← 返回 Skills 市场
340
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install operation-platform-enterprise-knowledge
功能描述
域名测试
安全使用建议
This skill is suspicious because its runtime instructions read a local credentials file (~/.openclaw/username) and send that value to an internal corporate API, which does not match the 'domain test' description. Before installing: 1) Ask the publisher why domain testing needs a merchant lookup and why it must read ~/.openclaw/username; 2) Verify what exactly is stored in ~/.openclaw/username and whether exposing it to that endpoint is acceptable; 3) Prefer a skill that requires an explicit, declared credential (env var or documented auth) rather than silently reading local files; 4) Only enable this skill if you trust the source and the internal endpoint (e.g., you're on the same corporate network and the owner is known); 5) If unsure, do not install or run the skill in an environment containing sensitive credentials—test it in an isolated sandbox first.
功能分析
Type: OpenClaw Skill
Name: operation-platform-enterprise-knowledge
Version: 1.0.2
The skill 'domain-test-skill' (SKILL.md) instructs the AI agent to read a specific local file path (~/.openclaw/username) to retrieve a username for use in an API request to an internal corporate endpoint (merchant-lego.corp.kuaishou.com). While the behavior appears aligned with an internal enterprise lookup tool, the explicit instruction to perform local filesystem I/O to access configuration/credential data is a high-risk pattern that could be abused for unauthorized data access or credential exposure if the agent's environment is not strictly sandboxed.
能力评估
Purpose & Capability
Name/description indicate a domain test, but the runtime instructions perform a merchant-seller lookup against an internal corporate API and require a local username file. These requests are not explained by 'domain testing' and appear out of scope.
Instruction Scope
SKILL.md directs the agent to read a local config file (~/.openclaw/username) for `${username}` and then POST that plus a parsed sellerName to https://merchant-lego.corp.kuaishou.com/.... It returns the raw HTTP response to the user. Reading a local user file and sending it to an external/internal endpoint is beyond what's expected for a generic 'domain test' skill.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is written to disk by an installer step.
Credentials
The skill accesses a local credential file (~/.openclaw/username) but declares no required env vars or credentials. That local-file access is sensitive and not justified by the skill description. There is no explicit primary credential declared even though a username is read from disk.
Persistence & Privilege
always is false and the skill does not request persistent, system-wide changes or modify other skills' configurations. Autonomous invocation is allowed (default) but not by itself a red flag 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 operation-platform-enterprise-knowledge - 安装完成后，直接呼叫该 Skill 的名称或使用
/operation-platform-enterprise-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
v1.0.2
- Removed all scripts and evaluation files related to智能报告 and诊断报告 functionalities.
- Skill scope has changed from "智能报告" to a basic "域名测试" service.
- All previous diagnosis routing logic and report generation features have been removed.
- New功能: 支持根据请求调用接口自动查找商家ID，仅此固定流程。
- 用户需本地配置用户名用于认证，未配置时报错提示。
v1.0.1
Version 1.0.1 of operation-platform-enterprise-knowledge introduces initial support for automated diagnosis report generation.
- Added scripts for intelligent seller, live, and brand diagnosis reports.
- Introduced a new intent and keyword set for triggering report generation based on user requests.
- Implemented routing logic to select the correct report type based on user input.
- Added sample evaluation configuration.
v1.0.0
- Initial release of "enterprise-knowledge" (知识库检索) skill for retrieving internal Kuaishou enterprise policies, processes, SOPs, and FAQs.
- Supports searching and extracting top relevant content snippets and links from business spaces/knowledge bases.
- Implements a fixed 3-step retrieval workflow: fetch business spaces, select knowledge repo, and retrieve content.
- Includes clear usage rules, error handling, memory/cache logic, and unified output format for top 3 results.
- Chinese-language and enterprise-specific prompts, triggers, and matching strategies included.
元数据
常见问题
测试 是什么？
域名测试. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 340 次。
如何安装 测试？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install operation-platform-enterprise-knowledge」即可一键安装，无需额外配置。
测试 是免费的吗？
是的，测试 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
测试 支持哪些平台？
测试 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 测试？
由 Jim Adara（@jimadara）开发并维护，当前版本 v1.0.2。
推荐 Skills