This is a prototype connector that lets Claude read and write Word documents while preserving formatting, headers, tables, and layout instead of treating them like plain text. You'd reach for this when you need to generate reports, edit existing .docx files, or work with structured documents where formatting matters. It's pulled from OpenAI's skills repository, so you're getting their reference implementation. The listing acts as a pointer, you still need to install the actual upstream bundle from GitHub to get the working code. Worth noting it's marked prototype, so expect some rough edges if you're doing anything complex with heavily styled documents.
- skills.sh installs
- 2.9K
- GitHub stars
- 106.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add nexu-io/open-design --skill doc --agent claude-codeInstalls into .claude/skills of the current project.
Files
doc
Curated from OpenAI's skills repository.
What it does
Read, create, and edit .docx documents with formatting and layout fidelity via OpenAI's document skill.
Source
- Upstream: https://github.com/openai/skills
- Category:
documents
How to use
This catalogue entry advertises the skill in OpenDesign so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:
# Inspect the upstream README for exact paths
open https://github.com/openai/skills
Then ask the agent to invoke this skill by name (doc) or with
one of the trigger phrases listed in this skill's frontmatter.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/nexu-io/open-design
- Categories
- Frontend Development, Documentation, AI & Agent Building, Design & UI/UX, Office & Documents
- First seen
- Jun 3, 2026
More from nexu-io/open-design
All 217- Editorial Burgundy Principles Template2.9K
- Imagegen2.9K
- Image Enhancer2.9K
- Fal Generate2.9K
- Figma Use2.9K
- Fal Image Edit2.9K
- Fal Upscale2.9K
- Faq Page2.9K
- Domain Name Brainstormer2.9K
- Ai Music Album2.9K
- Release Notes One Pager2.9K
- Swiss User Research Video Template2.9K
- Fal Vision2.9K
- Minimax Docx2.9K
- Speech2.9K
- Fal Tryon2.9K
- Paywall Upgrade Cro2.9K
- Deck Guizang Editorial2.8K
- Fal Restore2.8K
- Venice Image Edit2.8K
- Fal Video Edit2.8K
- Sora2.8K
- Figma Generate Library2.8K
- Gif Sticker Maker2.8K
Recommended
More Frontend Development
draw-io-diagram-generatorgithub/awesome-copilotUse when creating, editing, or generating draw.io diagram files (.drawio, .drawio.svg, .drawio.png). Covers mxGraph XML authoring, shape libraries, style string2.9Kskills.sh installs
nitroantfu/skillsNitro is the framework-agnostic server toolkit (powering Nuxt) for building and deploying web servers anywhere. Use when working with nitro.config, server route2.9Kskills.sh installs
active-researchactionbook/actionbookDeep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SP2.9Kskills.sh installs
fal-video-editnexu-io/open-designEdit existing videos using AI — remix style, upscale, remove background, and add audio via fal.ai's hosted video models.2.8Kskills.sh installssoranexu-io/open-designGenerate, remix, and manage short video clips via OpenAI's Sora API. Useful for cinematic shots, b-roll, and rapid concept video iteration.2.8Kskills.sh installs
computer-automationweb-infra-dev/midscene-skillsVision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language c2.8Kskills.sh installs