跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

data-extractor

>

claude-office-skills · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add claude-office-skills/skills --skill data-extractor

技能说明


═══════════════════════════════════════════════════════════════════════════════

CLAUDE OFFICE SKILL - Enhanced Metadata v2.0

═══════════════════════════════════════════════════════════════════════════════

Basic Information

name: data-extractor description: ">" version: "1.0" author: claude-office-skills license: MIT

Categorization

category: parsing tags:

  • extraction
  • data
  • unstructured department: All

AI Model Compatibility

models: recommended: - claude-sonnet-4 - claude-opus-4 compatible: - claude-3-5-sonnet - gpt-4 - gpt-4o

MCP Tools Integration

mcp: server: office-mcp tools: - extract_text_from_pdf - extract_tables_from_pdf

Skill Capabilities

capabilities:

  • data_extraction
  • format_handling

Language Support

languages:

  • en
  • zh

Data Extractor Skill

Overview

This skill enables extraction of structured data from any document format using unstructured - a unified library for processing PDFs, Word docs, emails, HTML, and more. Get consistent, structured output regardless of input format.

How to Use

  1. Provide the document to process
  2. Optionally specify extraction options
  3. I'll extract structured elements with metadata

Example prompts:

  • "Extract all text and tables from this PDF"
  • "Parse this email and get the body, attachments, and metadata"
  • "Convert this HTML page to structured elements"
  • "Extract data from these mixed-format documents"

Domain Knowledge

unstructured Fundamentals

from unstructured.partition.auto import partition

# Automatically detect and process any document
elements = partition("document.pdf")

# Access extracted elements
for element in elements:
    print(f"Type: {type(element).__name__}")
    print(f"Text: {element.text}")
    print(f"Metadata: {element.metadata}")

Supported Formats

FormatFunctionNotes
PDFpartition_pdfNative + scanned
Wordpartition_docxFull structure
PowerPointpartition_pptxSlides & notes
Excelpartition_xlsxSheets & tables
Emailpartition_emailBody & attachments
HTMLpartition_htmlTags preserved
Markdownpartition_mdStructure preserved
Plain Textpartition_textBasic parsing
Imagespartition_imageOCR extraction

Element Types

from unstructured.documents.elements import (
    Title,
    NarrativeText,
    Text,
    ListItem,
    Table,
    Image,
    Header,
    Footer,
    PageBreak,
    Address,
    EmailAddress,
)

# Elements have consistent structure
element.text           # Raw text content
element.metadata       # Rich metadata
element.category       # Element type
element.id            # Unique identifier

Auto Partition

from unstructured.partition.auto import partition

# Process any file type
elements = partition(
    filename="document.pdf",
    strategy="auto",          # or "fast", "hi_res", "ocr_only"
    include_metadata=True,
    include_page_breaks=True,
)

# Filter by type
titles = [e for e in elements if isinstance(e, Title)]
tables = [e for e in elements if isinstance(e, Table)]

Format-Specific Partitioning

# PDF with options
from unstructured.partition.pdf import partition_pdf

elements = partition_pdf(
    filename="document.pdf",
    strategy="hi_res",              # High quality extraction
    infer_table_structure=True,     # Detect tables
    include_page_breaks=True,
    languages=["en"],               # OCR language
)

# Word documents
from unstructured.partition.docx import partition_docx

elements = partition_docx(
    filename="document.docx",
    include_metadata=True,
)

# HTML
from unstructured.partition.html import partition_html

elements = partition_html(
    filename="page.html",
    include_metadata=True,
)

Working with Tables

from unstructured.partition.auto import partition

elements = partition("report.pdf", infer_table_structure=True)

# Extract tables
for element in elements:
    if element.category == "Table":
        print("Table found:")
        print(element.text)
        
        # Access structured table data
        if hasattr(element, 'metadata') and element.metadata.text_as_html:
            print("HTML:", element.metadata.text_as_html)

Metadata Access

from unstructured.partition.auto import partition

elements = partition("document.pdf")

for element in elements:
    meta = element.metadata
    
    # Common metadata fields
    print(f"Page: {meta.page_number}")
    print(f"Filename: {meta.filename}")
    print(f"Filetype: {meta.filetype}")
    print(f"Coordinates: {meta.coordinates}")
    print(f"Languages: {meta.languages}")

Chunking for AI/RAG

from unstructured.partition.auto import partition
from unstructured.chunking.title import chunk_by_title
from unstructured.chunking.basic import chunk_elements

# Partition document
elements = partition("document.pdf")

# Chunk by title (semantic chunks)
chunks = chunk_by_title(
    elements,
    max_characters=1000,
    combine_text_under_n_chars=200,
)

# Or basic chunking
chunks = chunk_elements(
    elements,
    max_characters=500,
    overlap=50,
)

for chunk in chunks:
    print(f"Chunk ({len(chunk.text)} chars):")
    print(chunk.text[:100] + "...")

Batch Processing

from unstructured.partition.auto import partition
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor

def process_document(file_path):
    """Process single document."""
    try:
        elements = partition(str(file_path))
        return {
            'file': str(file_path),
            'status': 'success',
            'elements': len(elements),
            'text': '\n\n'.join([e.text for e in elements])
        }
    except Exception as e:
        return {
            'file': str(file_path),
            'status': 'error',
            'error': str(
阅读完整来源 ↗