← Back to Skills Marketplace
flyfujian

Autoglm Search Image

by flyfujian · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
31
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install autoglm-search-image
Description
使用 AutoGLM 搜图接口,根据用户输入的关键词搜索相关图片。当用户需要搜索图片、查找图片素材等场景时使用此 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 Search Image Skill

根据用户输入的关键词,调用 AutoGLM 搜图 API 返回相关图片列表。


API

项目 内容
地址 https://autoglm-api.zhipuai.cn/agentdr/v1/assistant/skills/search-image
方式 POST
请求体 {"query": "\x3C搜索关键词>"}

脚本启动时会先向本地服务发起 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。

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 search-image.py

python search-image.py "猫咪"

无需安装第三方依赖,仅使用 Python 标准库。


返回结果处理

响应结构

{
  "code": 0,
  "msg": "SUCCESS",
  "data": {
    "results": [
      {
        "original_url": "图片链接",
        "caption": "图片描述",
        "source": "来源",
        "original_width": 1267,
        "original_height": 845
      }
    ],
    "query": "搜索词",
    "count": 4
  }
}

输出要求

遍历 data.results,以 Markdown 格式展示每张图片及其描述:

**1. 图片描述(来源)**
![图片描述](original_url)
Usage Guidance
Install only if you trust the publisher and understand the local token service. Running the skill will send your image search terms and a locally obtained bearer token to AutoGLM, so avoid confidential queries and verify that the token is narrowly scoped and short-lived.
Capability Assessment
Purpose & Capability
The stated purpose is AutoGLM image search, and the script is narrowly focused on calling the documented image-search endpoint with the user's query.
Instruction Scope
The skill can be invoked for ordinary image-search requests, but each run automatically fetches and uses a local bearer token without an explicit consent step or explanation of token scope.
Install Mechanism
The artifact contains a SKILL.md file and a single Python script using only the standard library; there is no installer, background service, dependency installation, or autorun hook.
Credentials
Network access is expected for image search, but the script retrieves a token from http://127.0.0.1:53699/get_token and sends it with the search query to https://autoglm-api.zhipuai.cn, while the local token provider and authorization boundaries are not explained.
Persistence & Privilege
No persistence or privilege escalation is present, but the script handles 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-search-image
  3. After installation, invoke the skill by name or use /autoglm-search-image
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
autoglm-search-image 1.0.0 - 首次发布,提供基于 AutoGLM 搜图 API 的图片搜索功能。 - 自动从本地服务获取 Token,无需手动配置环境变量。 - 支持命令行使用,无需第三方依赖,仅用 Python 标准库。 - 图片搜索结果以 Markdown 形式输出,包含图片及其描述和来源。
Metadata
Slug autoglm-search-image
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Autoglm Search Image?

使用 AutoGLM 搜图接口,根据用户输入的关键词搜索相关图片。当用户需要搜索图片、查找图片素材等场景时使用此 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 31 downloads so far.

How do I install Autoglm Search Image?

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

Is Autoglm Search Image free?

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

Which platforms does Autoglm Search Image support?

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

Who created Autoglm Search Image?

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

💬 Comments