Pdf workflow

Skill EigenCharlie/pdf-toolkit-mcp/skills/pdf-workflow

Multi-step PDF workflows using the pdf-toolkit MCP server. Use when the user wants to combine, convert, secure, OCR, or reshape PDFs and the task spans more than one tool call (e.g., "merge these PDFs and compress", "scan and OCR then convert to Word", "compress and password-protect"). Do NOT trigger for single-tool asks — call the MCP tool directly.From its SKILL.md

Install

npx -y skills add EigenCharlie/pdf-toolkit-mcp --skill pdf-workflow

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.3 KB, as published. Nobody here has run it

PDF Workflow

Orchestrates common multi-step PDF pipelines using the pdf-toolkit MCP server. Each workflow calls the 18 MCP tools in a specific order.

When to use

Assemble: merge many PDFs then optimize the result
Convert + secure: turn an Office doc into a watermarked, password-protected PDF
Scan cleanup: repair a broken scan, OCR it, add page numbers
Prep for email: aggressively compress + lock with a password
Extract + OCR: pull specific pages then OCR them into Word

Assumed tools

merge_pdf, split_pdf, compress_pdf
pdf_to_word, pdf_to_excel, pdf_to_powerpoint, pdf_to_jpg
office_to_pdf, html_to_pdf, image_to_pdf
rotate_pdf, add_page_numbers, extract_pdf_pages
unlock_pdf, protect_pdf, repair_pdf
add_watermark, ocr_pdf

All tools accept input_file or input_files (absolute or CWD-relative paths) and an optional output_path.

Workflow 1: Assemble

Goal: combine N PDFs into one, then shrink, and optionally protect.

Call merge_pdf(input_files=[...], output_path="<tmp>/merged.pdf").
Call compress_pdf(input_file="<tmp>/merged.pdf", compression_level="recommended", output_path=<final>).
Optionally call protect_pdf(input_file=<final>, password=<user-provided>).

Workflow 2: Convert and secure

Goal: turn a Word/Excel/PPT file into a watermarked, password-protected PDF.

office_to_pdf(input_file=<file>) → <raw.pdf>.
add_watermark(input_file=<raw.pdf>, mode="text", text="CONFIDENTIAL") → <wm.pdf>.
protect_pdf(input_file=<wm.pdf>, password=<pw>) → final.

Workflow 3: Extract and OCR

Goal: pull specific pages from a PDF, OCR them, then convert to Word.

extract_pdf_pages(input_file=<src>, pages="3,5-9") → <sub.pdf>.
ocr_pdf(input_file=<sub.pdf>, languages=["eng"]) → <ocr.pdf>. (warn: slow for many pages)
pdf_to_word(input_file=<ocr.pdf>) → final.docx.

Workflow 4: Prep for email

Goal: shrink a PDF aggressively and lock it behind a password.

compress_pdf(input_file=<src>, compression_level="extreme") → <small.pdf>.
protect_pdf(input_file=<small.pdf>, password=<pw>) → final.

Workflow 5: Scan cleanup

Goal: fix a corrupt scan, OCR it, then number the pages.

repair_pdf(input_file=<scan>) → <fixed.pdf>.
ocr_pdf(input_file=<fixed.pdf>, languages=["eng"]) → <ocr.pdf>.
add_page_numbers(input_file=<ocr.pdf>, starting_number=1, horizontal_position="center", vertical_position="bottom") → final.

Notes

If credentials are missing the tool call fails with MISSING_CREDENTIALS. Tell the user to set ILOVEAPI_PROJECT_PUBLIC_KEY and ILOVEAPI_PROJECT_SECRET_KEY env vars and restart Claude Code.
ocr_pdf and large-PDF operations can exceed 60s. Mention that to the user before kicking off.
Always prefer absolute paths. If the user gave relative paths, resolve against their CWD.
Always report the final output path back to the user in your reply.