菜单
Capture screenshots of the application UI and analyze image content. Use for visual verification, UI inspection, accessibility review, and generating image-grounded descriptions.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/benmcnulty/orgos --skill vision命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | Vision |
| description | Capture screenshots of the application UI and analyze image content. Use for visual verification, UI inspection, accessibility review, and generating image-grounded descriptions. |
| version | 1.0.0 |
| tools | ["screenshot","image_analyze"] |
| context | 2048 |
Provides screenshot capture and image analysis for the orgos UI and external images.
Capture the current state of the application UI.
Output: PNG image passed directly to the vision model Scope: Full-page or element-scoped capture
SCREENSHOT: full | element:#panel-id
→ Returns image for analysis
Describe or extract information from an image.
Input: Image (from screenshot or provided URL) Output: Structured description or extracted data
Usage pattern:
SCREENSHOT: full
→ ANALYZE: What panels are currently open?
→ ANALYZE: Are there any visible error states?
→ ANALYZE: What is the current agent queue status shown?
Use to confirm that a UI change produced the expected visual result:
Analyze a screenshot for: