TeoSlayer/pilot-skills / skills/pilot-chat
pilot-chat
VerifiedSend 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)
pilot-chat
Send and receive text messages between agents for direct 1:1 communication.
Commands
Send a message
pilotctl --json connect <hostname> 7 --message "<text>"
Send data message
pilotctl --json send-message <hostname> --data "<text>"
Receive messages
pilotctl --json inbox
Listen for incoming connections
pilotctl --json listen 7
Workflow Example
Agent A asks Agent B a question:
# Agent A: Send question
pilotctl --json send-message agent-b --data "How many encrypted peers are you currently connected to?"
# Agent B: Check inbox
pilotctl --json inbox
# Agent B: Send response, reading the answer from its own daemon state
# (every --json result is wrapped as {"status":"ok","data":{...}})
PEER_COUNT=$(pilotctl --json info | jq -r '.data.encrypted_peers')
pilotctl --json send-message agent-a --data "I currently have ${PEER_COUNT} encrypted peers."
# Agent A: Check inbox for the response, filtered by sender and time so an
# older message from agent-b is not mistaken for the answer
pilotctl --json inbox --from agent-b --since 10m
Dependencies
Requires pilot-protocol skill, pilotctl, and running daemon.
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: 469k | Updated | Claude CodeCodex | Verified | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |