← 返回 Skills 市场
udiedrichsen

Shopping Expert

作者 udiedrichsen · GitHub ↗ · v1.1.0
cross-platform ⚠ suspicious
3443
总下载
5
收藏
16
当前安装
2
版本数
在 OpenClaw 中安装
/install shopping-expert
功能描述
Find and compare products online (Google Shopping) and locally (stores near you). Auto-selects best products based on price, ratings, availability, and preferences. Generates shopping list with buy links and store locations. Use when asked to shop for products, find best deals, compare prices, or locate items locally. Supports budget constraints (low/medium/high or "$X"), preference filtering (brand, features, color), and dual-mode search (online + local stores).
安全使用建议
This skill appears to do what it says (uses SerpAPI for online results and Google Places for local stores), but review these points before installing or providing API keys: - The registry requires both SERPAPI_API_KEY and GOOGLE_PLACES_API_KEY. If you only need online shopping, you should not have to provide a Google Places key — ask the publisher why both are mandatory or avoid providing the Places key. - The code is a Python script that declares dependencies (requests, urllib3) but the install spec only installs 'uv' via brew. Ensure you run it in an environment with Python 3.10+ and the required Python packages, or the script will fail. - The skill makes external network calls to SerpAPI and Google Places using your API keys. Only supply keys you trust and be aware of possible charges and quota usage from those services. - If you have security concerns, run the script in an isolated environment (container/VM) and inspect or run it with limited API keys (read-only or quota-limited) first. If you want to proceed, ask the publisher to clarify why GOOGLE_PLACES_API_KEY is listed as required in the registry (when SKILL.md states it's only needed for local/hybrid) and to provide an install step for the Python dependencies or a packaged runtime.
功能分析
Type: OpenClaw Skill Name: shopping-expert Version: 1.1.0 The OpenClaw AgentSkills skill bundle 'shopping-expert' is classified as benign. The `SKILL.md` documentation clearly outlines the skill's purpose and required API keys (`SERPAPI_API_KEY`, `GOOGLE_PLACES_API_KEY`), which are directly relevant to its functionality. The `scripts/shop.py` Python code uses standard libraries (`requests`, `urllib3`) to interact with the legitimate SerpAPI and Google Places API endpoints. There is no evidence of data exfiltration, unauthorized command execution, persistence mechanisms, obfuscation, or prompt injection attempts against the agent. All observed behaviors are aligned with the stated purpose of finding and comparing products online and locally.
能力评估
Purpose & Capability
Name/description align with functionality: the code calls SerpAPI for Google Shopping and Google Places for local searches. Requesting SERPAPI_API_KEY and GOOGLE_PLACES_API_KEY is expected for online and local modes respectively.
Instruction Scope
SKILL.md instructs the agent to run the provided Python script via 'uv run'. The runtime instructions and script only reference the two API keys and do not ask for unrelated files or secrets. The SKILL.md correctly documents that GOOGLE_PLACES_API_KEY is only required for local/hybrid modes, but the registry's required env list contradicts that (see environment_proportionality).
Install Mechanism
Install spec is a brew formula for 'uv' which matches the example 'uv run ...' usage. This is a low-risk install mechanism compared with arbitrary downloads. However, the script is Python and declares Python package dependencies (requests, urllib3) in its header, but the install spec does not install those Python dependencies or ensure Python is present—this mismatch may cause runtime failures.
Credentials
Registry requires both SERPAPI_API_KEY and GOOGLE_PLACES_API_KEY. SKILL.md and the code indicate SERPAPI is needed for online/hybrid and GOOGLE_PLACES only for local/hybrid. Requiring both keys unconditionally is disproportionate if a user only wants online-only searches. PrimaryEnv set to SERPAPI_API_KEY is appropriate, but forcing a Places key when not needed is an unnecessary credential request.
Persistence & Privilege
The skill does not request always:true and does not declare any system-wide configuration changes. It runs as an on-demand script and has normal autonomous-invocation defaults; no elevated persistence or cross-skill modification is present.
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 shopping-expert
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /shopping-expert 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
v1.1.0
Default to German search (Amazon.de, Google.de), add --country parameter, EUR currency support
v1.0.0
Initial release: dual-mode shopping with SerpAPI Google Shopping for online products and Google Places API for local stores. Smart scoring algorithm, budget parsing, preference matching, and both Markdown and JSON output formats.
元数据
Slug shopping-expert
版本 1.1.0
许可证
累计安装 17
当前安装数 16
历史版本数 2
常见问题

Shopping Expert 是什么?

Find and compare products online (Google Shopping) and locally (stores near you). Auto-selects best products based on price, ratings, availability, and preferences. Generates shopping list with buy links and store locations. Use when asked to shop for products, find best deals, compare prices, or locate items locally. Supports budget constraints (low/medium/high or "$X"), preference filtering (brand, features, color), and dual-mode search (online + local stores). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 3443 次。

如何安装 Shopping Expert?

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

Shopping Expert 是免费的吗?

是的,Shopping Expert 完全免费(开源免费),可自由下载、安装和使用。

Shopping Expert 支持哪些平台?

Shopping Expert 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 Shopping Expert?

由 udiedrichsen(@udiedrichsen)开发并维护,当前版本 v1.1.0。

💬 留言讨论