← 返回 Skills 市场
购物比价师
作者
zhongzhiqiang-test
· GitHub ↗
· v1.0.0
· MIT-0
153
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install z-price-compare
功能描述
通过搜索引擎公开数据,比较各大电商平台商品价格,生成对比报告并提供个人购买建议。
安全使用建议
This skill appears internally consistent and implements a search-engine–based price comparator. Before installing, confirm that the OpenClaw/OpenAI agent tools it expects (web_search/web_fetch) are configured to only return/search public search-engine results (so it cannot be redirected to fetch arbitrary pages). Be aware the skill relies on search snippets so prices may be stale or incomplete—always verify final prices on the vendor site. Also note the bundled script can write JSON files locally (save_to_json) — if you run the skill in a shared environment, consider file permissions and sensitive-data policies.
功能分析
Type: OpenClaw Skill
Name: z-price-compare
Version: 1.0.0
The skill bundle provides a shopping price comparison tool designed to operate in a 'Safe Mode' by using search engine results (via web_search) instead of direct web scraping. The Python script (scripts/price_checker.py) and documentation (SKILL.md, README.md) consistently emphasize compliance, legal disclaimers, and the use of publicly indexed data. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description, SKILL.md, README, and scripts/price_checker.py all describe the same behavior: build search queries, use search-engine results (web_search) and extract visible snippet data to generate comparison reports. There are no unrelated environment variables, binaries, or cloud credentials requested.
Instruction Scope
SKILL.md and the script consistently instruct the agent to use web_search/web_fetch to read public search-index snippets and not to perform direct scraping, logins, or cookie/session manipulation. Note: the documentation refers to web_fetch and placeholders for parsing search results — the actual safety depends on the agent's implementation of web_search/web_fetch and whether those tools are constrained to search-engine content only.
Install Mechanism
No install spec is provided (instruction-only skill) and included code is local. Nothing is downloaded from external URLs and no archives are extracted, so there is minimal install risk.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The functionality described does not require secrets or external credentials, so requested access is proportionate.
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or agent-wide configuration. Autonomous invocation (model-invocation enabled) is the platform default and not by itself a concern here.
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 z-price-compare - 安装完成后,直接呼叫该 Skill 的名称或使用
/z-price-compare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
v1.0.0
**Major update — Safe mode & compliance rewrite:**
- All direct scraping/crawling features removed; now relies solely on search engine results for data collection.
- Extensive legal disclaimer and compliance section added (in both English & Chinese), outlining responsible use and prohibited activities.
- Output/reporting logic revised for clear, search-based comparison tables with highlighted platform info and buying advice.
- Trust score and phase/gate mechanisms from previous workflow removed to match new "safe-mode" approach.
- Reference and script files reorganized; legacy trust-checklist/platforms references removed.
- Now targets Chinese shopping platforms (JD, Taobao, Tmall, Pinduoduo, etc.) and output examples adapted for this market.
元数据
常见问题
购物比价师 是什么?
通过搜索引擎公开数据,比较各大电商平台商品价格,生成对比报告并提供个人购买建议。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 153 次。
如何安装 购物比价师?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install z-price-compare」即可一键安装,无需额外配置。
购物比价师 是免费的吗?
是的,购物比价师 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
购物比价师 支持哪些平台?
购物比价师 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 购物比价师?
由 zhongzhiqiang-test(@zhongzhiqiang-test)开发并维护,当前版本 v1.0.0。
推荐 Skills