1. Conduid
  2. AI
  3. Skillify
MCP server · AI

Skillify

Pack MCP (Model Context Protocol) servers into Agent Skills.

Unclaimed ai
37Low

Scored 7 months ago · breakdown

About Skillify

Skillify is an MCP server in the AI category: pack MCP (Model Context Protocol) servers into Agent Skills.

Install

Claude Code
claude mcp add skillify -- npx -y skillify
npx
npx -y skillify

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Skillify

Powered by Claude · Grounded in docs

I know everything about Skillify. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

skillify

Pack MCP (Model Context Protocol) servers into Agent Skills.

[!NOTE] MCP servers can change their APIs freely because clients (LLMs) get the latest spec at runtime. Skillify breaks this model. It creates a snapshot of the server's API at generation time. This snapshot may not work with newer server versions.

Maybe a future version will support a flag for dynamic.

Installation

bun install

Usage

List tools from an MCP server

# stdio (spawn command)
skillify list "npx -y @modelcontextprotocol/server-memory"

# SSE (URL)
skillify list http://localhost:3000/sse

Pack into a skill

# Interactive selection
skillify pack "npx -y @modelcontextprotocol/server-memory"

# Include all tools
skillify pack "node ./my-server.js" --all --name my-skill

# Custom description
skillify pack "..." --description "Custom skill description here"

# Custom message
skillify pack "..." --message "This message appears after the title"

# Filter tools
skillify pack "..." --include tool1,tool2
skillify pack "..." --exclude tool3,tool4

Options

Option Description
-o, --output <dir> Parent output directory; skill is placed in <dir>/<skill-name> (default: .)
-n, --name <name> Skill name (default: MCP server name or mcp-skill)
-d, --description <desc> Custom skill description
-m, --message <msg> Custom message after title in SKILL.md
--include <tools> Comma-separated tools to include
--exclude <tools> Comma-separated tools to exclude
--all Include all tools without prompting
--amp Generate Amp-native skill with mcp.json
--pin-tools Force includeTools in mcp.json (requires --amp --all)

Output Format

Standard Mode (default)

Generates an Agent Skills compliant directory:

my-skill/
├── SKILL.md
├── references/tools/
│   ├── tool-one.md
│   └── tool-two.md
└── scripts/
    ├── call-tool.js
    └── mcp-client.js

Amp Mode (--amp)

Generates an Amp-compatible skill with embedded MCP configuration:

skillify pack "npx -y @modelcontextprotocol/server-memory" --amp --name memory --all
my-skill/
├── SKILL.md
└── mcp.json

The mcp.json file specifies the MCP server command and optionally pins tools with includeTools.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Skillify

How do I install Skillify?

Run claude mcp add skillify -- npx -y skillify, then add the server to your MCP client's configuration.

Is Skillify safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Skillify still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.