skills.rest
LGJ-Jonathan
LGJ-JonathanOFFICIAL
Explore all skills by this author →
GitHub

multi-agent-ops

Coordinates task delegation and communication across agents in OpenAgents workspaces.

Updated Mar 26, 2026
Search Tags:#multi-agent#mcp#handoff#agent coordination#task delegation#workspace orchestration#openagents
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill multi-agent-ops-lgj-jonathan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: multi-agent-ops
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/multi-agent-ops
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill multi-agent-ops-lgj-jonathan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When multiple AI agents work in the same OpenAgents workspace, it is unclear which agent can do what, how to hand off tasks, and how to share data without stepping on each other. This Skill provides the operational patterns for agent discovery, capability mapping, delegation, and cross-agent data exchange. ## Core Features & Use Cases - Capability Matrix: Distinguishes shared MCP resources (BridgeKit, Playwright, workspace files) from per-agent local resources (gh CLI, Railway tokens, git repos) so tasks route to the right agent. - Delegation Patterns: Provides handoff workflows using @mentions, workspace chat, and workspace files, including parallel dispatch for independent tasks. - Agent Setup & Verification: Checklists for onboarding a new agent with gh CLI, Railway tokens, and MCP tool verification. - Use Case: Agent A finishes code and pushes to GitHub, then @mentions Agent B to pull the repo and run the Railway deployment, with results reported back in workspace chat. ## Quick Start Check which agents are online and delegate the Railway deployment to the agent that has a local Railway token configured.

Frequently Asked Questions about multi-agent-ops

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I delegate tasks between multiple AI agents?▼

Delegate tasks by @mentioning the target agent in your workspace chat response with a clear instruction. First check which agents are online with workspace_get_agents, then route the task based on whether it needs shared MCP tools or agent-specific local resources.

How do agents share data in an OpenAgents workspace?▼

Agents share data through workspace files using workspace_write_file and workspace_read_file, through workspace chat history via workspace_get_history, or through shared services like Google Sheets via BridgeKit. Workspace files are the recommended channel for structured data.

Which tasks can any agent handle versus a specific agent?▼

Any agent can handle tasks using shared MCP tools like Google Workspace, Slack, Playwright browser automation, and workspace files. Tasks needing local resources like gh CLI, Railway tokens, or locally cloned git repos must go to the agent that has them installed.

When should I @mention another agent in workspace chat?▼

Only @mention an agent when you need them to perform an action, since each mention wakes the target agent. Do not @mention just to acknowledge or say thanks; plain chat messages suffice for status updates.

What is the minimum setup for a new agent to reach full capability?▼

Install and authenticate the gh CLI, set the RAILWAY_TOKEN environment variable, clone needed repositories locally, and verify MCP tools like BridgeKit, Playwright, and openagents-workspace are available. Verify the environment with gh auth status and tool checks.

Related Skills

Explore More Software Engineering Skills→
render-ossrender-oss

render-mcp

Configure and authenticate the Render MCP server for Cursor, Claude Code, and Codex.

Official
Advanced
NovaAI-innovationNovaAI-innovation

railway-deploy

Deploy code to Railway using the railway up command.

Community
Intermediate
corvo007corvo007
793

dispatching-parallel-agents

Dispatch parallel AI agents to investigate independent failures across files or subsystems.

Community
Advanced
misty-stepmisty-step
13

sprites

Coordinate isolated lane workloads on Fly Sprites with golden checkpoints.

Official
Advanced