← Back to Skills Marketplace
flyfujian

Autoglm Websearch

by flyfujian · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
30
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install autoglm-websearch
Description
使用 AutoGLM Web Search 接口进行网络信息搜索。当用户需要联网搜索、查询最新资讯、检索网页内容或获取实时信息时使用此 skill。 Token 通过本地服务 http://127.0.0.1:53699/get_token 自动获取,无需手动配置环境变量。
README (SKILL.md)

AutoGLM WebSearch Skill

调用 AutoGLM Web Search API 进行网络搜索。


Token 获取

脚本启动时自动向本地服务发起 HTTP GET 请求获取 token:

项目 内容
地址 http://127.0.0.1:53699/get_token
方式 GET
返回 Bearer xxx(直接作为 Authorization 头使用)

若返回值不含 Bearer 前缀,脚本会自动补全。


Search API

项目 内容
地址 https://autoglm-api.zhipuai.cn/agentdr/v1/assistant/skills/web-search
方式 POST
请求体 {"queries": [{"query": "\x3C搜索词>"}]}

签名 Headers(每次动态生成):

  • X-Auth-Appid: 100003
  • X-Auth-TimeStamp: 当前秒级 Unix 时间戳
  • X-Auth-Sign: MD5(100003 + "&" + timestamp + "&" + 38d2391985e2369a5fb8227d8e6cd5e5)

执行脚本

使用同目录下的 websearch.py

python websearch.py "搜索关键词"

返回结果处理

响应结构

{
  "code": 0,
  "msg": "SUCCESS",
  "data": {
    "results": [
      {
        "webPages": {
          "value": [
            {
              "name": "页面标题",
              "url": "页面链接",
              "snippet": "摘要内容"
            }
          ]
        }
      }
    ]
  }
}

输出要求

1. 总结搜索内容 基于所有条目的 snippet 字段,提炼出与用户 query 相关的核心信息,用自然语言组织成简洁的回答。

2. 附加引用列表 在回答末尾附上参考来源:

**参考来源:**
1. [页面标题](页面链接)
2. [页面标题](页面链接)
Usage Guidance
Install only if you trust the AutoGLM endpoint and the local token service on your machine. Treat search terms as data sent to a third party, and confirm that the local bearer token is intended for this API, scoped narrowly, and not shared with unrelated services.
Capability Assessment
Purpose & Capability
The stated purpose is AutoGLM web search, and the script performs that by sending a user-provided query to the documented AutoGLM endpoint.
Instruction Scope
The activation language is broad for latest information and page retrieval, so agents may use it frequently for ordinary web questions while also triggering credential retrieval and external requests.
Install Mechanism
The artifact contains a markdown skill file and a Python helper script with no package install, autorun hook, background worker, or persistence mechanism.
Credentials
The skill depends on a local HTTP token service at 127.0.0.1:53699 and sends the resulting bearer token plus the search query to an external API; the local token provider, token scope, and user-control model are not explained.
Persistence & Privilege
No persistence or privilege escalation is present, but the script does handle bearer credentials automatically whenever it is run.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install autoglm-websearch
  3. After installation, invoke the skill by name or use /autoglm-websearch
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
AutoGLM WebSearch Skill 1.0.0 - 实现通过 AutoGLM Web Search API 联网搜索、获取最新资讯和网页内容。 - 启动时自动从本地服务获取 token,免去手动配置。 - 支持动态生成签名 Headers,实现安全 API 访问。 - 提供简单命令行脚本用法,快速发起搜索。 - 搜索结果自动总结并附带清晰的参考来源列表。
Metadata
Slug autoglm-websearch
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Autoglm Websearch?

使用 AutoGLM Web Search 接口进行网络信息搜索。当用户需要联网搜索、查询最新资讯、检索网页内容或获取实时信息时使用此 skill。 Token 通过本地服务 http://127.0.0.1:53699/get_token 自动获取,无需手动配置环境变量。 It is an AI Agent Skill for Claude Code / OpenClaw, with 30 downloads so far.

How do I install Autoglm Websearch?

Run "/install autoglm-websearch" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Autoglm Websearch free?

Yes, Autoglm Websearch is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Autoglm Websearch support?

Autoglm Websearch is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Autoglm Websearch?

It is built and maintained by flyfujian (@flyfujian); the current version is v1.0.0.

💬 Comments