Amp Skill Creator

Amp Skill Creator

This skill covers Amp-specific features for skill creation. After reading this, load the agent-skill-creator skill and follow its workflow, applying the overrides at the end of this document.

First: Ask Where to Install

Before creating a skill, ask the user where they want it installed (if they haven't already specified):

• .agents/skills/ — workspace-local (project-specific)
• ~/.config/amp/skills/ — global user

Amp-Specific Features

Amp Frontmatter Fields

Beyond the required name and description, Amp supports:

---
name: my-skill-name
description: What the skill does and when to use it
argument-hint: "[query]" # Shown in /skill-list (e.g., "[repo] [issue]")
disable-model-invocation: true # Hides from agent auto-detection (manual /skill only)
---

Bundled MCP Servers

Skills can bundle MCP servers via mcp.json in the skill root:

skill-name/
├── SKILL.md
└── mcp.json

mcp.json Format

{
  "local-server-name": {
    "command": "npx",
    "args": ["-y", "some-mcp-server@latest"],
    "env": {
      "API_KEY": "${MY_API_KEY}"
    },
    "includeTools": ["tool_a", "tool_b", "navigate_*"]
  },
  "remote-server-name": {
    "url": "https://some-mcp-server.com/mcp",
    "headers": {
      "Authorization": "Bearer ${TOKEN}"
    },
    "includeTools": ["tool_a", "tool_b"]
  }
}

Local Server Fields

Remote Server Fields

Environment Variables

Use ${VAR_NAME} syntax in any field:

{
  "my-server": {
    "command": "node",
    "args": ["${HOME}/scripts/mcp-server.js"],
    "env": {
      "API_KEY": "${SERVICE_API_KEY}"
    }
  }
}

Always Filter Tools

MCP servers often expose many tools (20+ = thousands of tokens). Always use includeTools:

{
  "includeTools": ["navigate_page", "take_screenshot", "click"]
}

Glob patterns supported: ["navigate_*", "click"] or ["*"] for all.

Adding MCP Servers via CLI

Use amp mcp add to quickly generate MCP server config:

# Local server (command-based)
amp mcp add <name> -- <command> [args...]

# Local server with env vars
amp mcp add <name> --env KEY=VAL -- <command> [args...]

# Remote server (URL-based, auto-detects transport)
amp mcp add <name> <url>

# Remote server with headers
amp mcp add <name> --header "Authorization=Bearer <token>" <url>

# Add to workspace settings instead of global
amp mcp add <name> --workspace -- <command> [args...]

Note: This command adds the server config to ~/.config/amp/settings.json (or workspace settings with --workspace), not directly into a skill's mcp.json. After running, copy the relevant entry from settings into your skill's mcp.json file.

Options

Examples

# NPX-based server
amp mcp add context7 -- npx -y @upstash/context7-mcp

# Postgres with env vars
amp mcp add postgres --env PGUSER=myuser -- npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydb

# Remote with auth header
amp mcp add sourcegraph --header "Authorization=token <token>" https://sourcegraph.example.com/.api/mcp/v1

# Remote with OAuth (auto-triggers browser auth)
amp mcp add linear https://mcp.linear.app/sse

# Workspace-specific server
amp mcp add project-server --workspace -- npx -y @some/server

Now: Load agent-skill-creator

Load the agent-skill-creator skill now and follow its 6-phase workflow for creating the skill content. Apply these overrides during implementation:

Overrides for agent-skill-creator

What to USE from agent-skill-creator:

• ✅ General SKILL.md content structure (workflows, examples, error handling)
• ✅ Scripts organization (scripts/, utils/)
• ✅ References organization (references/)
• ✅ Quality standards (1000+ words, real examples, no TODOs)
• ✅ Modular architecture patterns
• ✅ Testing approaches
• ✅ Validation patterns