PDF Toolkit

What it does

When your agent uses it

• Extracting text or tables from an existing PDF
• Merging, splitting, rotating or watermarking PDF pages
• Filling a fillable form or overlaying text onto a scanned one
• Building a new PDF report, invoice or certificate
• Running OCR over a scanned document

Example prompts

• “Extract all tables from ./reports/q3.pdf into CSV files.”
• “Merge cover.pdf and body.pdf, then rotate the last page.”
• “Fill in the W-9 form in ./forms/w9.pdf with my details.”
• “OCR the scanned contract in ./scans/contract.pdf so it becomes searchable.”

Requirements

• Python 3 with pypdf, pdfplumber, pypdfium2, reportlab and Pillow
• qpdf, only for merge, split, encrypt and repair tasks

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1PDF origin is bottom-left, image origin is top-left. Every "off by a
2. 2pypdf.extract_text() returns nothing for scans. That's not a bug —
3. 3**Unicode subscripts / superscripts render as black rectangles in
4. 4CJK text renders as black boxes when the font never registered.
5. 5XFA forms are not AcroForms. If probe_fields.py returns [] on a
6. 6writer.encrypt(pw) in pypdf uses RC4 by default. For real AES-256,

What it can do on your machine

Read from SKILL.md and the folder at commit 6babeb0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 11 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • brew
  • apt-get
  • qpdf
  • python3
  • uv
  • pdftotext

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PDF Toolkit loads about 1.7k tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 638 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~155

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from XiaomiMiMo/MiMo-Code at commit 6babeb0, republished under its Apache-2.0 licence (© XiaomiMiMo). 638 words, ~1,655 tokens.

name

pdf-official

description

Use this skill whenever a PDF file is being produced, opened, transformed, filled, or read. That includes: extracting text or tables from an existing PDF; combining, carving, rotating, cropping, or watermarking pages; composing a fresh PDF (report, invoice, certificate); filling AcroForm fields or overlaying text onto a non-fillable scanned form; encrypting or unlocking a PDF; running OCR over a scanned document; rendering pages to PNG/JPEG for visual analysis. Trigger on mentions of 'PDF', a filename ending in .pdf, requests like 'turn this into a PDF report', or references to AcroForm / form fields.

license

Apache-2.0 — see LICENSE for terms and third-party attributions

python3 -m pip install --upgrade pypdf pdfplumber pypdfium2 reportlab Pillow

# qpdf — merge/split/encrypt/repair, Apache-2.0
brew install qpdf                # macOS
apt-get install -y qpdf          # Debian / Ubuntu

# Tesseract — OCR for scanned PDFs, Apache-2.0
brew install tesseract
python3 -m pip install pytesseract pdf2image
apt-get install -y tesseract-ocr

# Poppler — pdftotext / pdftoppm / pdfimages, GPL-2.0
# Optional. Only install if you accept a GPL dependency at CLI level.
brew install poppler
apt-get install -y poppler-utils

scripts/survey.py path/to/file.pdf --pretty

{
  "path": "/abs/path/file.pdf",
  "page_count": 12,
  "is_locked": false,
  "form_field_count": 34,
  "looks_scanned": false,
  "metadata": {"Title": "...", "Author": "...", "Producer": "..."}
}

© XiaomiMiMo, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 17 other files (scripts) in packages/cli/src/skill/builtin/.bundle/pdf-official of XiaomiMiMo/MiMo-Code.

• SKILL.md
• LICENSE
• README.md
• compose.md
• extract.md
• interactive.md
• scripts/apply_values.py
• scripts/carve.py
• scripts/combine.py
• scripts/overlay_text.py
• scripts/probe_fields.py
• scripts/recognize.py
• scripts/render_pages.py
• scripts/reorient.py
• scripts/sanity_check.py
• scripts/survey.py
• scripts/text_dump.py
• transform.md

Open the folder on GitHubat commit 6babeb0