Claude Code Plugins

Community-maintained marketplace

Feedback

filling-pdf-forms

@jhs/Chatfield
3
0

Complete PDF forms by collecting data through conversational interviews and populating form fields. Use when filling forms, completing documents, or when the user mentions PDFs, forms, form completion, or document population.

Install Skill

1Download skill
2Enable skills in Claude

Open claude.ai/settings/capabilities and find the "Skills" section

3Upload to Claude

Click "Upload skill" and select the downloaded ZIP file

Note: Please verify skill by going through its instructions before using it.

SKILL.md

name filling-pdf-forms
description Complete PDF forms by collecting data through conversational interviews and populating form fields. Use when filling forms, completing documents, or when the user mentions PDFs, forms, form completion, or document population.
allowed-tools Read, Write, Edit, Glob, Bash
version 1.0.0a2
license Apache 2.0

Filling PDF Forms

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

When to Use This Skill

Use when completing PDF forms with user-provided data.

Workflow Selection

PDFs may have programmatic form fields (fillable) or require visual annotation (non-fillable). Check which type:

python scripts/check_fillable_fields.py input.pdf

Fillable fields detected? → See references/fillable-forms.md

No fillable fields? → See references/nonfillable-forms.md

Both workflows use identical Chatfield conversational interview models - only the field extraction and PDF population mechanisms differ.


Interview Validation Checklist

Both fillable and non-fillable workflows require building a high-quality Chatfield interview. Use this checklist to validate the interview definition before running the server:

Interview Validation Checklist:
- [ ] All field_ids from .form.json or .fields.json are mapped (either directly or via .as_*() casts)
- [ ] No field_ids are duplicated or missing
- [ ] Fan-out patterns use .as_*() casts on single field to populate multiple PDF fields
- [ ] Split pattern: multi-part values use .as_*() casts (e.g., identifier → 3 casts for 3 parts)
- [ ] Discriminate + split: mutually-exclusive fields use .as_*() casts with "or empty/0 if N/A" descriptions
- [ ] Expand pattern: multiple checkboxes use .as_*() casts on single field
- [ ] .conclude() used only when necessary (multi-field dependencies or complex logic)
- [ ] Alice traits include extracted form knowledge
- [ ] Field hints provide context from PDF instructions
- [ ] Optional fields explicitly marked with hint("Background: Optional...")
- [ ] .must() used sparingly (only for true content requirements)
- [ ] .as_*() transformations used liberally for all type casts and formatting
- [ ] Field .desc() questions are natural and user-friendly (no technical field_ids)

If any items fail validation:

  1. Review the specific issue in the checklist
  2. Fix the interview definition
  3. Re-run validation checklist
  4. Proceed only when all items pass

Additional Resources