메뉴
Linux GUI app automation on a virtual X display. Launch non-browser Linux GUI apps in Docker, see screenshots, and interact by pixel coordinates.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Use whenever the user asks to build a web page, landing page, dashboard, form, or any frontend UI — whether from scratch or by redesigning an existing interface. Helps with aesthetic direction, typography, color palettes, layout, and making choices that don't read as templated defaults. Also trigger when the user says 'design a page', 'make a UI', 'build a frontend', 'redesign this', 'make it look good', or wants HTML/CSS for a visual interface.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck,' 'slides,' 'presentation,' or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Create new skills, modify and improve existing skills. Use when users want to create a skill from scratch, edit, or optimize an existing skill. Also trigger when the user says 'create a skill', 'make a skill', 'improve this skill', 'update skill', 'turn this into a skill', or when a task is important and likely to repeat.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like 'the xlsx in my downloads') — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
| name | xvfb |
| description | Linux GUI app automation on a virtual X display. Launch non-browser Linux GUI apps in Docker, see screenshots, and interact by pixel coordinates. |
Use xvfb_gui for non-browser Linux GUI programs inside Docker: small desktop utilities, installers, dialogs, editors, or test apps that need an X display.
For web browsing, use browser-use. Do not route normal browser work through Xvfb.
Xvfb, xdotool, xterm, x11-apps, and ImageMagick import.One Xvfb display is shared by launched apps. The tool returns screenshots when the model supports vision. Coordinates are pixels from the top-left of the root window.
1. xvfb_gui action=launch app="xterm"
-> auto-creates the Xvfb session, launches the app, returns a screenshot
2. Look at the screenshot and choose pixel coordinates.
3. xvfb_gui action=click x=420 y=310
-> clicks and returns a new screenshot
4. xvfb_gui action=type text="echo hello"
5. xvfb_gui action=key key="Return"
6. xvfb_gui action=close
Always verify with a screenshot after meaningful actions.
# App lifecycle
xvfb_gui action=launch app="<command with args>" # e.g. "xterm" or "xclock"
xvfb_gui action=kill_app pid=<pid>
# Observation and interaction
xvfb_gui action=screenshot
xvfb_gui action=click x=420 y=310 [button=1|2|3] [double=true] [settle_ms=1000]
xvfb_gui action=drag x1=100 y1=200 x2=500 y2=400 [settle_ms=1000]
xvfb_gui action=type text="hello world"
xvfb_gui action=key key="Return"
xvfb_gui action=scroll x=640 y=400 [amount=3] [direction=up|down]
# Cleanup
xvfb_gui action=close
All interaction actions accept settle_ms in milliseconds. It defaults to 700 and is capped at 10000.
key, type, click, drag, and scroll; there are no app-specific shortcuts.settle_ms for slow dialogs or apps that animate.close when done so the Xvfb process and launched apps are cleaned up.