screenshot
Capture desktop, window, or region screenshots when browser-level capture is unavailable or the user explicitly wants OS-level evidence.
来源信息
- 仓库
- Calvin-Corbett/thomas
- 最近来源活动
- 2026年9月9日 02:49
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 4
- 分支
- 0
安装方式
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。
检查来源文件
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。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- screenshot
- description
- Capture desktop, window, or region screenshots when browser-level capture is unavailable or the user explicitly wants OS-level evidence.
# Screenshot
Use this skill when Thomas needs an OS-level screenshot of the desktop, a window, or a specific screen region.
## Workflow
1. Confirm the target surface and the reason the screenshot is needed.
2. Capture the smallest scope that answers the question or proves the issue.
3. Name or organize the artifact clearly if multiple captures are involved.
4. Review the image to ensure the relevant UI state is actually visible.
5. Reference the screenshot directly in the follow-up explanation.
## Rules
- Do not capture broad desktop state when a narrower region is enough.
- Use screenshots as evidence, not as a substitute for analysis.
在 GitHub 查看