Sx 2.0
Open source package manager for AI skills, now with a desktop app that shares them through a Dropbox, Drive, OneDrive or iCloud folder.
Opens sleuth-io.github.io in a new tab.
How the 6.6 was reached
- Quality of output5/10
Only vendor descriptions of translating skills into each client's format and plain markdown storage; no independent results or reviews of output. Source: sleuth-io.github.io
- Ease of use8/10
Open app, point at a cloud folder, drag skills in; no server, no accounts, one-click sync. Docs page not found. Source: sleuth-io.github.io
- Pricing value9/10
Free, open-source Apache 2.0 tool with no required paid dependency; the Sleuth paid plan listed is a separate product. Source: everydev.ai
- API and integration quality6/10
Installs across Claude Code, Cursor, Copilot, Codex, Gemini, Cline and Kiro with a lock file, and has a CLI; no documented API or SDK found. Source: sleuth-io.github.io
- Solves the problem it claims to solve5/10
Vendor describes shared-folder skill sharing without git or terminal; the directory lists no user ratings, so no independent confirmation it delivers. Source: everydev.ai
6.6/10 is the average of the five criterion scores above. The evidence comes from 2 different sources.Scores come from public evidence (the tool's own pages and documentation, and independent reviews); we do not test every tool hands-on. Scored 18 October 2026, on version 1 of our five-criteria scoring method.
Pricing
- Open source package manager for AI assets
- Git vaults for developers
- Desktop app for Mac, Windows and Linux
For the full list of what each plan includes, and current prices, see everydev.ai.
Key Features
- Desktop app for Mac, Windows and Linux aimed at people who do not use git or a terminal
- Shared-folder library: point the app at a Dropbox, Google Drive, OneDrive or iCloud folder and teammates see published skills
- Markdown files become skills, per the announcement
- Git vaults with a lock file and deterministic installs for developers
- Installs skills across Claude Code, Cursor, Copilot, Codex, Gemini, Cline and Kiro
Pros & Cons
Pros
- Uses a file sync service a team already pays for, so no server or accounts are needed, per the post
- Targets non-developers in marketing, legal, sales and ops who write skills but avoid the command line
- Supports many AI coding clients from one library
- Open source, with a lock file for repeatable installs
Cons
- Sharing through a synced folder offers less access control and audit history than a git workflow
- The announcement is the only source reviewed, so pricing, support and team features beyond the folder model are unclear
- Skill portability depends on each client's own skill and MCP support
- Version 2.0 is new, with little public track record to judge
Sx 2.0 takes a sensible route to team skill sharing: it reuses the shared folder that most offices already have. That should lower the barrier for non-developers, though the evidence here is the maker's own blog post. Developers who want strict versioning will likely stay with the git vaults.
Added to scored.tools on
For the Sx 2.0 team: put this score on your website
A small image (a badge) that shows this score and links back to this page. Free for any tool, at any score. It always shows the current score, so it changes when the score does. Copy this code into your website where you want the badge:
<a href="https://scored.tools/tools/sx-skill-manager/"><img src="https://scored.tools/badge/sx-skill-manager.svg" alt="Sx 2.0 on scored.tools: 6.6/10" width="160" height="40"></a>Do you work for Sx 2.0? Claim this page: prove you work there, then confirm the facts, correct a mistake or add a short reply. It is free and never changes the score.
Competitors to Sx 2.0
Other tools in the Productivity category worth comparing.
Claude Code
7.6/10Anthropic's coding agent that takes on bug fixes, tests and migrations from the terminal, IDE, Slack or web.
Cursor
7.8/10AI-native code editor built on VS Code with integrated chat, autocomplete, and codebase understanding.
Repomix
8.8/10Pack your entire codebase into AI-friendly formats for better LLM processing