← 返回 Skills 市场
460
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install web-search-skill
功能描述
联网搜索工具，通过百度和必应搜索引擎获取实时网络信息，无需API Key。当用户需要搜索网络信息、查找最新资讯、获取实时数据、或需要联网查询任何内容时使用此技能。适配中国网络环境。
安全使用建议
This skill is coherent for the stated purpose (web-scraping search results). Before installing, consider: 1) It performs network requests to search engines and may fetch arbitrary result pages (treat fetched content as untrusted). 2) SKILL.md asks you to pip install third‑party Python packages — install them in a controlled virtualenv. 3) The script parses HTML and may break if search engines change their layout; it also leaves Baidu redirect URLs as-is and suggests using a separate WebFetch step to resolve real target pages. 4) Review scripts/search.py yourself (or run it in a sandbox) to confirm no additional data exfiltration or unexpected remote endpoints are present. If you need stricter controls, disable autonomous invocation for the agent or restrict this skill to manual use only.
功能分析
Type: OpenClaw Skill
Name: web-search-skill
Version: 1.0.0
The skill bundle provides a legitimate web search tool that scrapes Baidu and Bing search results using the 'requests' and 'BeautifulSoup' libraries. The Python script (scripts/search.py) implements standard scraping techniques, such as random User-Agents and delays, to avoid rate limiting, and the documentation (SKILL.md) contains appropriate instructions for an AI agent without any evidence of malicious prompt injection or unauthorized data access.
能力评估
Purpose & Capability
The name and description match the included search script: it scrapes Baidu and cn.bing.com for results. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to install standard Python scraping libs, run the provided script, and optionally use a WebFetch tool to retrieve full pages. The instructions do not ask the agent to read local secrets, system files, or send data to unexpected third-party endpoints beyond the target search engines and fetched result pages.
Install Mechanism
There is no install spec; the skill is instruction+script only. Dependencies are installed via pip (requests, beautifulsoup4, lxml) — a common and expected approach for a Python scraper. No downloads from unknown URLs or archive extraction were observed.
Credentials
The skill declares no required environment variables or credentials. All operations are network requests to search engines; no secret access or unrelated service tokens are requested.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request elevated or persistent system privileges and does not modify other skills or system-wide configs.
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-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/web-search-skill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
- 首次发布 web-search 工具，支持通过百度和必应（中国版）进行实时网络搜索，无需API Key。
- 适配中国网络环境，可灵活指定搜索引擎、时间范围和结果数量。
- 支持搜索引擎原生高级语法，如 site、filetype、intitle 等。
- 提供 Bash/Windows 命令行调用方法，并支持 JSON 格式输出。
- 搜索流程、结果分析和信息整合操作流程详尽说明。
- 默认解析HTML页面提取信息，返回摘要与来源，并建议结合 WebFetch 深入获取页面内容。
元数据
常见问题
web-search-skill 是什么？
联网搜索工具，通过百度和必应搜索引擎获取实时网络信息，无需API Key。当用户需要搜索网络信息、查找最新资讯、获取实时数据、或需要联网查询任何内容时使用此技能。适配中国网络环境。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 460 次。
如何安装 web-search-skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-search-skill」即可一键安装，无需额外配置。
web-search-skill 是免费的吗？
是的，web-search-skill 完全免费（开源免费），可自由下载、安装和使用。
web-search-skill 支持哪些平台？
web-search-skill 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-skill？
由 shidifu（@shidifu）开发并维护，当前版本 v1.0.0。
推荐 Skills