← 返回 Skills 市场
Ai Video Generation Skills
作者
mango_fish
· GitHub ↗
· v1.0.1
· MIT-0
221
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install pixwith-ai-video-generation
功能描述
AI video, image generation. 40+ models — Sora, Veo 3, Kling, Seedance, GPT Image, Hailuo, WAN. Text-to-video, image-to-video, text-to-image,image-to-image.
安全使用建议
This skill is instruction-only and coherently documents how to use Pixwith through OpenClaw's MCP. Before installing or enabling it: verify you trust the Pixwith homepage and the MCP server URL (the README suggests https://api.pixwith.ai/mcp), and only supply an API key obtained from the official Pixwith site. Understand that any images you upload may be sent to Pixwith (uploads use presigned S3 POSTs), so avoid submitting sensitive images. Confirm the MCP server you add is the official Pixwith endpoint (not a third-party or attacker-controlled URL). Finally, note that the skill will check your Pixwith credits and can create generation tasks that consume them — monitor usage and billing in your Pixwith account.
功能分析
Type: OpenClaw Skill
Name: pixwith-ai-video-generation
Version: 1.0.1
The skill bundle is a legitimate integration for the Pixwith AI media generation service (pixwith.ai) using the Model Context Protocol (MCP). The instructions in SKILL.md and the reference files (service-contract.md, model-snapshot.md) provide clear, functional guidance for the agent to perform image and video generation tasks, including model discovery, credit checks, and asynchronous task polling. No evidence of data exfiltration, malicious command execution, or prompt injection was found.
能力评估
Purpose & Capability
The name/description (text-to-image/video, image-to-video, model listing, credits) match the runtime instructions. The skill only requires MCP tool access to Pixwith endpoints (list_models, get_model_schema, upload_image, generate, get_task_result, get_credits), which are exactly the capabilities needed for the stated functionality.
Instruction Scope
SKILL.md is an instruction-only workflow that limits actions to discovering models, validating schemas, uploading reference images via presigned URLs, creating generation tasks, polling results, and checking credits. It does not instruct reading local system files, environment variables, or sending data to third-party endpoints beyond the Pixwith MCP/upload endpoints; all external calls are justified by the stated purpose.
Install Mechanism
There is no install spec and no code files; this is low-risk instruction-only content. No downloads, packages, or binaries are requested or required.
Credentials
The skill requires a Pixwith API key to be configured in the MCP server; it does not request unrelated credentials or environment variables. Asking the user to add the Api-Key in OpenClaw MCP is proportionate to interacting with the Pixwith API.
Persistence & Privilege
The skill is not always:true and does not request system-wide configuration changes. disable-model-invocation is false (normal), meaning the agent may invoke the skill autonomously per platform defaults; that is expected for an integration and is not combined with other red flags.
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 pixwith-ai-video-generation - 安装完成后，直接呼叫该 Skill 的名称或使用
/pixwith-ai-video-generation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
v1.0.1
- Skill name changed from "pixwith-media-generation" to "pixwith-ai".
- Minor formatting update to setup instructions (numbered steps now use dashes for consistency).
- No workflow, feature, or functionality changes included in this update.
v1.0.0
- Initial release of Pixwith AI video and image generation skill, supporting 40+ models.
- Enables text-to-video, image-to-video, text-to-image, and image-to-image creation via Pixwith through OpenClaw MCP.
- Guides users through first-time setup, including MCP and API key configuration.
- Handles dynamic model discovery, schema inspection, credit checking, and reference image upload according to Pixwith API requirements.
- Provides thorough workflow and guardrails to ensure reliable, schema-compliant media generation and error feedback.
元数据
常见问题
Ai Video Generation Skills 是什么？
AI video, image generation. 40+ models — Sora, Veo 3, Kling, Seedance, GPT Image, Hailuo, WAN. Text-to-video, image-to-video, text-to-image,image-to-image. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 221 次。
如何安装 Ai Video Generation Skills？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pixwith-ai-video-generation」即可一键安装，无需额外配置。
Ai Video Generation Skills 是免费的吗？
是的，Ai Video Generation Skills 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ai Video Generation Skills 支持哪些平台？
Ai Video Generation Skills 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 Ai Video Generation Skills？
由 mango_fish（@tate-kt）开发并维护，当前版本 v1.0.1。
推荐 Skills