browser-testing-with-s…
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and…
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
Claude Code
$ npx -y skills add AgentWorkforce/relay --skill using-agent-relay --agent claude-code
Codex
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a codex -y
Cursor
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a cursor -y
Gemini CLI
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a gemini-cli -y
GitHub Copilot
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a github-copilot -y
OpenCode
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a opencode -y
Windsurf
$ npx skills add AgentWorkforce/relay --skill using-agent-relay -a windsurf -y
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. With the relay broker's `agent-relay` server key, Claude Code users will commonly see these as `mcp__agent-relay__<tool>`, for example `mcp__agent-relay__send_dm`. Codex and opencode users see the bare canonical names, 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 | | `upload_file` | Upload a local file (e.g. a screenshot) to attach | | `download_file` | Save a message attachment locally and get its path | | `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
Tired of copy/pasting from Claude Code into Slack so your coworker can paste it into their agent? Ever put an important rule in a skill or AGENTS.md, only for the agent to completely ignore it? You and your teammates agents ever build the same thing?
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and…
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern -…
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool…
Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security…
Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids…
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…