메뉴
Create and edit Word documents (.docx): headings, styled paragraphs, tables, images, headers/footers, and page formatting. Use whenever the user asks to write, format, or modify a Word/.docx document.
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
Pilot PubCommander editorial and social campaigns through its MCP tools. Use for listing, drafting, revising, submitting, scheduling, or publishing posts while preserving human approval and dry-run safety.
Analyze tabular data and render charts (bar, line, scatter, pie, histogram) to PNG/SVG with pandas + matplotlib. Use whenever the user wants to plot, chart, graph, or visualize data from a CSV/JSON/Excel file or inline numbers.
Autonomous multi-source web research: fetch several web pages, extract their main content, and synthesize a cited Markdown brief. Use whenever the user wants to research a topic, gather and compare sources, or produce a referenced write-up from the web.
Drive a real headless browser with Playwright (Python): navigate pages, screenshot, scrape rendered content, and fill/submit forms — with an optional Camoufox stealth backend. Use whenever the user wants to automate, scrape, or screenshot a website programmatically.
Read existing documents (PDF, Word, PowerPoint, Excel, HTML) and convert them into clean Markdown/plain text the agent can reason over: extract text, ingest a file, summarize a document. Use whenever the user wants to READ, extract, ingest, transcribe, or summarize the contents of an existing file (not create one).
Work with PDF files: extract text, merge/split/reorder pages, rotate, read form fields, and render pages to images. To author a formatted PDF, build a .docx/.pptx and convert it. Use whenever the user asks to read, combine, split, or produce a PDF.
| name | docx |
| description | Create and edit Word documents (.docx): headings, styled paragraphs, tables, images, headers/footers, and page formatting. Use whenever the user asks to write, format, or modify a Word/.docx document. |
| license | MIT (Code Buddy original skill) |
| nativeEngine | {"triggers":["word document","docx","word doc",".docx","write a document","report document"]} |
Build real .docx files with the open-source python-docx library
(python3 -c "import docx"). Work in visible steps; verify before reporting done.
bash tool) that assembles the
document with python-docx and saves it.Document(path) and assert key paragraphs/headings
exist; print(path).doc.add_heading('Title', level=0), level=1/2) so the
document has a proper outline — not just bold text.doc.add_table(rows, cols, style='Light Grid Accent 1'); bold the header row.doc.add_picture(path, width=Inches(5)); add a caption paragraph.doc.sections[0] when the user specifies them.python3 - <<'PY'
from docx import Document
from docx.shared import Pt, Inches
doc = Document()
doc.add_heading('Q2 Robotics Budget', level=0)
doc.add_heading('Overview', level=1)
doc.add_paragraph('Funding target: 120k EUR — status: on track.')
doc.add_heading('Line items', level=1)
t = doc.add_table(rows=1, cols=3); t.style = 'Light Grid Accent 1'
hdr = t.rows[0].cells
for i, h in enumerate(['Item', 'Cost', 'Status']):
hdr[i].text = h; hdr[i].paragraphs[0].runs[0].font.bold = True
for item, cost, status in [('Actuators', '8000', 'ordered'), ('Compute', '3500', 'done')]:
c = t.add_row().cells; c[0].text = item; c[1].text = cost; c[2].text = status
doc.save('report.docx')
assert Document('report.docx').paragraphs[0].text == 'Q2 Robotics Budget'
print('report.docx')
PY
Document(path).paragraphs / .tables, or python3 -m markitdown file.docx if available.save() back; preserve tracked
changes and comments where present.