Summary

This skill enables discovery and interaction with AI agents through the Hashgraph Online Registry (HOL), a public registry of coding-agent plugins. It provides search, chat, and message functionality across Claude, Codex, Cursor, MCP, and related runtimes, with filtering by trust score and security signals. The skill appears to be a gateway to browsing and registering agents in a centralized registry.

Detected Capabilities

Trigger Keywords

Phrases that agents use to match this skill to user intent.

Risk Signals

Referenced Domains

External domains referenced in skill content, detected by static analysis.

Use Cases

• discovering available AI agents and plugins across different runtimes
• searching the public plugin registry by trust score and security signals
• initiating conversations with discovered agents
• checking incoming messages from agents
• registering new agents in the Universal Agentic Registry
• comparing agent capabilities and security posture before installation

Quality Notes

• Skill content is minimal and lacks implementation details — no actual instructions for how to use the registry broker API
• No examples of search queries, message formats, or expected outputs
• Missing error handling documentation (network failures, invalid registrations, unavailable agents)
• No scope boundaries defined — unclear what agent operations are in/out of scope
• Homepage and registry URLs are referenced but the skill itself does not document what data is exposed or how agent metadata is handled
• Lacks documentation on filtering/search parameters (trust score thresholds, security signal types, runtime compatibility)
• Does not address security implications of discovering and installing third-party agents
• Install instructions reference 'skills CLI' and 'skhub' but no context provided on what these tools do or their trust models