Rylai PDF
SkillFiles & storageCreate, inspect, extract, merge, split, rotate, and render PDF files with local open-source tools, including structural and visual verification.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Rylai PDF skill
What this skill tells your AI
The instructions your AI receives, as published by rylaispirit/rylai-codex-hermes-skills in skills/pdf/SKILL.md and read by ahel’s review.
Original Codex-Hermes-Claude skill by Rylai.
Use local files and deterministic tools. Preserve the source document unless the user explicitly requests an in-place replacement. Never invent passwords, embed credentials, or upload documents to an external service without direct approval.
Runtime
Use Python 3 with:
pypdffor page-level inspection and editing.pdfplumberwhen higher-quality text extraction is useful.pypdfium2or Popplerpdftoppmfor optional page rendering.- LibreOffice only when converting an Office source into PDF.
Probe before installing:
python -c "import pypdf; print(pypdf.__version__)"
python -c "import pdfplumber; print(pdfplumber.__version__)"
Install only missing Python packages:
python -m pip install pypdf pdfplumber pypdfium2
Resolve scripts/rylai_pdf.py relative to this skill directory.
Workflow
- Confirm the input path, requested operation, output path, and page range.
- Run
infobefore editing an unfamiliar or encrypted PDF. - Write to a new output path. Use
--forceonly when replacement is intended. - Re-open the result and check page count, metadata, and extracted text where applicable.
- For layout-sensitive work, render representative pages and inspect the PNG output.
- Report skipped checks when Poppler, LibreOffice, OCR, or another optional dependency is absent.
For scanned pages with no useful text layer, use an available local OCR engine. Keep the original PDF and state which OCR tool and language model were used.
Bundled CLI
Inspect:
python scripts/rylai_pdf.py info input.pdf
Extract selected pages:
python scripts/rylai_pdf.py extract input.pdf output.txt --pages 1-3,7
Merge:
python scripts/rylai_pdf.py merge output.pdf first.pdf second.pdf
Split selected pages into individual files:
python scripts/rylai_pdf.py split input.pdf output-pages --pages 2-5
Rotate selected pages clockwise:
python scripts/rylai_pdf.py rotate input.pdf rotated.pdf 90 --pages 1,3
Render with local PDFium or Poppler:
python scripts/rylai_pdf.py render input.pdf rendered-pages --dpi 144
Add --password only when the user supplied the password for that document.
Quality Bar
- The output opens without repair warnings.
- Page order, count, rotation, and selected ranges match the request.
- Extracted text is not silently empty; scanned pages are identified.
- Rendered pages have no unexpected clipping or blank output.
- No source file, temporary file, password, or user path is bundled with the skill.
Signals
- GitHub stars
- 55
- Forks
- 41
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
pdf-rylaispirit- Source
- github.com/rylaispirit/rylai-codex-hermes-skills