← 返回 Skills 市场
Ai Image Generation Skills
作者
mango_fish
· GitHub ↗
· v1.0.1
· MIT-0
227
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install pixwith-ai-image-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 an instruction-only connector for Pixwith and appears internally consistent. Before installing: (1) confirm the MCP endpoint URL (https://api.pixwith.ai/mcp) is the official Pixwith endpoint you expect; (2) create a Pixwith API key with minimal privileges and add it to your OpenClaw MCP config (do not paste your key into chat); (3) be mindful when uploading private images — the skill may instruct you to upload them to a Pixwith-hosted URL (presigned S3), so review Pixwith's privacy/retention policy and monitor credit usage. If you want stronger containment, verify MCP server TLS certificate and consider rotating the API key after initial tests.
功能分析
Type: OpenClaw Skill
Name: pixwith-ai-image-generation
Version: 1.0.1
The skill bundle provides a legitimate integration for the Pixwith AI media generation service using the Model Context Protocol (MCP). It contains well-documented workflows for image and video generation, including model discovery, schema validation, and credit management. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found; the requirement for an API key and connection to https://api.pixwith.ai/mcp is consistent with the skill's stated purpose.
能力评估
Purpose & Capability
The name/description (Pixwith image/video generation) matches the instructions: discovery, schema inspection, uploading reference images, creating async generate tasks, and polling results. Nothing requested (no env vars, no binaries, no special paths) is out of scope for a cloud media-generation integration.
Instruction Scope
SKILL.md limits agent actions to MCP tool calls (list_models, get_model_schema, upload_image, generate, get_task_result, get_credits), guiding user setup and upload flows. It does not instruct reading local secrets, unrelated files, or exfiltrating data to unexpected endpoints. Upload semantics and polling behavior are explicitly described.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only, which minimizes risk. All external endpoints referenced point to pixwith.ai and MCP presigned upload URLs (S3 semantics) described in the docs.
Credentials
The skill does not declare or require environment variables. It instructs the user to add a Pixwith API key to OpenClaw's MCP configuration (appropriate for a third‑party API). No unrelated credentials, secret paths, or broad environment access are requested.
Persistence & Privilege
always is false and the skill does not request any elevated or persistent platform privileges nor modify other skills. The skill allows normal autonomous invocation (disable-model-invocation: false) which is the platform default and acceptable here given the limited scope.
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-image-generation - 安装完成后，直接呼叫该 Skill 的名称或使用
/pixwith-ai-image-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"
- Installation/setup guidance is now shown as a bulleted list for clarity
- No functional changes or workflow adjustments introduced
- All core instructions, workflows, and guardrails remain unchanged
v1.0.0
- Initial release of Pixwith Media Generation skill for OpenClaw.
- Supports AI video and image generation across 40+ models, including Sora, Veo 3, Kling, Seedance, GPT Image, Hailuo, and WAN.
- Provides workflows for text-to-image, image-to-image, text-to-video, and image-to-video generation.
- Integrated guidance for configuration and MCP setup, including ready-to-use examples.
- Includes guardrails for model discovery, schema inspection, credit checking, and robust error handling.
元数据
常见问题
Ai Image 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 227 次。
如何安装 Ai Image Generation Skills？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pixwith-ai-image-generation」即可一键安装，无需额外配置。
Ai Image Generation Skills 是免费的吗？
是的，Ai Image Generation Skills 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ai Image Generation Skills 支持哪些平台？
Ai Image 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 Image Generation Skills？
由 mango_fish（@tate-kt）开发并维护，当前版本 v1.0.1。
推荐 Skills