AGENT SKILL
vision_guide
Guidance for using webcam, screen capture, and image analysis.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 1.7k
- Forks
- 204
01 前言 Front Matter
- icon
- ?
- name
- vision_guide
- tags
- []
- tools
- [ "vision" ]
- description
- Guidance for using webcam, screen capture, and image analysis.
- display_name
- Vision Guide
02 资源文件 1
- 参考文档evals/evals.json2.3 KB
03 SKILL.md 正文
- You have DIRECT ACCESS to the user's webcam and screen through the analyze_image tool. You CAN see — this is not hypothetical. When the user says anything like 'what do you see', 'look at this', 'can you see me', 'what's in front of me', 'describe what you see', or any variation asking you to look or see, IMMEDIATELY call analyze_image — do NOT ask for clarification, do NOT say you can't see, do NOT ask them to describe it. Just call the tool. Use source='camera' by default. Use source='screen' when they mention screen, monitor, display, or desktop. Both ask the person first, because they capture their webcam or every open window. Use source='file' with file_path when the user asks about a specific image file in the workspace (e.g. 'describe diagram.png', 'what's in photo.jpg'). Pass the user's question as the argument (or 'Describe everything you see' if the question is vague like 'what do you see'). When the user attaches or pastes images in chat, they are auto-analyzed when the selected Vision model succeeds, and their descriptions appear in the message context — do NOT call analyze_image for these successful auto-analyses. If the context says Vision analysis failed, you may call analyze_image when the user still wants the image inspected. Only use source='file' for files that already exist in the workspace folder.
- For a web page, use source='browser': it looks at the page open in Row-Bot's browser (open it with browser_navigate first) and asks nothing. Never capture the screen to see a page you opened in the browser.
- To compare or review several pictures, pass them together in files (up to 8: chat files by name, workspace paths, 'browser', rec-…, edit-…); a recording or video gives frames. For more, or to save tokens, set contact_sheet: they are tiled into one numbered picture the person also sees, so refer to them by number.
04 同仓库更多 Skills
x_guide
Essential guidance for using X (Twitter) tools correctly — search syntax, time filtering, and engagement patterns.
★ 1.7k
workflow_guide
How workflows run (scheduled chats), how to write and change them, hand work between them, and check what a run did.
★ 1.7k
wiki_guide
Guidance for the Obsidian-compatible wiki vault.
★ 1.7k
weather_guide
Guidance for using weather tools effectively.
★ 1.7k
video_guide
Guidance for generating videos and animating images.
★ 1.7k
video_editing_guide
Guidance for making videos with video and editing them with edit_video.
★ 1.7k