← 返回 Skills 市场
bargain-hunter
作者
hanxueyuan
· GitHub ↗
· v0.1.0
· MIT-0
90
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install bargain-hunter
功能描述
AI bargain hunting
使用说明 (SKILL.md)
🛒 Bargain Hunter
AI bargain hunting
What It Does
Aggressive deal-seeking agent that monitors flash sales, clearance events, warehouse deals, and price errors across e-commerce platforms. Uses historical pricing data to identify genuine bargains versus fake discounts. Supports custom alert rules and spending limits.
Usage
When the user mentions buying, purchasing, shopping, or looking for product deals, this skill activates to help find the best options.
Example Prompts
- "Find me the best deal on [product]"
- "Compare prices for [product] across platforms"
- "Is there a coupon for [product]?"
- "Help me buy [product] under [budget]"
Configuration
Set up API credentials in environment variables as needed for each supported platform.
Architecture
User Request → Intent Parser → Product Search API → Result Ranker → Recommendation Display
Roadmap
- v0.1: Basic product search via web search
- v0.2: Platform API integration
- v0.3: Price tracking and alerts
- v1.0: Full autonomous purchasing flow
Author
Created by hanxueyuan as part of the Agent Commerce initiative. License: MIT
安全使用建议
This skill is not outright malicious, but it lacks important implementation and security details. Before installing or using it, ask the author to: (1) list exactly which platform APIs it will use and the precise environment variables required, (2) describe how monitoring works (frequency, background processes), where data and historical prices are stored, and who can access them, (3) confirm whether the skill can perform purchases autonomously and, if so, require explicit user approval flows and spending limits, and (4) provide a privacy/retention policy for collected data. If you plan to give it access to any payment or API credentials, only do so after you have explicit, concrete answers and prefer testing in a sandbox account. Because the current SKILL.md is vague about these matters, treat it as suspicious until those gaps are closed.
功能分析
Type: OpenClaw Skill
Name: bargain-hunter
Version: 0.1.0
The skill bundle contains only metadata and documentation (SKILL.md) for a shopping assistant. There is no executable code, and the instructions are consistent with the stated purpose of finding product deals without any signs of prompt injection or malicious intent.
能力评估
Purpose & Capability
Name/description match the high-level purpose (bargain hunting, price comparison). However, claimed capabilities like continuous monitoring, historical price analysis, alerts, and 'full autonomous purchasing' imply persistent storage, platform API access, and credential use — none of which are declared or specified. Saying "Set up API credentials in environment variables as needed" without declaring which credentials or requiring env vars is an inconsistency.
Instruction Scope
SKILL.md is high-level and leaves runtime behavior unspecified. It instructs activation whenever the user mentions buying/shopping and describes monitoring/alerts, but gives no concrete limits on data collection, polling frequency, storage locations, or where alerts are sent. That vagueness grants the agent broad discretion (possible continuous monitoring or arbitrary network access) without bounds.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install footprint. Nothing will be written to disk by an installer because there is no install mechanism declared.
Credentials
The doc tells users to "Set up API credentials in environment variables as needed for each supported platform," but the skill declares no required env vars or primary credential. For the claimed platform integrations (e.g., e-commerce APIs) you'd normally expect explicit env var names and justification; that mismatch is a red flag because it may later ask for sensitive keys without upfront disclosure.
Persistence & Privilege
Flags show normal defaults (always: false, agent can invoke autonomously). That is expected. However the roadmap explicitly mentions 'full autonomous purchasing flow' in future — if that is implemented later, it could require higher privileges (payment credentials, order placement). The current package does not request those, but the roadmap increases future risk and should be treated cautiously.
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 bargain-hunter - 安装完成后，直接呼叫该 Skill 的名称或使用
/bargain-hunter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
v0.1.0
bargain-hunter 0.1.0 initial release
- Launches an AI-powered agent for finding bargains and genuine deals across e-commerce platforms.
- Monitors flash sales, clearance events, warehouse deals, and price errors.
- Uses historical pricing to filter out fake discounts.
- Customizable alert rules and spending limits.
- Activates automatically with shopping-related prompts.
- Supports basic product search via web scraping in this version.
元数据
常见问题
bargain-hunter 是什么？
AI bargain hunting. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 90 次。
如何安装 bargain-hunter？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install bargain-hunter」即可一键安装，无需额外配置。
bargain-hunter 是免费的吗？
是的，bargain-hunter 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
bargain-hunter 支持哪些平台？
bargain-hunter 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 bargain-hunter？
由 hanxueyuan（@hanxueyuan）开发并维护，当前版本 v0.1.0。
推荐 Skills