一键导入
imagesearch
Visual research - search the web, find images, analyze them visually
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Visual research - search the web, find images, analyze them visually
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Interactive setup wizard for claude-vision - configures Docker images and platform settings
Read clipboard contents (text or image) and respond to a prompt about it
Read the latest screenshot and respond to a prompt about it
Analyze a video or screen recording by extracting frames and spawning an analysis agent
基于 SOC 职业分类
| name | imagesearch |
| description | Visual research - search the web, find images, analyze them visually |
Search the web for visual information, download and analyze relevant images, and synthesize findings.
/imagesearch <query>
/imagesearch majormud color system
/imagesearch "retro BBS door game UI design"
/imagesearch what font does discord use
WebSearch for the query + relevant visual terms (add "screenshot", "UI", "design", "example" etc. as appropriate)
WebFetch promising results to extract:
 tagsDownload images to /tmp/imagesearch-$$ using curl:
curl -sL "https://example.com/image.png" -o /tmp/imagesearch-$$/image-001.png
Read the downloaded images to analyze them visually
Synthesize findings into actionable information:
rm -rf /tmp/imagesearch-$$/When analyzing images, pay attention to:
User: /imagesearch majormud color system
Claude:
1. Searches "majormud color system screenshot ANSI"
2. Fetches wiki pages, finds image URLs
3. Downloads screenshots to /tmp
4. Analyzes the visual style:
- ANSI 16-color palette
- Cyan for system messages
- Yellow for item names
- Red for combat/damage
- etc.
5. Provides implementation recommendations