← 返回 Skills 市场
Retail Knowledge
作者
fangwei-frank
· GitHub ↗
· v1.0.0
· MIT-0
187
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install retail-knowledge
功能描述
Product knowledge Q&A and policy lookup for retail digital employees. Answers customer and staff questions about products, store policies, promotions, FAQs,...
安全使用建议
This skill appears coherent and low-risk: it searches a local knowledge_base.json and constructs answers from that KB. Before installing, confirm (1) the source and contents of the knowledge base (who can edit the JSON file), (2) where the skill's "internal" logs will be stored (the SKILL.md mentions logging but doesn't specify the storage/retention), and (3) the other referenced setup/hand-off skills (retail-agent-setup, product-recommender, inventory-query, complaint-handler) to ensure they are trustworthy. If you plan to run kb_search.py, ensure the KB file path you supply is the intended, access-controlled file and not a general system path.
功能分析
Type: OpenClaw Skill
Name: retail-knowledge
Version: 1.0.0
The retail-knowledge skill bundle is a standard implementation for a retail Q&A agent. It includes a Python script (scripts/kb_search.py) for searching a local JSON knowledge base using weighted keyword matching and documentation (SKILL.md and references/) that guides the agent on answer construction and persona management. No malicious behaviors, data exfiltration, or harmful instructions were found.
能力评估
Purpose & Capability
Name/description map to a KB-driven Q&A assistant. The included kb_search.py and the SKILL.md both focus on searching a local knowledge_base.json and constructing grounded answers; nothing in the bundle requires access to unrelated services or credentials.
Instruction Scope
Runtime instructions stay within the stated scope (classify queries, consult KB, build answers, hand off to other retail skills when appropriate). One small ambiguity: SKILL.md says to "log the query internally for Step 12 gap digest" but doesn't define the log location or retention — this is an operational detail to clarify, not an evidence of malicious behavior.
Install Mechanism
No install spec — instruction-only with a single Python script. The script is small, local, and does not fetch external artifacts or write arbitrary files; risk from installation is minimal.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The code only reads a KB file passed as an argument; it does not access other environment secrets or network endpoints.
Persistence & Privilege
always is false and the skill is user-invocable with normal autonomous invocation allowed. The skill does not request persistent system-wide privileges or modify other skills' config.
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 retail-knowledge - 安装完成后，直接呼叫该 Skill 的名称或使用
/retail-knowledge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
first release
元数据
常见问题
Retail Knowledge 是什么？
Product knowledge Q&A and policy lookup for retail digital employees. Answers customer and staff questions about products, store policies, promotions, FAQs,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 187 次。
如何安装 Retail Knowledge？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install retail-knowledge」即可一键安装，无需额外配置。
Retail Knowledge 是免费的吗？
是的，Retail Knowledge 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Retail Knowledge 支持哪些平台？
Retail Knowledge 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 Retail Knowledge？
由 fangwei-frank（@fangwei-frank）开发并维护，当前版本 v1.0.0。
推荐 Skills