Tiger Skills

timescale/tiger-skills-mcp-server

Brings Claude's Skills spec to any MCP-compatible LLM by loading modular capability packages from local directories or GitHub repos. Each skill is a SKILL.md file with YAML frontmatter plus optional bundled scripts, references, and assets. The server exposes skills as both tools and resources, letting you control which protocol to use via connection string parameters. You can point it at Anthropic's official skills repo or build your own collection. Also includes a subagent tool for breaking complex tasks into subtasks, where each subagent inherits the same skill set. Config is YAML-based with support for individual skills or entire collections, plus TTL-based caching to avoid reloading on every request.

GitHub stars: 7
tool: 1
auth: Secret needed
transport: STDIO
env vars: 2
last updated: Dec 10, 2025

View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

subagentProvides a subagent tool that can be used to break up complex tasks into smaller subtasks, each handled by its own agent instance.

Provides a subagent tool that can be used to break up complex tasks into smaller subtasks, each handled by its own agent instance.

No parameter schema in public metadata yet.

Configuration

GITHUB_TOKENsecret

Token to access (private) GitHub repos

SKILLS_FILE

Location of configuration file for skills

Readme

Tiger Skills MCP Server

Emulate Claude Skills with any LLM via a Model Context Protocol (MCP) server.

What are Skills?

Skills are modular components that enhance the capabilities of an MCP-compatible agent by providing specific functionalities, workflows, and domain expertise. They transform a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

The goal is to be fully compatible with Anthropic's skill format. See their Agent Skills Spec and related documentation for more details.

An overview of the Skills spec

Skill Structure

Skills are modular, self-contained packages that extend agent capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform the agent from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.