Enables LLMs to dynamically discover and execute tools through a structured skills system. Serves as a documentation hub where skills are defined in directories, allowing progressive loading and interpretation of capabilities.
Integrates Agent Skills into LLMs by discovering skills in a configured directory and progressively loading their instructions and resources on demand through a structured disclosure pattern.
Serves SKILL.md-based skills as MCP resources and tools over streamable HTTP, enabling remote discovery and retrieval of skill files with full YAML frontmatter parsing.
Turns Claude-style skills (SKILL.md files with resources) into callable MCP tools for any agent. Discovers skills from a directory, exposes their instructions and resources, and can execute bundled helper scripts.
Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.
A local-first skill runtime for AI coding agents that defines skills as verifiable, composable units with sandboxed execution, and exposes them as MCP tools over HTTP.
