메뉴
DOCX: Read text, tables, and metadata from a Word document.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
cURL (curl): Command-line web browser alternative. Fetch webpage HTML, test site connectivity, bypass basic bot detection, and read public web content directly from the terminal.
Python as a general-purpose problem-solving capability — use it to DO things (CV, parsing, APIs, data), not just to write programs. When stuck, reach for Python and install what you need into your dedicated Tool Environment. if you need a new package and you are unsure. ask the user for guidance and confirm before installing.
GitHub CLI (gh): Manage pull requests, issues, repositories, workflows, and releases from the terminal.
DOCX: Create a new Word document with headings, paragraphs, tables, and lists.
DOCX: Edit an existing Word document — append content, replace text, or add tables.
Google Calendar: Show upcoming events across all calendars.
SOC 직업 분류 기준
| name | docx-read |
| description | DOCX: Read text, tables, and metadata from a Word document. |
| metadata | {"version":"0.22.0","openclaw":{"category":"productivity","requires":{"bins":["python"]}},"maxent":{"requires":{"bins":[{"name":"python","install":{"windows":{"method":"winget","id":"Python.Python.3"},"linux":{"method":"apt","id":"python3"},"darwin":{"method":"brew","id":"python"}}}]}}} |
PREREQUISITE: Ensure
python-docxis installed:pip install python-docx
Read text, tables, and metadata from a .docx Word document.
python - <<'EOF'
from docx import Document
doc = Document("path/to/file.docx")
for para in doc.paragraphs:
print(para.text)
EOF
python - <<'EOF'
from docx import Document
doc = Document("report.docx")
for para in doc.paragraphs:
if para.text.strip():
print(para.text)
EOF
python - <<'EOF'
from docx import Document
doc = Document("report.docx")
for para in doc.paragraphs:
if para.text.strip():
print(f"[{para.style.name}] {para.text}")
EOF
python - <<'EOF'
from docx import Document
doc = Document("report.docx")
for i, table in enumerate(doc.tables):
print(f"--- Table {i+1} ---")
for row in table.rows:
print([cell.text for cell in row.cells])
EOF
python - <<'EOF'
import csv, sys
from docx import Document
doc = Document("report.docx")
writer = csv.writer(sys.stdout)
for i, table in enumerate(doc.tables):
print(f"# Table {i+1}")
for row in table.rows:
writer.writerow([cell.text.strip() for cell in row.cells])
EOF
python - <<'EOF'
from docx import Document
doc = Document("report.docx")
cp = doc.core_properties
print("Title: ", cp.title)
print("Author: ", cp.author)
print("Created:", cp.created)
print("Modified:", cp.modified)
print("Subject:", cp.subject)
EOF
python - <<'EOF'
from docx import Document
doc = Document("report.docx")
print("=== PARAGRAPHS ===")
for para in doc.paragraphs:
if para.text.strip():
print(f"[{para.style.name}] {para.text}")
print("\n=== TABLES ===")
for i, table in enumerate(doc.tables):
print(f"--- Table {i+1} ---")
for row in table.rows:
print([cell.text.strip() for cell in row.cells])
EOF
doc.paragraphs includes headings; check para.style.name to distinguish (e.g. "Heading 1", "Normal").doc.tables — iterate cell.tables if needed.para.runs to access individual text runs with font/bold/italic details.