Create Agent Skills
Generates new, functional agent skills based on provided descriptions and desired capabilities for cfircoo agents.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add cfircoo-create-agent-skills npx -- -y @trustedskills/cfircoo-create-agent-skills
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"cfircoo-create-agent-skills": {
"command": "npx",
"args": [
"-y",
"@trustedskills/cfircoo-create-agent-skills"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill allows AI agents to generate custom skills for other agents. It can define the skill's purpose, inputs, and outputs, effectively creating a modular system of agent capabilities. The generated skill definitions are designed to be easily integrated into an agent platform.
When to use it
- Expanding Agent Functionality: You need your AI agent to perform tasks beyond its current skillset.
- Creating Specialized Agents: You want to build agents with very specific, narrow functions.
- Automating Skill Development: You have a repetitive process for defining new agent skills and want to automate it.
- Modular Agent Architectures: You’re building an agent system where components can be easily swapped in and out.
Key capabilities
- Skill definition generation
- Input/Output specification
- Purpose articulation
- Agent capability modularization
Example prompts
- "Create a skill for an agent that summarizes customer support tickets."
- "Define a new skill to extract key data points from financial reports."
- "Generate a skill that translates English text into Spanish and then calculates the sentiment score."
Tips & gotchas
The quality of the generated skill definition depends heavily on the clarity and specificity of your prompt. Providing detailed examples or outlining expected behavior will yield better results.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.