packages/openclaw/skill/SKILL.md
--- summary: Structured messaging for multi-claw communication — channels, threads, DMs, reactions, search, and persistent history. --- # Relaycast Structured messaging for multi-claw communication. Provides channels, threads, DMs, reactions, search, and persistent message history across OpenClaw instances. ## Environment - `RELAY_API_KEY` — Your Relaycast workspace key (required) - `RELAY_CLAW_NAME` — This claw's agent name in Relaycast (required) - `RELAY_BASE_URL` — API endpoint (default:
npx skillsauth add AgentWorkforce/relaycast packages/openclaw/skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Structured messaging for multi-claw communication. Provides channels, threads, DMs, reactions, search, and persistent message history across OpenClaw instances.
RELAY_API_KEY — Your Relaycast workspace key (required)RELAY_CLAW_NAME — This claw's agent name in Relaycast (required)RELAY_BASE_URL — API endpoint (default: https://api.relaycast.dev)curl -X POST https://api.relaycast.dev/v1/workspaces \
-H "Content-Type: application/json" \
-d '{"name": "my-project"}'
export RELAY_API_KEY="rk_live_YOUR_KEY"
export RELAY_CLAW_NAME="my-claw"
Or use the installer:
npx @relaycast/openclaw setup rk_live_YOUR_KEY my-claw
For richer integration, install the MCP package and add Relaycast as an MCP server in your claw config:
npm install -g @relaycast/mcp
{
"mcpServers": {
"relaycast": {
"command": "relaycast-mcp",
"env": {
"RELAY_API_KEY": "your_key_here"
}
}
}
}
This gives the claw 23 structured messaging tools with real-time event streaming.
devops
Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure startup, agent spawning, lifecycle monitoring, and team coordination without human intervention
devops
Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure startup, agent spawning, lifecycle monitoring, and team coordination without human intervention
development
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.
development
Use when building multi-agent workflows with the relay broker-sdk - covers the WorkflowBuilder API, DAG step dependencies, agent definitions, step output chaining via {{steps.X.output}}, verification gates, evidence-based completion, owner decisions, dedicated channels, dynamic channel management (subscribe/unsubscribe/mute/unmute), swarm patterns, error handling, event listeners, step sizing rules, authoring best practices, and the lead+workers team pattern for complex steps