Document Handler

Read, extract text and metadata, and convert documents in formats like PDF, DOCX, XLSX, PPTX, EPUB, RTF, and OpenDocument.

Security Scan

The skill's scripts and instructions match its stated purpose (extracting text/metadata and converting documents); no hidden endpoints, credentials, or installation of remote code are present, though it relies on many external CLI tools that are not declared and a couple of platform-specific commands.

Purpose & Capability

The name/description (document extraction and conversion) aligns with the included scripts and SKILL.md examples. However, the skill references many external CLI tools (pdftotext, pdfinfo, pdftoppm, unzip, textutil, lynx, tesseract, etc.) but declares no required binaries; the absence of declared required binaries is a documentation/packaging omission rather than a functional mismatch.

Instruction Scope

SKILL.md and scripts explicitly instruct the agent to read local files, extract metadata and text, and convert PDFs to images. These actions are within the stated purpose. The README triggers on mentions of file paths which could cause frequent activations, but that behavior is consistent with a document-handler skill.

Install Mechanism

There is no install spec (instruction-only plus two local scripts). Nothing is downloaded or written by an installer. The scripts only call local command-line tools; no remote code fetch or archive extraction from external URLs is present.

Credentials

The skill requests no environment variables or credentials and the scripts do not read any env vars or config paths. This is proportionate to the document-processing purpose.

Persistence & Privilege

The skill is not always-enabled and does not request elevated persistence. It does include a trigger definition (activate on mentions of document files) which is normal for an invocable skill; nothing in the files attempts to modify other skills or system-wide settings.

Assessment

This skill appears to do what it says: extract text/metadata and convert documents. Before installing, be aware of the following: (1) it relies on many external CLI tools (pdftotext, pdfinfo, pdftoppm, unzip, textutil, lynx, tesseract, etc.) which are not declared — make sure those tools are available on your system or the commands will fail; (2) textutil is macOS-specific and some examples assume tools that may not exist on Linux/Windows; (3) extracted metadata can contain sensitive info (author, timestamps) — avoid passing files with secrets unless you trust the runtime; (4) the SKILL.md states it triggers on mentions of file paths, so consider whether you want automatic invocation in your agent. If you need higher assurance, review and run the two included scripts locally in a safe environment to confirm behavior.

Extract text, metadata, and content from any document format.

Supported Formats

Format	Extensions	Text Extract	Metadata	Convert
PDF	.pdf	✅ pdftotext	✅ pdfinfo	✅ pdftoppm
Word	.docx	✅ unzip + xml	✅	✅
Excel	.xlsx	✅ unzip + xml	✅	✅
PowerPoint	.pptx	✅ unzip + xml	✅	✅
EPUB	.epub	✅ unzip + html	✅	✅
RTF	.rtf	✅ textutil	✅	✅
OpenDocument	.odt, .ods, .odp	✅ unzip + xml	✅	✅

Quick Commands

PDF

# Extract text
pdftotext -layout input.pdf output.txt

# Get metadata
pdfinfo input.pdf

# Convert to images (for OCR or viewing)
pdftoppm -png input.pdf output_prefix

# Extract specific pages
pdftotext -f 5 -l 10 -layout input.pdf output.txt

DOCX/XLSX/PPTX (Office Open XML)

# Extract text from DOCX
unzip -p input.docx word/document.xml | sed 's/<[^>]*>//g' | tr -s ' \n'

# Extract text from XLSX (all sheets)
unzip -p input.xlsx xl/sharedStrings.xml | sed 's/<[^>]*>//g' | tr -s '\n'

# Extract text from PPTX
unzip -p input.pptx ppt/slides/*.xml | sed 's/<[^>]*>//g' | tr -s ' \n'

# Get metadata
unzip -p input.docx docProps/core.xml

RTF (macOS)

# Convert RTF to plain text
textutil -convert txt input.rtf -output output.txt

# Convert RTF to HTML
textutil -convert html input.rtf -output output.html

EPUB

# Extract and read EPUB content
unzip -l input.epub                    # List contents
unzip -p input.epub "*.html" | lynx -stdin -dump  # Text via lynx
unzip -p input.epub "*.xhtml" | sed 's/<[^>]*>//g'  # Raw text

OpenDocument (ODT/ODS/ODP)

# Extract text from ODT
unzip -p input.odt content.xml | sed 's/<[^>]*>//g' | tr -s ' \n'

# Extract from ODS
unzip -p input.ods content.xml | sed 's/<[^>]*>//g'

# Get metadata
unzip -p input.odt meta.xml

Scripts

extract_document.sh

Extracts text and metadata from any supported document format.

~/Dropbox/jarvis/skills/document-handler/scripts/extract_document.sh <file>

Output:

• Text content to stdout
• Metadata as JSON comments

pdf_to_images.sh

Converts PDF pages to images for OCR or visual processing.

~/Dropbox/jarvis/skills/document-handler/scripts/pdf_to_images.sh <pdf> <output_dir> [dpi]

Workflow

1. Identify format — Check file extension
2. Extract text — Use appropriate tool
3. Get metadata — Author, date, pages, etc.
4. Process content — Summarize, search, transform

Notes

• PDFs with scanned images need OCR (pdftoppm + tesseract)
• Encrypted PDFs require password
• Complex formatting may be lost in text extraction
• For tables in PDFs, consider tabula or camelot