0.12
- The required environment variable for the API key has changed from VAP_API_KEY to API_KEY throughout documentation and code examples.
- All usage instructions, sample code, and environment setup guidance now refer to API_KEY.
- The skill's metadata was updated to reflect the new environment variable requirement.
- No core logic or API coverage changed; adjustment is purely related to credential naming for better clarity and consistency.
v1.0.11
- Task execution rule updated: Agents should now write standalone `.py` scripts for all invocations instead of using inline Python execution.
- Emphasis added: Task scripts should be kept until output is verified, then cleaned up if one-off.
- Agent execution section reworded for clarity and revised to support auditable, script-based execution.
- No API or file structure changes; this is purely a documentation and workflow update.
v1.0.9
- Added strict agent execution rules: all Python invocations must be inline; standalone temporary scripts are not allowed and must be deleted immediately if created.
- Clarified the list of files permitted to persist in the skill directory; all others must be temporary and removed after use.
- Polished the description for clarity on supported generative and editing features, and summarized supported models.
- Updated API coverage to include new endpoints such as "Google Veo 3.1 Fast."
- No code or dependency changes in this release.
v1.0.8
**Summary:**
Now includes strict agent execution rules to prevent standalone task scripts, mandates only inline or immediately-deleted temp Python code.
- Added a new "Agent Execution Rules" section: agents must NOT create standalone `.py` scripts for tasks, but use inline Python or delete any temp files after use.
- Clarified which files are allowed to persist in the skill directory.
- No code or endpoint changes; interface and API coverage remain identical.
- General documentation and description refinements for clarity.
v1.0.7
- No code or documentation changes in this release.
- Version incremented to 1.0.7 with no detected file modifications.
v1.0.6
Version 1.0.6
- Updated skill metadata structure to include homepage, environment variable, and pip install instructions for requirements.
- Improved requirements documentation, emphasizing environment variable VAP_API_KEY.
- Minor formatting changes for clarity and consistency.
- No changes to API logic, input/output formats, or functionality.
v1.0.5
- Declared VAP_API_KEY as a required secret in SKILL.md for clearer credential management.
- Added a description for VAP_API_KEY, specifying usage and where to apply for a key.
- No functionality changes; documentation updated for improved security guidance and platform compatibility.
v1.0.4
- Updated publisher information to indicate community maintenance (not an official Media.io release).
- Added a detailed pre-upload security checklist (ClawHub Security Scan) for safer publishing.
- Clarified environment variable usage and improved example import paths for consistency.
- No functional or code changes; documentation only.
v1.0.3
- Updated API key environment variable from MEDIAIO_API_KEY to VAP_API_KEY for all usage and documentation.
- Clarified credential requirements and loading instructions.
- Adjusted all usage examples and environment setup guidance to match the new key variable.
- No functional or file changes to the skill logic.
v1.0.2
- Added a new "Trust and Credential Notes" section detailing the publisher, official sources, target API domain, credential usage, and security recommendations.
- Clarified credential handling and security best practices for using MEDIAIO_API_KEY.
- No changes to functionality or code; documentation improvements only.
v1.0.1
- Added license, publisher, homepage, and required environment variable metadata to the skill specification.
- Updated the API list in documentation to clarify and uniquely name all text-to-video endpoints, improving clarity and invocation guidance.
- Clarified that API names are now unique and the router will validate duplicates at startup.
- Improved and shortened the skill description for clarity, listing supported model names and main capabilities.
- No functional or code changes; documentation and metadata updates only.
v1.0.0
- Initial release of the unified MediaIO AIGC API router skill.
- Supports credits queries, task status lookup, and content generation (text-to-image, image-to-image, image-to-video, text-to-video) via a single entry point.
- Covers 24 MediaIO API endpoints, including models like Imagen 4, Nano Banana, Seedream, Wan, Kling, Vidu, Hailuo, and Veo.
- Provides polling workflow for asynchronous task result retrieval.
- Includes example Python usage and environment setup guidance.
元数据
常见问题
Media.io AI Image & Video Generation API 是什么？
Generate and edit AI images and videos with Media.io OpenAPI. Supports text-to-image, image-to-image, text-to-video, and image-to-video, plus task status and... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 403 次。
如何安装 Media.io AI Image & Video Generation API？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mediaio-aigc-generate」即可一键安装，无需额外配置。
Media.io AI Image & Video Generation API 是免费的吗？
是的，Media.io AI Image & Video Generation API 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Media.io AI Image & Video Generation API 支持哪些平台？
Media.io AI Image & Video Generation 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 Media.io AI Image & Video Generation API？
由 wondershare-boop（@wondershare-boop）开发并维护，当前版本 v1.0.14。
推荐 Skills