TeoSlayer/pilot-skills / skills/pilot-a2a-bridge
pilot-a2a-bridge
VerifiedBridge A2A (Agent-to-Agent) protocol messages over Pilot tunnels. Use this skill when: 1. You need to connect A2A agents across different networks 2. You want to route A2A messages through Pilot's overlay network 3. You're building multi-agent systems that need reliable messaging Do NOT use this skill when: - Agents are on the same local network (use direct A2A instead) - You need raw TCP/UDP access (use pilot-protocol directly) - The daemon is not running
Pilot A2A Bridge
Bridge Agent-to-Agent protocol messages over Pilot tunnels with NAT traversal and encryption.
Commands
Start A2A Bridge
pilotctl --json daemon start --hostname a2a-agent-1
pilotctl --json listen 5000
Send A2A Message
pilotctl --json send-message remote-agent --data '{"type":"task","action":"analyze","payload":"data"}'
Subscribe to A2A Events
pilotctl --json subscribe remote-agent a2a-events
Receive A2A Messages
pilotctl --json recv 5000
Workflow Example
#!/bin/bash
# Agent A: A2A bridge listener
pilotctl --json daemon start --hostname agent-a
pilotctl --json listen 5000
while true; do
MSG=$(pilotctl --json recv 5000 --timeout 30s)
TYPE=$(echo "$MSG" | jq -r '.type')
SENDER=$(echo "$MSG" | jq -r '.sender')
case "$TYPE" in
task)
RESULT=$(process_task "$(echo "$MSG" | jq -r '.payload')")
pilotctl --json send-message "$SENDER" --data "{\"type\":\"result\",\"data\":\"$RESULT\"}"
;;
esac
done
Message Format
{
"type": "task|result|event|status",
"action": "analyze|process|compute",
"payload": "arbitrary data"
}
Dependencies
Requires pilot-protocol skill with running daemon and A2A-compatible agents.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |