with one click
broadcast
Send a message to all active agent sessions, excluding the orchestrator. Use when the orchestrator needs to announce information or coordinate the entire team at once. For messaging a single agent, use send-message instead.
Menu
Send a message to all active agent sessions, excluding the orchestrator. Use when the orchestrator needs to announce information or coordinate the entire team at once. For messaging a single agent, use send-message instead.
| name | Broadcast |
| description | Send a message to all active agent sessions, excluding the orchestrator. Use when the orchestrator needs to announce information or coordinate the entire team at once. For messaging a single agent, use send-message instead. |
| version | 1.0.0 |
| category | communication |
| skillType | claude-skill |
| assignableRoles | ["orchestrator"] |
| triggers | ["broadcast","message all","announce"] |
| tags | ["communication","broadcast","team"] |
| execution | {"type":"script","script":{"file":"execute.sh","interpreter":"bash","timeoutMs":60000}} |
Send a message to all active agent sessions. The skill queries active sessions from the backend, skips the orchestrator's own session (crewly-orc), and delivers the message to each remaining agent individually.
Run this skill when the orchestrator needs to announce information, coordinate timing, or send instructions to the entire team at once. Each agent receives the message in their terminal session via the delivery endpoint.
| Parameter | Required | Description |
|---|---|---|
message | Yes | The message text to broadcast to all agents |
bash config/skills/orchestrator/broadcast/execute.sh '{"message":"Team standup in 5 minutes"}'
bash config/skills/orchestrator/broadcast/execute.sh '{"message":"Priority shift: all agents focus on bug fixes for the next sprint"}'
{
"sent": 3,
"failed": 0,
"message": "Broadcast complete"
}
sent — number of agents that received the messagefailed — number of delivery failuresmessage — status summary| Error | Cause | Solution |
|---|---|---|
Missing required parameter: message | message not provided in JSON input | Include message in the JSON payload |
Failed to get sessions | Backend not reachable or sessions endpoint failed | Verify the Crewly backend is running |
curl failed with exit code N | Network issue or backend down | Check backend health at CREWLY_API_URL/api/health |
High failed count | One or more agent sessions are unresponsive | Check agent status with get-team-status and restart failed agents |
send-message — send a message to a single agent sessionget-team-status — check which agents are active before broadcastingdelegate-task — send a task (not just a message) to a specific agentTranscribe a local audio (or video) file to text with timestamps using Whisper. Defaults to local whisper.cpp (free, offline, word/segment-level timestamps) and automatically falls back to the OpenAI Whisper API (whisper-1) when the local engine is not installed. Any agent can call it for meetings, podcasts, voice notes, interviews, or video audio tracks.
Accept and take the next available task from the task queue. Use when an agent is idle and ready to pick up the highest-priority unassigned task. For assigning tasks to specific agents, use assign-task instead.
Register the agent as active with the Crewly backend on startup. Use when an agent first launches and needs to join the team and become visible to the orchestrator. For confirming responsiveness after registration, use heartbeat instead.
Analyze git changes and produce a structured code review with automated checks for missing tests, debug statements, potential secrets, large changes, and dependency modifications. Use when reviewing staged changes, unstaged diffs, recent commits, or branch comparisons before submitting a pull request. For task-level quality gates, use check-quality-gates instead.
Assign a task to a specific agent via the task management system. Use when the orchestrator needs to target a particular agent with a known task ID. For agents self-assigning the next available task, use accept-task instead.
Record a learning or insight gained during task execution for team knowledge sharing.