Agent skill

help

Provides information about using the skill-to-mcp server and how to install additional skills

Stars 21
Forks 3

Install this agent skill to your Project

npx add-skill https://github.com/biocontext-ai/skill-to-mcp/tree/main/src/skill_to_mcp/default_skills/help

SKILL.md

Help Skill

This is the default skill loaded by the skill-to-mcp server when no skills directory is specified.

Purpose

The skill-to-mcp server converts AI Skills (following Claude Skills format) into MCP server resources. This help skill provides basic information about using the server.

Available Tools

The server provides three core tools:

  1. get_available_skills: Lists all available skills with their descriptions
  2. get_skill_details: Returns the full SKILL.md content and file listing for a specific skill
  3. get_skill_related_file: Reads any file within a skill directory

Installing Additional Skills

To use custom skills with this server, you need to:

  1. Create or obtain a skills directory containing skill subdirectories
  2. Configure the server to use your skills directory

Option 1: Using Command-Line Option

bash
skill_to_mcp --skills-dir /path/to/your/skills

Or with uvx:

bash
uvx skill_to_mcp --skills-dir /path/to/your/skills

Option 2: Using Environment Variable

Set the SKILLS_DIR environment variable:

bash
export SKILLS_DIR=/path/to/your/skills
skill_to_mcp

Option 3: MCP Client Configuration

Configure your MCP client (e.g., Claude Desktop) to pass the skills directory:

json
{
  "mcpServers": {
    "my-skills": {
      "command": "uvx",
      "args": ["skill_to_mcp", "--skills-dir", "/path/to/your/skills"],
      "env": {
        "UV_PYTHON": "3.12"
      }
    }
  }
}

Creating Your Own Skills

Each skill must:

  1. Have its own subdirectory
  2. Contain a SKILL.md file with YAML frontmatter
  3. Follow this frontmatter format:
markdown
---
name: my-skill-name
description: Brief description of what this skill does and when to use it
---

# Skill Content

Your skill instructions and documentation go here...

Example Skill Structure

my-skills/
├── skill-1/
│   ├── SKILL.md
│   ├── scripts/
│   │   └── example.py
│   └── references/
│       └── guidelines.md
└── skill-2/
    └── SKILL.md

Finding More Skills

  • BioContextAI Registry: biocontext.ai/registry - Community catalog of biomedical MCP servers and skills
  • GitHub: Search for repositories tagged with "claude-skills" or "mcp-skills"
  • Community Resources: Check the skill-to-mcp documentation for links to skill collections

Next Steps

  1. Identify or create skills relevant to your use case
  2. Configure the server with your skills directory
  3. Use the get_available_skills tool to discover what's available
  4. Start using the skills with get_skill_details and get_skill_related_file

Documentation

For more information, visit:

Expand your agent's capabilities with these related and highly-rated skills.

biocontext-ai/skill-to-mcp

single-cell-rna-qc

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy best practices for single-cell analysis.

21 3
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results