Does it work on scanned PDFs?

Yes. Scanned documents usually have no form fields, so the skill positions text directly on the page at the exact spot where each value belongs.

Do my documents leave my computer?

No. The skill fills PDFs locally, so the file and the data entered into it stay on the machine where the agent runs.

What kinds of PDF fields does it support?

It handles native AcroForm fields, per-character (comb) fields, and flat PDFs with no fields at all. For field-less or scanned documents it places text at precise page positions.

pdf-fill-studio

SkillDocs & knowledge

pdf-fill-studio is a skill that lets an AI agent fill out PDF forms. It works locally and covers native AcroForm fields as well as flat or scanned PDFs that have no form fields. A visual editor places each value precisely on the page, including per-character (comb) fields, so text lands exactly where it belongs.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add the pdf-fill-studio skill to the agent so it is available for document tasks.

Then ask your AI: use the pdf-fill-studio skill

What your AI can do with it

Fill PDF forms locally without uploading the file anywhere
Fill native AcroForm fields in standard PDF forms
Enter text on flat, field-less PDFs by positioning it on the page
Place values on scanned PDFs where no fields exist
Handle per-character (comb) fields that split entries into boxes
Adjust the exact position of each value in a visual editor

Getting started

Add the pdf-fill-studio skill to the agent so it is available for document tasks.
Have the PDF form file saved locally, since the skill fills it on the machine where it runs.
Give the agent the values to enter and any instructions about where they should go.
Use the visual editor to check where each value was placed and adjust positions as needed.
Keep the filled PDF, or ask the agent to reposition values and fill again.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/document-processing/pdf-fill-studio/SKILL.md and read by ahel’s review.

Fill a PDF locally, place the values precisely, then export. Flat PDFs use a browser editor; AcroForm PDFs fill natively; the signature is always left blank for the user to sign.

When to use

The user gives you a PDF to fill (form, claim, tax/bank/insurance document).

Setup (once)

pip install pdf-fill-studio (provides the pdf-fill-studio command). From source instead: python3 -m venv .venv && .venv/bin/pip install -e ., then use .venv/bin/pdf-fill-studio.

Flow

(Replace form.pdf and profile.json with the user's actual file paths.)

Start: pdf-fill-studio form.pdf -o out/form_filled.pdf. It detects the form type.
AcroForm (native fields): re-run with a profile of known facts: pdf-fill-studio form.pdf -o out/form_filled.pdf --profile profile.json. Matched fields fill automatically; it prints "Needs manual input: [...]" for the rest. Ask the user for each listed field, add them to the profile, re-run, then render to verify.
Flat (no fields): a local browser editor opens. Tell the user to type values, drag boxes onto the lines, nudge with arrow keys, and click "Export PDF". Comb fields (one box per character, e.g. postal code) are detected and filled one character per cell automatically.
XFA: tell the user this form type is not supported yet (open it in free Adobe Reader).
The filled PDF is written to out/. The user signs it themselves.

Self-check (before declaring done)

Render and look: python -m pdf_fill_studio.render_page out/form_filled.pdf out/preview. Check each value sits on its line / inside its cell, not too low or spilling outside. Apply minimal coordinate corrections and re-bake if needed.

Rules

Never fill a signature field.
Never store or hard-code a SIN, bank account, or card number (the profile matcher skips them).
Everything runs locally; no document is uploaded.

Signals

GitHub stars: 32k
Forks: 4k
Last commit: Oct 2026

ahel review

K1binfo
installs-packages

Automated review, not a security audit. Ruleset v1+k2.

Questions

Does it work on scanned PDFs?: Yes. Scanned documents usually have no form fields, so the skill positions text directly on the page at the exact spot where each value belongs.
Do my documents leave my computer?: No. The skill fills PDFs locally, so the file and the data entered into it stay on the machine where the agent runs.
What kinds of PDF fields does it support?: It handles native AcroForm fields, per-character (comb) fields, and flat PDFs with no fields at all. For field-less or scanned documents it places text at precise page positions.

Advanced

Item type: skill
Key: pdf-fill-studio
Source: github.com/davila7/claude-code-templates

github.com/davila7/claude-code-templates