AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Photo → Scanned PDF

Turns phone photos of paper documents into clean, scanner-looking A4 PDFs — with content-based page ordering and a mandatory full-document check.

Docs & OfficeIntermediate★ 1,323⑂ 212AI score 10/10Last updated: Aug 8, 2026

What it does

  • Runs phone photos of contracts, stamped certificates, receipts, forms and handwritten notes through perspective rectification → noteshrink background whitening → A4 PDF assembly.
  • Orders pages by reading their content (dates, titles, page numbers) instead of trusting filenames, since batch-exported photos share timestamps and can even be fully reversed.
  • Routes colored paper stock through a white-balance pre-pass so black ink stops reading blue-purple and red stamps stop reading maroon, and keeps colored pages out of the global palette batch.
  • Forces a contact-sheet review of every page before delivery, catching wrong-slot overwrites and palette-poisoning bugs that per-page checks miss.
  • Includes a second branch for synthesizing a handwriting-style signature onto an unsigned digital document so it looks signed and scanned.

Who it's for

  • Anyone who has to submit paperwork with only a phone camera and no scanner.
  • Admin, HR and finance staff who regularly digitize contracts and receipts.
  • Terminal-comfortable users (brew, uv) who prefer a scriptable pipeline over paid scanner apps.

Examples

  1. "Turn these 17 photos of a signed contract into a scanned PDF" → pages reordered by content, output as a flat-white A4 PDF.
  2. "Replace page 5 of this existing scanned PDF with a new photo" → reprocess just that page, then re-verify the whole document.
  3. "This form was printed on blue paper and the ink looks purple — fix it" → colored-paper branch with white-balance pre-pass.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/daymade-docs/photo-to-scanned-pdf/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the daymade-docs/photo-to-scanned-pdf folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/photo-to-scanned-pdf/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-docs/photo-to-scanned-pdf ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/daymade/claude-code-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy this skill only: cp -r claude-code-skills/daymade-docs/photo-to-scanned-pdf ~/.claude/skills/
  5. Install dependencies (macOS): brew install poppler, plus brew install uv if you don't have uv.
  6. Warm up the enhancer: uvx noteshrink --help (first run takes ~30s).
  7. Restart Claude Code and ask something like "make these photos look scanned as a PDF" to trigger the skill.
View source on GitHub ↗License: MIT