fill-form — Claude Code command for PDF forms
The fill-form Claude Code command fills PDF form fields in a live viewer. The agent checks unclear fields against page labels and shows the completed pages for review.
Apache-2.0 ★ 36,654 updated 2026-10-24
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install pdf-viewer@knowledge-work-pluginsWhat fill-form does
The command helps fill a PDF form in a viewer, with visual feedback as values are entered. For a simple form, the viewer can ask for the values before opening the document. For a complex form, the agent inspects the field list and takes page screenshots to match unclear field names to their printed labels.
Values can come from the conversation or from answers supplied by the user. After filling the form, the agent shows screenshots of the completed pages. Fields remain editable in the viewer, while signatures are handled separately with /pdf-viewer:sign.
What it helps with
- fill PDF fields using details from a conversation
- identify fields with machine-generated names from their page labels
- review completed pages in screenshots
- edit a field directly in the viewer
Example prompts for the agent
- Fill in
application.pdfusing the details from our conversation. - Check what
Text1andField_7refer to inapplication.pdf, then help fill them. - Show screenshots of the completed pages in
application.pdffor review.
How to install fill-form
1Plugin marketplace
/plugin marketplace add anthropics/knowledge-work-plugins/plugin install pdf-viewer@knowledge-work-plugins2Manually: put the files in place
.claude/commands/fill-form.mdCall it with /fill-form. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/fill-form.mdCall it with /prompts:fill-form. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/fill-form.prompt.mdManually: put the files in place
.gemini/commands/fill-form.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about fill-form
How do I install fill-form in Claude Code?
Add the marketplace with /plugin marketplace add anthropics/knowledge-work-plugins, then install the plugin with /plugin install pdf-viewer@knowledge-work-plugins. The command file is at .claude/commands/fill-form.md.
What does fill-form do?
It helps complete PDF fields in a viewer. The agent uses page labels to interpret unclear field names, then shows screenshots of the filled pages.
How does fill-form handle fields with unclear names?
The agent takes screenshots of pages containing those fields and matches them to nearby printed labels. It can use details from the conversation or ask the user for values.
Source text
fill-form.md · Apache-2.0
---
description: Fill PDF form fields interactively with live visual feedback
argument-hint: "[path-or-url]"
---
> If you need to check which tools are connected, see [CONNECTORS.md](../CONNECTORS.md).
# Fill Form
Help the user complete a fillable PDF form in the live viewer. Unlike
programmatic form tools, this gives the user **direct visual feedback**
on every field as it's filled, with easy undo/edit in the viewer.
## Why use this instead of programmatic form filling
- **Visual confirmation** — the user sees each value land in the right
box, not just a success message
- **Unnamed/unlabeled fields** — many real-world PDFs have fields with
machine names like `Text1`, `Field_7`, or no name at all. The label
("Date of Birth", "SSN") is printed **next to** the field on the
rendered page, not in the field metadata. Use `get_screenshot` to
see what each field actually is, then fill by name.
- **Easy correction** — the user can edit or clear any field directly
in the viewer, or ask you to `fill_form` again with new values
## Two approaches
### User-driven (simple, well-labeled forms)
Call `display_pdf` with `elicit_form_inputs: true`. The server detects
form fields and prompts the user to enter values **before** the viewer
opens. The filled PDF is then displayed.
### AI-assisted (complex forms, unnamed fields, or when you have context)
1. `display_pdf` (without elicit) — inspect returned `formFields`
(name, type, page, bounding box)
2. If field names are cryptic (`Text1`, `Field_7`), use `interact` →
`get_screenshot` of each page with fields. Look at the visual
labels next to each bounding box to understand what each field is.
3. For each field, either:
- Infer the value from conversation context (name, date, email)
- Ask the user, describing the field by its **visual** label
("the 'Date of Birth' box on page 1")
4. `interact` → `fill_form` with `fields: [{name, value}, ...]`
5. `interact` → `get_screenshot` of each filled page
6. Show the user, ask them to confirm or edit
## Example
> **User:** Help me fill out this W-9
>
> *You:* `display_pdf` → formFields: `f1_1`, `f1_2`, `f1_3`, `c1_1`, ...
> (cryptic names)
>
> *You:* `interact` → `get_screenshot` page 1 → see `f1_1` is next to
> "Name", `f1_2` is "Business name", `c1_1` is the "Individual" checkbox
>
> *You:* "I can see Name, Business name, Address, TIN, and tax
> classification checkboxes. I'll fill Name and Date from what I
> know — what's your TIN and business address?"
>
> *After answers:* `interact` → `fill_form` + `get_screenshot`
>
> *You:* "Here's the filled form [screenshot]. The signature line is
> still blank — want to add your signature with `/pdf-viewer:sign`?"
## Notes
- Signature fields are usually separate — fill text first, then hand
off to `/pdf-viewer:sign` for the image
- Checkbox/radio values are `true`/`false` or the option string
- The user can always drag & edit fields directly in the viewer
© Anthropic · Apache-2.0 · anthropics/knowledge-work-plugins