Extract text from PDFs using shell tools when read_file fails
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./benchmarks/gdpval/skills/pdf-text-extraction/SKILL.mdUse this skill when read_file with filetype='pdf':
The built-in PDF handler is unreliable for structured text extraction. Shell-based tools provide more robust alternatives.
# Extract text from PDF to stdout
pdftotext /path/to/file.pdf -
# Extract text to a file
pdftotext /path/to/file.pdf output.txt
# Preserve layout (maintains spacing/structure)
pdftotext -layout /path/to/file.pdf output.txtUsage in agent:
run_shell command="pdftotext -layout /path/to/document.pdf -"# Get PDF metadata (pages, author, creation date, etc.)
pdfinfo /path/to/file.pdfUsage in agent:
run_shell command="pdfinfo /path/to/document.pdf"import fitz # PyMuPDF
doc = fitz.open("/path/to/file.pdf")
text = ""
for page in doc:
text += page.get_text()
doc.close()
print(text)Usage in agent:
run_shell command="python3 -c \"import fitz; doc=fitz.open('file.pdf'); print(''.join(p.get_text() for p in doc))\""import pdfplumber
with pdfplumber.open("/path/to/file.pdf") as pdf:
for page in pdf.pages:
text = page.extract_text()
tables = page.extract_tables() # For tabular dataUsage in agent:
run_shell command="python3 -c \"import pdfplumber; pdf=pdfplumber.open('file.pdf'); print(''.join(p.extract_text() or '' for p in pdf.pages))\""Try pdftotext first - Fastest and most reliable for plain text
run_shell command="pdftotext -layout /path/to/file.pdf -"If pdftotext unavailable, check for Python libraries
run_shell command="python3 -c \"import fitz; print('PyMuPDF available')\""For table/structured data, use pdfplumber
run_shell command="python3 -c \"import pdfplumber; ...\""Verify extraction succeeded - Check output contains readable text, not binary data
If tools are not available:
# Ubuntu/Debian
apt-get install poppler-utils # pdftotext, pdfinfo
# Install Python libraries
pip install pymupdf pdfplumberread_file with filetype='pdf' for critical text extraction# Step 1: Try pdftotext
RESULT=$(pdftotext -layout /path/to/form.pdf - 2>/dev/null)
# Step 2: Verify we got text, not error
if [ -z "$RESULT" ]; then
# Fallback to Python
RESULT=$(python3 -c "import fitz; doc=fitz.open('/path/to/form.pdf'); print(''.join(p.get_text() for p in doc))")
fi
# Step 3: Use extracted text
echo "$RESULT"HKUDS/OpenSpace
3827781
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.