← 返回 Skills 市场
1688aiinfra

1688 Item Image Optimizer

作者 1688AiInfra · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
29
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install 1688-item-image-optimizer
功能描述
1688 商品图片智能优化助手 —— 打开图片优化页面,为商品主图增加热卖元素。 触发词:优化图片、图片优化、主图优化、商品图片、改图。
使用说明 (SKILL.md)

1688-item-image-optimizer — 商品图片智能优化

技能概述

1688 商品图片智能优化助手。根据上下文是否包含商品 ID,打开对应的图片优化页面。

Agent 执行规范

禁止反问用户、禁止调用任何 CLI 命令、禁止执行任何额外逻辑。 仅根据上下文判断是否包含商品 ID,直接按 references/interaction-specs.mdopen_tab_image_optimize 的数据结构返回对应的 JSON 即可,流程到此结束,无需任何后续步骤。

安全使用建议
Treat this as a Review item rather than a simple tab-opening skill. If you only need the open-tab image optimizer, do not run the bundled CLI or provide an AK unless you trust the publisher and have verified the gateway/config behavior. The publisher should either remove the unused CLI/auth code or clearly declare the required 1688 credential, config writes, and gateway communication.
功能分析
Type: OpenClaw Skill Name: 1688-item-image-optimizer Version: 0.1.0 The skill bundle is a legitimate tool for 1688 merchants to optimize product images. It includes a CLI for configuration and an instruction set for the AI agent to trigger a UI-based optimization page. The code implements standard HMAC signing for API requests to official 1688 endpoints (e.g., skills-gateway.1688.com) and includes telemetry for usage tracking. While the skill can modify its own configuration in the OpenClaw config file (~/.openclaw/openclaw.json), this behavior is aligned with its stated purpose of managing API keys. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The declared user-facing purpose is to return an open_tab JSON for a 1688 image optimization page, but bundled Python code includes credential configuration, signed API calls, and usage reporting that are not needed for that narrow flow.
Instruction Scope
SKILL.md explicitly says not to call any CLI commands or execute extra logic, yet the artifact includes an executable CLI and helper modules with materially broader behavior.
Install Mechanism
There is no install spec and the SKILL.md path should not auto-run code; however, the package still ships runnable Python files whose dependency and credential behavior are not reflected in the install/requirements metadata.
Credentials
Registry requirements declare no credentials, environment variables, or config paths, while the code reads ALI_1688_AK, OpenClaw config files, gateway URLs/tokens, and calls 1688 gateway APIs.
Persistence & Privilege
If the bundled configure command is used, it can persist an API key into OpenClaw configuration or send it to the local gateway; this is high-impact credential handling that is not disclosed by the skill’s main purpose.
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 1688-item-image-optimizer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /1688-item-image-optimizer 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
v0.1.0
Initial release of 1688-item-image-optimizer: - Opens the product image optimization page for 1688 items, automatically adding "hot sale" elements to main images. - Triggers on keywords like "优化图片", "主图优化", or "商品图片". - Returns a JSON to open the optimization page with or without the offerId parameter, based on context. - No follow-up questions or additional logic executed; strictly one-step interaction.
元数据
Slug 1688-item-image-optimizer
版本 0.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

1688 Item Image Optimizer 是什么?

1688 商品图片智能优化助手 —— 打开图片优化页面,为商品主图增加热卖元素。 触发词:优化图片、图片优化、主图优化、商品图片、改图。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 29 次。

如何安装 1688 Item Image Optimizer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install 1688-item-image-optimizer」即可一键安装,无需额外配置。

1688 Item Image Optimizer 是免费的吗?

是的,1688 Item Image Optimizer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

1688 Item Image Optimizer 支持哪些平台?

1688 Item Image Optimizer 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 1688 Item Image Optimizer?

由 1688AiInfra(@1688aiinfra)开发并维护,当前版本 v0.1.0。

💬 留言讨论