

Loading comments…
Achievement
Project Info
Product Keywords
skills.sh is a registry and command-line tool for discovering and installing reusable capabilities—called "skills"—for AI agents. Instead of building every function from scratch, developers can browse a community-driven leaderboard of skills and add them to their agent with a single terminal command: npx skills add. Each skill packages procedural knowledge—like API integrations, data processing routines, or domain-specific workflows—so agents can perform complex tasks without custom coding.
Skills are added to any agent environment with a single npx skills add command. No manual configuration, dependency hunting, or copy-pasting code—just run the command and the skill is ready to use.
The skills.sh leaderboard ranks skills by total installs, showing which capabilities are most trusted and widely adopted. Developers can quickly spot popular skills from sources like Microsoft Azure, Lark Suite, and independent creators.
Skills are organized by source, with collections from major providers and individual developers. For example, microsoft/azure-skills has over 4.5 million total installs across 14+ skills, while xixu-me/skills offers 9+ skills with 1.2 million installs.
"Skills are reusable capabilities for AI agents—install them with a single command to enhance your agents with access to procedural knowledge."
This approach treats agent capabilities as composable, shareable modules rather than monolithic codebases. The leaderboard creates a trust signal: high-install skills have been battle-tested by the community. Combined with the frictionless npx installation, skills.sh makes it practical to assemble a capable agent from pre-built parts instead of writing everything from scratch.
You're building AI agents and want to avoid reinventing common integrations. The leaderboard gives you a quick pulse on what's working for others, and the one-command install means you can test a skill in seconds. It's especially useful if you're prototyping agents or maintaining multiple agent configurations that need consistent, versioned capabilities.
Other tools you might consider
Self-hosted and open-source user profiles and long-term memory for your AI agents. Unlike generic memory solutions that store blobs of text, GetProfile extracts natural language summary, typed traits with confidence scores and relevant memories with importance levels into a structured user profiles stored in your own PostgreSQL database.
Netlify AI Gateway makes it easier to build AI features while you’re vibe coding. Instead of pausing to create provider accounts, manage API keys, or set up billing, AI Gateway securely handles credentials and usage for you. You can call the latest models from OpenAI, Anthropic, and Google Gemini directly from your Netlify project. It’s a faster path from experimenting with AI to something ready to run in production.
FastMCP 3.0 is a framework for building smarter AI context apps, not just tool servers. Pull tools and data from anywhere, reshape them, control access, track state, and run long tasks — with hot reload, versioning, and observability built in for production use.
AI can write code brilliantly but debugs blindly. It can't see your app, logs, or what users did, so you waste time explaining. BetterBugs MCP gives AI complete context to fix the bugs instantly.
Maker
moonbyte
Alternatives
Loading comments…