skills

Use when creating, updating, or reviewing a Workforce cloud persona (`persona.ts` + `agent.ts`) for the current deploy/runtime shape. Covers cloud, useSubscription, integrations with scope mounting/enabledByInput gating/adapter config passthrough, inputs, memory, sandbox modes, onEvent, runtime fields, capabilities, defineAgent triggers/schedules/watch/team-dispatcher launch, provider IO via @relayfile/relay-helpers, multi-transport delivery, ctx.relay messaging, and the deploy flow.

Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.

The canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.

Use when creating, editing, or validating an Agent Relay Factory factory.config.json file, including repo routing, Linear state/team settings, GitHub issue ingestion, live mode, babysitter options, and Relayflows dispatch wiring boundaries.

Use when adding webhook events to make sure integrations properly register the webhook events they carry

Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a local mount. Covers `relayfile setup`, dynamic integration discovery with `relayfile integration available/search`, Nango and Composio backend selection, Atlassian site selection and metadata, cloud login, OAuth/connect flows, mount verification, `RELAYFILE_LOCAL_DIR` handoff, writeback status and retry commands, and key May 2026 cloud-mount gotchas.

Use when an agent is exploring a relayfile mount for the first time or trying to locate a specific resource (Notion page, Linear issue, Slack channel, GitHub PR). Tells the agent to start with `<mount>/LAYOUT.md` and `<provider>/LAYOUT.md` rather than guessing paths from memory, and to use the `by-title/`, `by-id/`, `by-name/`, `by-edited/<date>/`, `by-state/` alias subtrees instead of recursively grepping. Filename convention is `<identifier>__<uuid>` (ticket number / slug first so listings are scannable). NOT for activity-summary questions, which should use the `activity-summary` skill instead.

Run a fan-out relay pattern for independent subtasks. Use when the same kind of work can be split across files, components, services, or targets with minimal coordination.

Run a sequential relay pipeline where each stage feeds the next. Use when worker N plus 1 depends on worker N's output or decisions.

Spawn and coordinate a relay team for a multi-part task. Use when work should be split across several Claude workers with explicit ACK and DONE signaling.

Use when adding new multi-agent coordination patterns to agent-relay - provides checklist for types, schema, templates, and docs updates

Use when an agent needs to write back to a provider through a relayfile mount (Linear comments, GitHub issues, Slack messages, Notion pages, etc.). Covers the file-creation writeback contract (drop JSON at the canonical path → provider mutation), discovering paths and schemas via .schema.json siblings, idempotency keys, writeback status with relayfile writeback list and relayfile status, and recovering from dead-lettered writes under .relay/dead-letter/. NOT for read operations or for direct API calls — relayfile mediates the writeback so you can ignore provider auth, retries, and rate limits.

Use when an agent is asked "what did I (or my team) work on yesterday / this week / today" across provider data in a relayfile mount (Linear, GitHub, Notion, Slack, Confluence, Jira, etc.). Tells the agent to consult the pre-computed `digests/yesterday.md` (and sibling digest files) at the workspace root BEFORE doing manual exploration with `ls`/`grep`/`find`. The digest is deterministic, exhaustive over the window, and costs one file read instead of dozens of provider queries.

Use when authoring or extending the digest set in a relayfile workspace - covers the contract for files under `<mount>/digests/` (`yesterday.md`, `today.md`, `this-week.md`, date-stamped daily files), the per-provider section format, link conventions back into the canonical mount tree, when digests are regenerated, and how adapter authors expose new provider data to the digest pipeline. NOT for agents answering activity questions — those should use the `activity-summary` skill to consume digests, not produce them.

Run headless multi-agent orchestration sessions via Agent Relay. Use when spawning teams of agents, creating channels for coordination, managing agent lifecycle, and running parallel workloads across Claude/Codex/Gemini/Pi/Droid agents.