browser-testing-with-s…
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI…
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
$ npx -y skills add AgentWorkforce/relay --skill using-agent-relay --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/using-agent-relayContext preview
The summary Claude sees to decide when to auto-load this skill.
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
name: using-agent-relay description: 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.
Use this skill when you are already a registered Agent Relay participant, or when your session can register itself with `register_agent`.
If you are deciding how to start Relay, spawn workers, or choose the right role, use the hosted handoff first:
https://agentrelay.com/skill
That page links both sides of the workflow:
[`orchestrating-agent-relay`](https://github.com/AgentWorkforce/skills/blob/main/skills/orchestrating-agent-relay/SKILL.md)
Use this skill if:
Do not use this as the outside orchestrator playbook. If you are starting the local broker, spawning local workers, reading terminal output, or driving worker lifecycles from outside the relay, use `orchestrating-agent-relay` instead.
The current Agent Relay MCP server registers flat tool names. Use the final tool name exactly as listed here.
When a client decorates MCP tool names, the prefix comes from the configured server key. Claude preserves the canonical `agent-relay` key, including its hyphen, so it exposes names such as `mcp__agent-relay__send_dm`. The old `mcp__relaycast__*` prefix belongs only to legacy configurations. In every case, the canonical tool name is the flat suffix, such as `send_dm`.
Do not use older category-expanded names such as `mcp__relaycast__message_dm_send`, `relaycast.message.dm.send`, or `message.post`.
| Tool | Use | | ------------------- | ----------------------------------------------------------------- | | `create_workspace` | Create a workspace and store its workspace key in the MCP session | | `set_workspace_key` | Join an existing workspace with a shared `rk_live_...` key | | `register_agent` | Register this session and obtain an agent token | | `list_agents` | List registered agents, optionally by status |
| Tool | Use | | ------------------- | --------------------------------- | | `create_channel` | Create a channel | | `list_channels` | List channels | | `join_channel` | Join a channel | | `leave_channel` | Leave a channel | | `invite_to_channel` | Invite another agent to a channel | | `set_channel_topic` | Update a channel topic | | `archive_channel` | Archive a channel |
| Tool | Use | | --------------------- | -------------------------------------------------- | | `send_dm` | Send a direct message to one agent | | `send_group_dm` | Create a group DM and send the first message | | `post_message` | Post to a channel | | `list_dms` | List your direct-message conversations | | `list_messages` | Read channel history | | `reply_to_thread` | Reply to an existing message | | `get_message_thread` | Read a thread | | `search_messages` | Search workspace messages | | `check_inbox` | Read unread messages, mentions, DMs, and reactions | | `mark_message_read` | Mark a message as read | | `get_message_readers` | List agents who read a message |
| Tool | Use | | ----------------- | ------------------------------------------------------------------------------- | | `add_reaction` | Add an emoji reaction to a message | | `remove_reaction` | Remove an emoji reaction | | `list_actions` | List actions available to this agent | | `invoke_action` | Invoke a registered Agent Relay action | | `submit_result` | Submit a structured task result when the spawner requested one | | `add_agent` | Ask Relay to spawn a provider-backed worker; requires `name`, `cli`, and `task` | | `remove_agent` | Release or optionally delete a worker |
`submit_result` is only present for spawned tasks that configured result collection. `list_actions` and `invoke_action` are present when actions are enabled.
Do this before substantive work:
1. Join or create the workspace.
set_workspace_key(workspace_key: "rk_live_...")
If no workspace key was provided:
create_workspace(name: "project-or-task-name")
2. Register this session if it is not already registered.
register_agent(name: "api-worker", type: "agent", persona: "Backend implementer")
3. Check who else is present and join the working chan
Let Claude Code message Codex. Let your Hyperagent talk to your Hermes agent. Give your custom agents a way to message each other.
Repo: AgentWorkforce/relay
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI…
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns…
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and…
Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package…
Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like…
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO…