← Back to Skills Marketplace
Image Analysis Litiao
by
litiao1224
· GitHub ↗
· v1.0.0
· MIT-0
846
Downloads
0
Stars
4
Active Installs
1
Versions
Install in OpenClaw
/install image-analysis-litiao
Description
Analyze images using browser and vision capabilities.
README (SKILL.md)
图片分析技能
使用浏览器和视觉能力来分析图片。
功能
- 打开图片链接
- 截取网页快照
- 分析图片内容
使用方法
打开图片链接
# 使用 browser 工具打开图片
browser action=open url="图片链接"
截取网页快照
# 使用 browser snapshot 截取页面
browser action=snapshot targetId="页面ID"
分析图片
对于 QQ 发来的图片，可以：
- 提取图片链接
- 使用 browser 打开
- 描述图片内容
支持的图片格式
- PNG
- JPG/JPEG
- GIF
- WebP
注意事项
- 需要 browser 工具支持
- Playwright 需要完整安装（不是 playwright-core）
- 图片链接需要可访问
Usage Guidance
This skill is instruction-only and appears to do what it says: open image links in a browser, snapshot pages, and describe images. Before using it, ensure the runtime has Playwright/full browser support installed as the SKILL.md requires. Only provide or allow access to image URLs you trust (the skill will fetch external resources). There are no requested credentials or installs in the package itself. If you plan to let the agent run autonomously, remember it may fetch arbitrary remote images when invoked — limit exposure by controlling which links or message sources the agent may access.
Capability Analysis
Type: OpenClaw Skill
Name: image-analysis-litiao
Version: 1.0.0
The skill bundle consists of metadata and instructions for an AI agent to perform image analysis using a browser tool. The SKILL.md file outlines standard procedures for opening URLs and taking snapshots via Playwright, with no evidence of malicious code, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the instructions: SKILL.md documents opening image links, taking snapshots, and analyzing images. The declared requirement for a browser tool/Playwright is consistent with the stated purpose.
Instruction Scope
Instructions are narrowly scoped to opening image URLs, taking snapshots, and describing image content. They reference extracting image links from QQ messages which is within the described image-analysis use case. Note: the skill will fetch external URLs (images/pages) — expected for this purpose but you should only provide/trust accessible links.
Install Mechanism
No install spec or code is included (instruction-only), so nothing will be written to disk. The SKILL.md asks for Playwright to be fully installed but does not attempt to install it — this is a reasonable runtime requirement, though the skill relies on the host environment having Playwright/browser tooling available.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportional to its stated image-analysis functionality.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skill configurations. Autonomous invocation is allowed by default but is not combined with any other concerning privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-analysis-litiao - After installation, invoke the skill by name or use
/image-analysis-litiao - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Bug fixes and improvements with -litiao suffix
Metadata
Frequently Asked Questions
What is Image Analysis Litiao?
Analyze images using browser and vision capabilities. It is an AI Agent Skill for Claude Code / OpenClaw, with 846 downloads so far.
How do I install Image Analysis Litiao?
Run "/install image-analysis-litiao" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Analysis Litiao free?
Yes, Image Analysis Litiao is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Image Analysis Litiao support?
Image Analysis Litiao is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Analysis Litiao?
It is built and maintained by litiao1224 (@litiao1224); the current version is v1.0.0.
More Skills