pdf-verification
Verify PDF page counts and file integrity programmatically using PyPDF2 after generation
- License 许可
- MIT
- 所属仓库
- HKUDS/AgentPilot
- 最近更新
- 2026-11-12
- Stars
- ★ 8.0k
- Forks
- 944
01 前言 Front Matter
- name
- pdf-verification
- description
- Verify PDF page counts and file integrity programmatically using PyPDF2 after generation
02 资源文件 1
- 其他.skill_id30 B
03 SKILL.md 正文
PDF Verification Skill
Purpose
After generating PDF files, always verify page counts and file integrity programmatically before declaring task completion. This catches formatting issues, empty pages, and corrupted files early.
When to Use
- After any PDF generation task
- When specific page counts are required
- Before marking a PDF-related task as complete
Verification Steps
1. Install PyPDF2 (if needed)
pip install PyPDF2
2. Verify Page Count and Integrity
Use run_shell to execute a Python verification script:
python -c "
from PyPDF2 import PdfReader
import sys
def verify_pdf(filepath, expected_pages=None):
try:
reader = PdfReader(filepath)
actual_pages = len(reader.pages)
print(f'✓ {filepath}: {actual_pages} pages')
if expected_pages and actual_pages != expected_pages:
print(f'✗ Page count mismatch: expected {expected_pages}, got {actual_pages}')
return False
# Check file is not empty/corrupted
if actual_pages == 0:
print(f'✗ Empty PDF: {filepath}')
return False
return True
except Exception as e:
print(f'✗ Error reading {filepath}: {e}')
return False
# Verify each PDF
results = []
results.append(verify_pdf('output.pdf', expected_pages=2))
print(f'All checks passed: {all(results)}')
sys.exit(0 if all(results) else 1)
"
3. Verify Multiple PDFs
For tasks with multiple PDFs, verify each one:
python -c "
from PyPDF2 import PdfReader
pdfs = {
'listings.pdf': 2,
'map.pdf': 1,
'summary.pdf': 1
}
all_passed = True
for filepath, expected in pdfs.items():
try:
reader = PdfReader(filepath)
actual = len(reader.pages)
status = '✓' if actual == expected else '✗'
print(f'{status} {filepath}: {actual}/{expected} pages')
if actual != expected:
all_passed = False
except Exception as e:
print(f'✗ {filepath}: {e}')
all_passed = False
print(f'Verification: {\"PASSED\" if all_passed else \"FAILED\"}')
"
4. Check File Size (Optional)
Add file size validation to catch empty or near-empty files:
python -c "
import os
from PyPDF2 import PdfReader
filepath = 'output.pdf'
min_size = 1000 # minimum bytes
file_size = os.path.getsize(filepath)
if file_size < min_size:
print(f'✗ File too small: {file_size} bytes')
else:
reader = PdfReader(filepath)
print(f'✓ {filepath}: {len(reader.pages)} pages, {file_size} bytes')
"
Best Practices
- Verify immediately after generation - Don't wait until the end of the task
- Check all required PDFs - Verify each file meets specifications
- Fail fast - If verification fails, regenerate before proceeding
- Log results - Print verification results for debugging
- Set reasonable minimums - Use file size checks to catch empty outputs
Common Issues Caught
- Wrong page counts (extra blank pages, missing content)
- Corrupted or unreadable PDF files
- Empty PDFs (0 pages)
- Files that appear generated but contain no actual content
Example Task Completion Check
# Final verification before marking task complete
python -c "
from PyPDF2 import PdfReader
import sys
required = {'listings.pdf': 2, 'map.pdf': 1}
passed = True
for f, pages in required.items():
try:
actual = len(PdfReader(f).pages)
if actual != pages:
print(f'FAIL: {f} has {actual} pages, expected {pages}')
passed = False
except Exception as e:
print(f'FAIL: Cannot read {f}: {e}')
passed = False
if passed:
print('SUCCESS: All PDFs verified')
sys.exit(0)
else:
sys.exit(1)
"
04 同仓库更多 Skills
agentpilot
Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.
remember
Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.
skill-discovery
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
delegate-task
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.
write-special-chars-ts-check
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.
write-special-chars-readback
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.