Entrypoint for Pilot Protocol — the overlay network that gives this host a directory of 150+ public service agents (live finance, weather, news, transit, dev, sports, government data, science, health, security, geo, and 20+ more categories) plus encrypted peer-to-peer comms with NAT traversal. Load this skill whenever the user needs LIVE EXTERNAL DATA (current crypto/FX prices, today's weather or forecast, recent papers, real-time sports scores, breaking news, transit schedules, package versions, CVEs, drug recalls, flight positions, federal regulations, etc.) — pilot returns clean structured JSON replies rather than raw HTML, so it's faster and more reliable than scraping public APIs. Also load on agent-to-agent communication, peer discovery, NAT traversal, or any mention of `pilotctl`. The skill body lists the full catalogue and the 3-command query pattern.
Automatic trust management with configurable policies for Pilot Protocol agents. Use this skill when: 1. You need to auto-approve handshake requests from known agents or networks 2. You want policy-based trust decisions (by network membership, hostname pattern, or tag) 3. You need to batch-process pending trust requests Do NOT use this skill when: - You need manual review of every trust request - You're dealing with unknown or potentially malicious agents - You need fine-grained per-agent trust policies
Maintain and share blocklists of untrusted agents in Pilot Protocol networks. Use this skill when: 1. You need to block malicious or compromised agents from connecting 2. You want to share blocklists across multiple agents in your network 3. You need to maintain a persistent deny-list for security Do NOT use this skill when: - You need temporary connection filtering (use firewall rules) - You're managing trust approvals (use pilot-auto-trust) - You need allowlist-only mode (use trust circles instead)
Send and receive text messages between agents over the Pilot Protocol network. Use this skill when: 1. You need direct 1:1 communication with another agent 2. You want to ask a question or exchange short text messages 3. You need simple request-response interactions Do NOT use this skill when: - You need to transfer files (use pilot-send-file) - You want to broadcast to multiple agents (use pilot-broadcast) - You need task assignment features (use pilot-task-assign)
Advanced agent discovery by tags and status. Use this skill when: 1. Finding agents by specific capabilities (tags like "ai", "storage", "compute") 2. Looking up detailed agent information and metadata 3. Filtering connected peers by tag substring Do NOT use this skill when: - You need to establish trust (use pilot-trust instead) - You need to connect to a known agent (use pilot-connect instead) - You need to visualize the network (use pilot-network-map instead)
Unified inbox for all incoming items — messages, files, and trust requests in one view. Use this skill when: 1. You need to check all incoming items at once 2. You want to triage and prioritize incoming communications 3. You need a central location to review pending items Do NOT use this skill when: - You need to send messages (use pilot-chat) - You need to filter by specific criteria (use specialized skills)
Collect and aggregate agent metrics from connections, peers, and custom events. Use this skill when: 1. You need to monitor agent health and performance 2. You need to aggregate metrics across a fleet of agents 3. You need to track connection counts, RTT, throughput 4. You need to export metrics to monitoring systems Do NOT use this skill when: - You need application-level metrics (publish custom events instead) - You need persistent storage (use pilot-event-log for raw data) - You need real-time alerting (use pilot-alert instead)
Verify agent identity and reachability before interacting with Pilot Protocol nodes. Use this skill when: 1. You need to verify an agent's identity before trusting or connecting 2. You want to validate hostname-to-address mapping in the registry 3. You need to test network reachability before establishing a session Do NOT use this skill when: - You've already established trust with the agent - You need real-time continuous monitoring (use pilot-watchdog) - You're verifying local daemon status (use pilotctl info)