← 返回 Skills 市场
277
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install web-search-engine
功能描述
Retrieve search results from web search engines.
安全使用建议
This skill is mostly what it says it is (an HTML-scraping search helper), but it fails to declare that it needs Node to run. Before installing, verify your agent environment provides a compatible Node runtime (and global fetch support, e.g. Node 18+), or update the skill metadata to list node as a required binary. Review the included search.js yourself — it performs live HTTP requests to external search engines (which may be subject to terms-of-service or blocking) and constructs URLs without encodeURIComponent (malformed or unexpected input may break requests). No secrets are requested, but if you plan to run this in production, consider running it in a restricted environment and confirm you are comfortable with on-demand outbound HTTP requests to the listed domains.
功能分析
Type: OpenClaw Skill
Name: web-search-engine
Version: 1.0.0
The skill is a legitimate web search utility that scrapes results from major search engines (Baidu, Bing, 360, and Sogou). The code in `search.js` uses the built-in Node.js fetch API to retrieve search results and implements basic regex-based HTML parsing to return text to the agent; there is no evidence of data exfiltration, malicious command execution, or prompt injection in `SKILL.md`.
能力评估
Purpose & Capability
The description and SKILL.md state the skill uses a Node script (search.js) to retrieve search results and the included code implements scraping of several search engines — that matches the stated purpose. However the registry metadata lists no required binaries; SKILL.md usage explicitly requires running `node search.js`. The skill therefore fails to declare a legitimate runtime dependency (node), which is an incoherence.
Instruction Scope
The runtime instructions are narrowly scoped: run the provided search.js with a keyword and optional engine list. The script only reads command-line args, performs HTTP GET requests to public search engines, scrapes returned HTML, and prints a JSON array. It does not access other files, environment variables, or external endpoints beyond the search engines.
Install Mechanism
There is no install spec (instruction-only with a bundled script). Nothing is downloaded at install time and no archives or remote installers are referenced.
Credentials
The skill declares no environment variables or credentials and the code does not read env vars or secrets. Requested privileges are proportional to the stated purpose.
Persistence & Privilege
The skill does not request permanent/always-on presence and does not modify other skills or system-wide configs; autonomous invocation defaults are unchanged (normal).
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 web-search-engine - 安装完成后，直接呼叫该 Skill 的名称或使用
/web-search-engine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
Initial release of web-search-engine skill.
- Retrieve search results using multiple web search engines (Baidu, 360, Bing, Sogou).
- Supports searches via Node.js script with customizable engine selection.
- Returns JSON-serialized arrays of search results.
- Enables simultaneous multi-engine searches for efficiency.
- Designed for lightweight operation and token-saving.
元数据
常见问题
web-search-engine 是什么？
Retrieve search results from web search engines. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 277 次。
如何安装 web-search-engine？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-search-engine」即可一键安装，无需额外配置。
web-search-engine 是免费的吗？
是的，web-search-engine 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
web-search-engine 支持哪些平台？
web-search-engine 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 web-search-engine？
由 小祺先生（@lwq057）开发并维护，当前版本 v1.0.0。
推荐 Skills