Microsoft 'skills' repo: MCP servers and agent grounding primitives for coding agents
Microsoft has published an open-source TypeScript repository called 'skills' that provides MCP servers, custom agents, and an Agents.md specification to ground coding agents within SDKs. The project appears to be infrastructure for standardizing how coding agents discover and invoke capabilities. With 2,656 stars and modest daily growth, it is an early-stage but notable contribution to the agent tooling ecosystem from a major lab.
Related guides (2)
Related events (8)
Google Labs Releases Stitch Skills: Agent Skills Library for MCP-Compatible Coding Agents
Google Labs has published stitch-skills, a TypeScript library of Agent Skills designed to work with the Stitch MCP server. The library follows the Agent Skills open standard, enabling compatibility with multiple coding agents including Gemini CLI, Claude Code, Cursor, and Antigravity. The repository has accumulated 5,597 stars with 70 added today, indicating active community interest in the MCP/agent tooling ecosystem.
agent-skills: Secure Validated Skill Registry for AI Coding Agents
A TypeScript-based open-source skill registry designed to extend AI coding agents including Claude Code, Cursor, GitHub Copilot, and Antigravity with validated, reusable capabilities. The project provides a structured way to add skills to multiple coding agent platforms with a focus on security and validation. It is gaining notable traction with 3,767 total stars and 225 stars added today.
Microsoft Azure DevOps MCP Server
Microsoft has published an open-source Model Context Protocol (MCP) server for Azure DevOps, enabling AI agents to interact directly with Azure DevOps services. The repository is implemented in TypeScript and has accumulated 1,710 GitHub stars. This extends the MCP ecosystem with enterprise DevOps tooling, allowing agents to perform operations such as managing pipelines, work items, and repositories.
AWS releases official agent toolkit with MCP servers and plugins for AI agents
AWS has published an official, AWS-supported toolkit on GitHub providing MCP servers, skills, and plugins to enable AI agents to interact with AWS services. The repository is Python-based and has accumulated 966 stars. This represents AWS's formal entry into the MCP server ecosystem for agentic workloads.
Vercel Labs releases open agent skills tool (npx skills)
Vercel Labs has published an open-source TypeScript project called 'skills' on GitHub, providing an agent skills tool invocable via npx. The repository has accumulated 23,611 stars with 106 added today, suggesting significant community interest. The project appears to be a framework or harness for defining and running agent capabilities.
AgentSkills: specification and documentation framework for agent skills
AgentSkills is a GitHub repository providing a specification and documentation framework for defining agent skills in Python. The project has accumulated 21,484 stars with modest daily growth (+47), suggesting an established but not rapidly accelerating community interest. It appears to be a tooling or protocol-level effort for standardizing how agent capabilities are described and composed.
Anthropic Publishes 'Agent Skills' Public Repository
Anthropic has made a public GitHub repository called 'skills' available, described as a public repository for Agent Skills. The repository has accumulated 136,679 total stars with 514 added today, suggesting significant community interest. The project appears to be a Python-based resource related to agent capabilities, though specific technical details are sparse from the available description.
Chrome DevTools MCP Server for Coding Agents
The chrome-devtools-mcp repository exposes Chrome DevTools functionality as a Model Context Protocol (MCP) server, enabling coding agents to interact with browser debugging tools programmatically. The project has accumulated over 40,000 stars on GitHub, with 132 added today, indicating strong community traction. This tooling bridges browser developer tooling with AI agent workflows, allowing agents to inspect, debug, and interact with web pages.