Document Creator
Create, edit, and convert Word documents and DOCX files.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/documents-hmbown/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Create, edit, inspect, or convert Word documents and DOCX deliverables such as memos, reports, letters, templates, and forms.
What this skill does
Documents
Use this skill when the user wants a .docx or Word-style document, or when an
existing document needs edits, comments, extraction, or conversion.
Workflow
- Clarify the output path if needed. Prefer a
.docxfile in the workspace. - Preserve existing documents. Write edited copies instead of overwriting originals unless the user asked for an in-place edit.
- Use the best available local tool:
python-docxfor creation and structured editspandocfor Markdown/HTML to DOCX conversion- OOXML inspection with
unziponly for targeted low-level fixes
- For new documents, choose a simple professional structure: title, metadata when useful, clear headings, readable body text, and tables only for real row/column data.
- For edits, make the smallest change that satisfies the request and keep the original formatting where practical.
- Verify by reopening the file with a parser such as
python-docx, checking paragraph/table counts, and extracting representative text. If LibreOffice or another renderer is available, render or export a quick visual check.
If required dependencies are missing, ask before installing packages. If the user only needs content and a DOCX cannot be produced in the environment, offer Markdown or HTML as a fallback and clearly state the limitation.
Related skills
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
Documentation Co-Authoring
anthropics
Guide structured workflows for writing docs, proposals, and technical specs collaboratively.
PPTX Text Extractor
axoviq-ai
Extract text and speaker notes from PowerPoint presentations.
Memory Search
davila7
Search conversation history and recall previous discussions, decisions, and context.