← 返回 Skills 市场
corinbtc

Openclaw Skill

作者 corinbtc · GitHub ↗ · v1.0.4 · MIT-0
cross-platform ⚠ suspicious
361
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install ai-product-space
功能描述
上传一张产品白底图,AI 自动生成电商全套素材:商品主图、场景图、卖点海报、营销文案与 8 秒展示视频。Generate full ecommerce assets from a single product photo.
使用说明 (SKILL.md)

AI Product Space Skill

将 AI Product Space 的电商素材生成能力接入 OpenClaw。一张白底产品图即可自动生成商品主图、场景图、卖点海报、营销文案和展示视频。

授权

首次使用时,OpenClaw 会自动弹出浏览器窗口引导你登录并授权。点击「允许」即可完成一键连接,无需手动配置 API Key。

如需手动配置(离线环境),在 config.json 中填入:

{
  "APS_BASE_URL": "https://renshevy.com",
  "APS_API_KEY": "aps_xxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}

API Key 可在 AI Product Space 的「设置 → API 密钥」页面创建。

工具说明

create_space

创建新的工作空间。每个产品建议一个独立空间。

  • name(可选): 空间名称,建议用产品名

upload_product_image

上传产品白底图到工作空间。支持本地路径或 URL。

  • space_id(必填): 空间 ID
  • image_path: 本地图片路径
  • image_url: 图片 URL(二选一)

run_ecommerce_pipeline

运行全套电商素材生成流水线,一键生成 20+ 张商品图和多段文案。

  • space_id(必填): 空间 ID
  • language: 输出语言(zh/en/ja/ko 等 10 种)
  • wait: 是否等待完成(默认 true,约需 2-5 分钟)

generate_single_image

根据自定义 Prompt 生成单张商品图。

  • space_id(必填): 空间 ID
  • prompt(必填): 图片描述
  • count: 生成数量(1-4)

generate_video

从商品图生成 8 秒展示视频。

  • space_id(必填): 空间 ID
  • image_urls(必填): 1-2 张图片 URL
  • prompt: 运镜/风格描述
  • wait: 是否等待完成(默认 true,约需 1-3 分钟)

get_space_status

查看空间状态和流水线进度。

  • space_id(必填): 空间 ID

list_assets

浏览已生成的素材资源。

  • folder_id(可选): 文件夹 ID

典型使用流程

完整流水线(推荐)

用户: 帮我生成蓝牙耳机的电商素材

1. create_space → 创建 "蓝牙耳机" 空间
2. (请用户提供产品图)
3. upload_product_image → 上传白底图
4. run_ecommerce_pipeline → 运行全套生成
5. 返回生成结果摘要

