Agent Discovery
Cleanexpo's agent-discovery identifies relevant internal experts and resources to address user requests quickly and accurately.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add agent-discovery npx -- -y @trustedskills/agent-discovery
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"agent-discovery": {
"command": "npx",
"args": [
"-y",
"@trustedskills/agent-discovery"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Agent Discovery skill allows AI agents to discover and install other skills. It facilitates expanding an agent's capabilities by dynamically integrating new functionalities from the TrustedSkills registry. This enables agents to adapt to changing needs and leverage a wider range of tools without manual configuration.
When to use it
- An agent requires access to a specific skill but doesn’t have it pre-installed.
- You want an agent to automatically update its skillset with new, relevant skills as they become available.
- A workflow involves chaining together multiple AI agents, each requiring different specialized skills.
- You need to rapidly prototype and test integrations between various AI agent functionalities.
Key capabilities
- Skill discovery from the TrustedSkills registry.
- Automated skill installation.
- Dynamic expansion of agent capabilities.
- Integration with other AI agents.
Example prompts
- "Find a skill that can summarize text."
- "Install the latest version of the 'image-generation' skill."
- "Discover skills related to data analysis and install them."
Tips & gotchas
The agent must have sufficient permissions to install new skills. The discovery process relies on accurate skill metadata within the TrustedSkills registry; ensure listed skills are compatible with your environment.
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.