Sx 2.0: Share AI skills with your team through Dropbox folder sync

What it does

Sx 2.0 is a desktop application for Mac, Windows, and Linux that allows teams to share AI skills—custom configurations, prompts, and commands—through cloud storage folders like Dropbox, Google Drive, OneDrive, or iCloud. Users create skills as markdown files, drop them into a shared folder, and teammates automatically receive them in their AI clients (Claude, Cursor, Copilot, Gemini, and others). The app translates skills into each client's native format and installs them with a single sync button.

The underlying technology is a vault format stored as plain markdown files on disk. Version history lives in a hidden folder. Since the backend is built on existing file-sync services, no separate servers or accounts are needed.

Who it is for

Sx 2.0 targets non-technical teams in marketing, legal, sales, and operations who create and refine AI skills but lack git or terminal knowledge. The original Sx was built for developers; this version removes that requirement entirely. Teams already using shared cloud folders are the natural fit.

Pricing

The site does not show prices.

How it stands out

The core differentiation is the translation layer. While a team could manually organize markdown files in a shared folder, Sx automatically converts each skill into the correct format for each AI client and writes it to the right location. This is the work a plain folder setup cannot automate.

Developers retain full backwards compatibility with the original CLI tool and git-based vaults. The app and CLI read the same vault format. Non-technical users get a graphical interface; developers can continue using the command line.

The reliance on existing file-sync products as the distribution backend eliminates infrastructure costs and leverages tools companies already pay for and trust.

What a founder should check

First, validate whether non-technical teams actually build reusable AI skills at scale or if skill-sharing remains niche. The claim rests on discovery interviews, but real adoption metrics and churn would reveal demand durability.

Second, examine switching costs and the moat. Teams can replicate parts of this workflow with a markdown vault in Obsidian or a shared folder plus manual client setup. The moat depends on whether the translation layer is sticky enough and whether incumbents (like Copilot or Claude) eventually ship native skill-sharing tools that bypass the need for intermediaries.

Third, pressure-test the business model. If the product remains free and open source, understand how monetization would work without alienating the user base. If a paid tier emerges, determine what non-developers would pay for and whether the cost justifies adoption friction.

Thinking of building something like this?

Every launch here is a competitor to somebody's idea. If yours is close, check it against the market before you build: the Full Check names the rivals, the prices and the gaps.