单张图片生成

用户: 帮我生成一张场景图,蓝牙耳机放在书桌上

1. generate_single_image → 使用自定义 prompt 生成
2. 返回图片链接

视频生成

用户: 把这张商品图做成视频

1. generate_video → 提交图片生成视频
2. 返回视频链接

注意事项

  • 生成流水线需要消耗积分,请确保账户余额充足
  • 上传的图片建议为白底产品图,效果最佳
  • 流水线生成通常需要 2-5 分钟,视频生成需要 1-3 分钟
  • 支持 10 种输出语言:中文、英语、日语、韩语、法语、德语、西班牙语、葡萄牙语、阿拉伯语、俄语
安全使用建议
This skill appears to do what it says (generate images, posters, copy, and short videos) and needs network access to your configured AI Product Space server plus permission to read any local image file you choose to upload. Before installing: - Understand where images will be sent: by default the skill's docs point to https://renshevy.com; confirm the APS_BASE_URL you configure is a trusted endpoint. Uploaded images and prompts are transmitted to that service. - OAuth: the plugin defines an OAuth flow with very broad scopes ("*") in the manifest. Confirm the authorization screen and scopes when the browser opens; only proceed if you trust the service. - Configuration mismatch: the documentation and SKILL.md say to set APS_BASE_URL and APS_API_KEY in config.json, but the runtime code looks for context.config.baseUrl and context.config.apiKey (and falls back to process.env.APS_BASE_URL). This is likely a bug — OAuth may work if OpenClaw injects the configured APS_BASE_URL into the plugin, but manual API-key setups may fail unless you set environment variables or the differently named config keys. If you plan offline/manual usage, be prepared to set environment variables APS_BASE_URL and/or provide values under the names the runtime expects (baseUrl / apiKey), or contact the author/maintainer. - Test with non-sensitive images first. Because the skill uploads images to a remote service, avoid uploading private or proprietary photos until you verify the provider's privacy policy and that the endpoints are correct. - Verify source/trust: the package lists a homepage/repository (renshevy.com / github.com/renshevy/ai-product-space). If you require higher assurance, inspect the upstream repository, confirm the maintainer identity, or run the skill in an isolated environment. Given the implementation/config mismatches and broad OAuth scopes, treat the skill as suspicious until you verify endpoints and test the auth flow. If you can share logs or how OpenClaw populates context.config after OAuth (or a corrected config mapping), the assessment could be upgraded.
功能分析
Type: OpenClaw Skill Name: ai-product-space Version: 1.0.4 The skill bundle is a legitimate integration for the AI Product Space platform, designed to generate ecommerce assets like images and videos. It uses network permissions to communicate with the service API (renshevy.com) and filesystem permissions to read local image files for uploading, both of which are justified by the tool's stated purpose. The code in 'dist/lib/api-client.js' and 'dist/tools/upload-image.js' follows standard patterns for file handling and API interaction without any evidence of obfuscation, data exfiltration, or malicious intent.
能力评估
Purpose & Capability
Name/description (generate ecommerce assets from a product photo) align with the implemented tools and required permissions (network for API calls, filesystem to read user-supplied image files). The included toolset (create_space, upload_product_image, run_ecommerce_pipeline, generate_single_image, generate_video, get_space_status, list_assets) matches the described functionality.
Instruction Scope
SKILL.md/instructions restrict actions to creating spaces, uploading a user-provided image (local path or URL), running pipelines, polling status, and listing assets. It does not instruct reading arbitrary files or other system state. However, instructions and docs reference config keys APS_BASE_URL and APS_API_KEY for manual setup whereas the runtime code reads context.config.baseUrl and context.config.apiKey (naming mismatch) — this is a scope/behavior inconsistency that may prevent the skill from working as documented.
Install Mechanism
No remote download/install steps are present. The package includes compiled JS files and an OpenClaw extension entry (./dist/index.js). There are no external URLs or archive extracts in an install spec to raise high-risk concerns.
Credentials
The skill requests only network and filesystem permissions which are appropriate for uploading images and making API calls. But there is a configuration naming inconsistency: documentation/config (APS_BASE_URL / APS_API_KEY) differs from what the code expects (baseUrl / apiKey) and the code also falls back to process.env.APS_BASE_URL. This mismatch could cause the skill to require setting environment vars or different config keys than documented, leading to misconfiguration or failed OAuth/manual auth flows. OAuth scopes in claw.json are listed as ["*"] — broad by default; verify the actual scopes granted by the provider before consenting.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes or modify other skills. It uses normal OpenClaw OAuth and config; no evidence it escalates privileges or persists beyond its own configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install ai-product-space
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ai-product-space 触发
  4. 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
v1.0.4
- Maintenance release with dependency and configuration updates. - Updated package.json and lock files for improved compatibility. - Revised metadata in claw.json and clawhub.json. - No user-facing changes to features or skill behavior.
v1.0.3
- Removed all TypeScript source files and type definitions from the project. - Removed related TypeScript configuration files. - Added new pipeline formatter tool (dist/tools/pipeline-formatter.js). - Updated or recompiled several JavaScript files in the dist directory. - No changes to skill documentation or feature set.
v1.0.1
Fix: add openclaw.extensions to package.json for proper plugin registration
v1.0.0
Initial release: 7 tools for full ecommerce asset generation, OAuth one-click auth, 10-language support
元数据
Slug ai-product-space
版本 1.0.4
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 4
常见问题

Openclaw Skill 是什么?

上传一张产品白底图,AI 自动生成电商全套素材:商品主图、场景图、卖点海报、营销文案与 8 秒展示视频。Generate full ecommerce assets from a single product photo. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 361 次。

如何安装 Openclaw Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-product-space」即可一键安装,无需额外配置。

Openclaw Skill 是免费的吗?

是的,Openclaw Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Openclaw Skill 支持哪些平台?

Openclaw Skill 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 Openclaw Skill?

由 corinbtc(@corinbtc)开发并维护,当前版本 v1.0.4。

💬 留言讨论