AgentWorkforce
- 6 skills
- 0 followers
- 20 hours ago last updated
- ▌ Relay 80 100 Workflow · agentworkforce-relaycastUse 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.
- ▌ Relay 80 100 Workflow 2 · agentworkforce-relaycastUse 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.
- ▌ Choosing Swarm Patterns · agentworkforce-relaycastUse when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) with decision framework and reflection protocol
- ▌ Writing Agent Relay Workflows · agentworkforce-relaycastUse 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
- ▌ Writing Agent Relay Workflows 2 · agentworkforce-relaycastUse 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
- ▌ Running Headless Orchestrator · agentworkforce-relaycastUse 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