DOCX Toolkit

Extract text, tables, and images from .docx and legacy .doc files. Handles large documents, CJK text, and complex table structures. Includes deduplication an...

Security Scan

The skill's code, instructions, and dependency list are coherent with its stated purpose (extracting text, tables, and images from .docx/.doc); no unexpected network access or credential requests were found.

Purpose & Capability

Name/description match the included scripts: extract_text.py, extract_doc_text.py, extract_images.py, and resize_images.py. Declared Python libraries (python-docx, olefile, Pillow) are appropriate for the stated functionality. No unrelated binaries, env vars, or external services are requested.

Instruction Scope

SKILL.md only instructs running the included scripts on local files and directories. The scripts read input document files, write extracted text/images to an output directory, and optionally write a JSON manifest. This is within scope. Notes: extract_doc_text reads raw OLE streams and may use significant RAM for very large .doc files; resize_images will overwrite files if output_dir is omitted; classify_by_context uses heuristic keyword matching (mostly Chinese keywords) and can misclassify. The scripts do not contact external endpoints or read environment variables.

Install Mechanism

No install spec is provided (instruction-only), and the code is bundled with the skill. Dependencies are normal Python packages installable via pip. No downloads from arbitrary URLs or archive extraction are present.

Credentials

The skill requests no environment variables, credentials, or special config paths. All required resources are local files and standard Python packages, which is proportionate to the functionality.

Persistence & Privilege

The skill is not always-enabled and does not request persistent or elevated platform privileges. It does not alter other skills' configuration or require platform-wide settings.

Assessment

This skill appears to do what it claims: local extraction of text, tables, and images from Word files. Before using on sensitive content, consider: run it on a sandbox or isolated environment for untrusted documents; expect the scripts to write files to the specified output_dir and note that resize_images overwrites in-place by default; very large legacy .doc files may use a lot of RAM; image extraction can pull out sensitive items (IDs, certificates)—review outputs before uploading anywhere; classification is heuristic and language-specific (may mislabel). No network exfiltration or secret usage was observed in the code. If you require stronger assurance, inspect the bundled scripts locally or run them in a container.

A complete toolkit for processing Microsoft Word documents (.docx and legacy .doc formats).

Capabilities

1. Text + Table Extraction (.docx)

python3 {baseDir}/scripts/extract_text.py input.docx output.txt

Extracts all paragraphs and tables with structure preserved. Tables are formatted as pipe-delimited rows for easy parsing.

2. Text Extraction (Legacy .doc)

python3 {baseDir}/scripts/extract_doc_text.py input.doc output.txt

Handles legacy OLE2 .doc format using olefile. Extracts Unicode text from the WordDocument stream.

3. Image Extraction (.docx)

python3 {baseDir}/scripts/extract_images.py input.docx output_dir/

Extracts all embedded images with:

• Automatic deduplication (MD5 hash comparison)
• Size filtering (skips tiny icons <5KB by default)
• Sequential renaming (img_001.png, img_002.jpg, etc.)

4. Image Compression

python3 {baseDir}/scripts/resize_images.py input_dir/ output_dir/ [--max-width 1024]

Batch resize/compress images for API processing (saves 50-70% on vision API costs).

Dependencies

• Python 3.6+
• python-docx — for .docx processing
• olefile — for legacy .doc processing
• Pillow — for image resizing (optional, only needed for resize script)

Install:

pip3 install python-docx olefile Pillow

Use Cases

• Document analysis: Extract text for AI review/summarization
• Migration: Pull content from Word docs into other formats
• Image audit: Extract and review all embedded images
• Cost optimization: Compress images before sending to vision APIs
• Batch processing: Process multiple documents in a pipeline

Notes

• Large .doc files (>200MB) may require significant RAM for olefile processing
• Image extraction preserves original format (png/jpg/gif/etc.)
• Deduplication catches exact duplicates; near-duplicates still pass through
• CJK (Chinese/Japanese/Korean) text is fully supported in both extractors