filling-pdf-forms

# Filling PDF Forms

Complete PDF forms by collecting required data through conversational interviews and populating form fields.

<purpose>
Use when completing PDF forms with user-provided data. Goal: produce `.done.pdf` populated with user information by following this process exactly.
</purpose>

## Process Overview

```plantuml
@startuml SKILL
title Filling PDF Forms - High-Level Workflow
|User|
start
:User provides PDF form to complete;
|filling-pdf-forms skill|
:Step 0: Initialize Chatfield;
:Step 1: Form Extraction;
:Step 2: Build Form Data Model;
:Step 3: Translation Decision;
if (User language is form language?) then (yes)
  :Use base Form Data Model;
else (no)
  :Translation Setup;
endif
:Step 4: Run Interview Loop;
partition "Chatfield CLI Interview Loop" {
  :Initialize: Run CLI without message;
  repeat
    :CLI outputs question to stdout;
    :Present question to user via AskUserQuestion();
    |User|
    :User provides response;
    |filling-pdf-forms skill|
    :Run CLI with user's message;
  repeat while (CLI indicates complete?) is (no)
  ->yes;
}
:Inspect collected data via CLI --inspect;
:Step 5: Populate PDF;
if (Fillable form?) then (yes)
  :Populate fillable fields
  (see Populating-Fillable.md);
else (no)
  :Populate non-fillable fields
  (see Populating-Nonfillable.md);
endif
|User|
:**✓ SUCCESS**;
:Receive completed PDF <basename>.done.pdf;
stop
@enduml
```

## Workflow

### Step 0: Initialize Chatfield

Test: `python -c "import pypdf; import pdf2image; import markitdown; import chatfield"`.

Install via `pip` if needed; exceptions:
- `markitdown` → `pip install "markitdown[pdf]"`
- `chatfield` → `pip install ./scripts/chatfield-1.0.0a2-py3-none-any.whl` (relative to this .md)

### Step 1: Form Extraction

Extract PDF form using `extracting-form-fields` sub-agent:

```python
Task(
    subagent_type="general-purpose",
    description="Extract PDF form fields",
    prompt=f"Extract form field data from PDF: {pdf_path}\n\nUse the extracting-fo