Word Document Builder
Documents skill, available on Zeplik
Word Document Builder is a ready-to-run documents skill on Zeplik. docx), especially when formatting or layout fidelity matters; uses python-docx plus a render script for visual checks. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Document artifact -- structured written deliverable with headed sections and a TL;DR (see artifact-templates/document.md).
The Word Document Builder skill loads automatically when your request matches it, or you can invoke it directly by typing /word-docs in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Word Document Builder skill can do
- Create Word documents with structured headings, styles, and tables
- Edit existing DOCX files while preserving formatting fidelity
- Render DOCX pages to images for visual layout verification
- Catch and fix formatting defects before final delivery
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Word Document Builder skill works
DOCX Skill
When to use
- Read or review DOCX content where layout matters (tables, diagrams, pagination).
- Create or edit DOCX files with professional formatting.
- Validate visual layout before delivery.
How the file actually reaches the user
You BUILD the document in the sandbox and DELIVER it with export_file. A file
written to the working directory and never exported does not reach the user at
all — they see your description and no download. Never end a build turn without
export_file.
Any document the user uploaded in this conversation is already staged in the
sandbox working directory under its (sanitized) filename: characters outside
A-Za-z0-9._- become _. List the directory if unsure:
import os; print(sorted(os.listdir(".")))
The sandbox has NO internet and no sudo: never try pip install, uv pip install, brew install or apt-get install. python-docx, pandoc,
LibreOffice (soffice), poppler-utils (pdftoppm) and pymupdf
(fitz) are pre-baked. An install attempt is a guaranteed failure that also
burns one of the turn's limited tool calls, which can push export_file past
the budget and cost the user the file.
For a substantial written document (report, memo, whitepaper) prefer the house
engine zeplik-docx, which takes Markdown and owns the layout — cover page,
contents, running header, "Page X of Y" footer, banded tables. Reach for raw
python-docx when you must edit an EXISTING .docx or hit a specific structural
requirement the engine does not cover.
Workflow
- Use
python-docxfor edits and structured creation (headings, styles, tables, lists). - After each meaningful change, render and inspect the pages:
soffice --headless --convert-to pdf --outdir out doc.docxthenpdftoppm -png out/doc.pdf out/page. Look at the PNGs — check pagination, table widths, and that nothing is clipped or orphaned. (scripts/render_docx.pyis bundled but depends onpdf2image, which is NOT installed in this sandbox — use the soffice/pdftoppm pair above instead.) - Re-open the saved file and assert it is intact (paragraph count, a heading, a spot value) — print the evidence.
export_filethe document, then tell the user in one short line that it is ready. Do not restate the document contents as text.
Temp and output conventions
- Write the deliverable into the working directory with a stable, descriptive
filename; that is the path you pass to
export_file. - Keep intermediate files out of the way (a
tmp/subfolder) and never export them. - Never ask the user to review rendered pages locally — they have no copy until you export it.
If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.
Environment
No required environment variables.
Rendering commands
DOCX -> PDF:
soffice -env:UserInstallation=file:///tmp/lo_profile_$$ --headless --convert-to pdf --outdir $OUTDIR $INPUT_DOCX
PDF -> PNGs:
pdftoppm -png $OUTDIR/$BASENAME.pdf $OUTDIR/$BASENAME
Bundled helper:
python3 scripts/render_docx.py /path/to/file.docx --output_dir /tmp/docx_pages
Quality expectations
- Deliver a client-ready document: consistent typography, spacing, margins, and clear hierarchy.
- Avoid formatting defects: clipped/overlapping text, broken tables, unreadable characters, or default-template styling.
- Charts, tables, and visuals must be legible in rendered pages with correct alignment.
- Use ASCII hyphens only. Avoid U+2011 (non-breaking hyphen) and other Unicode dashes.
- Citations and references must be human-readable; never leave tool tokens or placeholder strings.
Final checks
- Re-render and inspect every page at 100% zoom before final delivery.
- Fix any spacing, alignment, or pagination issues and repeat the render loop.
- Confirm there are no leftovers (temp files, duplicate renders) unless the user asks to keep them.
Zeplik output presentation
Present the final deliverable as a single polished artifact: clear headings, tables where the content is tabular, fenced code where it is code. Lead with the deliverable itself; keep process commentary to a single short line. If the skill produced multiple files or sections, end with a compact list of them with one-line purposes.
How to use the Word Document Builder skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Word Document Builder skill right away.
Describe your documents task
Ask in plain language, or type /word-docs to invoke the skill directly. Zeplik recognizes the Word Document Builder skill and applies its method.
Review and refine the result
Zeplik returns a structured document you can edit, download, and reuse. Ask follow-ups to refine it.
Source and credit
- Author
- openai
- License
- Apache-2.0
Adapted from the open-source davila7/claude-code-templates project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Word Document Builder skill?
- Word Document Builder is a ready-to-run documents skill on Zeplik. docx), especially when formatting or layout fidelity matters; uses python-docx plus a render script for visual checks. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Document artifact -- structured written deliverable with headed sections and a TL;DR (see artifact-templates/document.md).
- How do I use Word Document Builder on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /word-docs in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Word Document Builder skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Word Document Builder skill runs on your preferred model for the task.
- Where does the Word Document Builder skill come from?
- The Word Document Builder skill is adapted from the open-source davila7/claude-code-templates project (Apache-2.0) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Word Document Builder skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related documents skills
- Excel & Spreadsheet BuilderUse when the user wants to create, edit, analyze or format spreadsheets (.xlsx, .csv, .tsv), preserving formulas, references and formatting via openpyxl and pandas.
- File ConversionUse when converting file formats -- csv/json, markdown/word, images, audio, ebooks -- via artifact or exact tool steps. Not for spreadsheet work (use spreadsheet) or PDF edits (use pdf-processing).
- JSON CanvasProduces valid JSON Canvas 1.0 .canvas files with nodes, edges, groups, and connections. Not for rendered flowcharts in Markdown (use diagram).
- PDF Form FillerUse when a PDF form must be filled in - tax, insurance, bank, claim or application forms. You read the fields, fill them in the sandbox and hand back the finished PDF, and never hand the user a script.
- PDF ReaderUse when a PDF must be marked up - highlights, notes, APPROVED/DRAFT/CONFIDENTIAL stamps, redaction, a signature image. You apply it in the sandbox and never hand the user a script.
- PDF ToolkitUse when something must be done to a PDF - extract text, tables or images, split, merge, crop, rotate, reorder, compress, repair, OCR. You do it in the sandbox and never hand the user a script.
More on Zeplik
Try Word Document Builder on Zeplik
Every model, one chat. Bring the Word Document Builder skill into your next conversation and let the assistant do the work.