swarm-expert
Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.
- Installs
- 39
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/desplega-ai/ai-toolbox --skill swarm-expert- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads swarm-expert automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Swarm Expert
You are an expert on the agent-swarm MCP server for multi-agent coordination. Help users manage agent swarms, delegate tasks, communicate between agents, and coordinate work.
Note: This skill requires the
agent-swarmMCP server to be configured. The MCP provides tools for swarm coordination.
Quick Reference
| Goal | MCP Tool | Example |
|---|---|---|
| Join swarm | join-swarm | Join as leader or worker |
| Check swarm status | get-swarm | See all agents and status |
| List tasks | get-tasks | View tasks with filters |
| Delegate task | send-task | Assign task to agent/pool |
| Claim task | task-action | Claim from pool |
| Update progress | store-progress | Mark complete/failed |
| Send message | post-message | Chat with @mentions |
| Read messages | read-messages | Check unread/mentions |
Common Workflows
Starting as Leader
1. Use `join-swarm` with name and isLead=true
2. Use `get-swarm` to see available workers
3. Use `send-task` to delegate work to specific agents or pool
4. Monitor with `get-tasks` and `get-task-details`
Starting as Worker
1. Use `join-swarm` with name (isLead=false)
2. Use `poll-task` to check for assignments
3. Use `task-action` to claim unassigned tasks
4. Use `store-progress` to report completion
Delegating a Task
1. Use `send-task` with:
- title: Clear task description
- description: Detailed requirements
- toAgentId: Specific agent OR leave empty for pool
- tags: For categorization
- dependsOnTaskIds: If blocked by other tasks
Checking Status
1. Use `get-swarm` - Shows all agents (name, status, current task)
2. Use `get-tasks` - Filter by status, tags, or search text
3. Use `get-task-details` - Full task info, output, and logs
Agent Communication
1. Use `list-channels` - See available chat channels
2. Use `post-message` with:
- channelId: Target channel
- content: Message text (supports @mentions)
- replyToMessageId: For threading
3. Use `read-messages` with:
- unreadOnly: true for new messages
- mentionsOnly: true for @mentions to you
Task States
| State | Description |
|---|---|
pending | Created but not started |
in_progress | Being worked on |
completed | Successfully finished |
failed | Failed with reason |
blocked | Waiting on dependencies |
Troubleshooting
"Agent not found"
You need to join the swarm first. Use join-swarm with a name.
"Task not assigned to you"
Use task-action to claim the task before working on it.
"No tasks available"
Check get-tasks with different filters. Tasks may be assigned or blocked.
Can't see other agents
Use get-swarm to refresh the agent list. Agents may have disconnected.
Detailed Reference
For complete MCP tool documentation, see MCP-REFERENCE.md.
FAQ
What does the swarm-expert skill do?
Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.
How do I install swarm-expert?
Run npx skills add https://github.com/desplega-ai/ai-toolbox --skill swarm-expert in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/swarm-expert/ (personal) or .claude/skills/swarm-expert/ (project).
Which AI agents can use swarm-expert?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is swarm-expert safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains swarm-expert?
It is published by desplega-ai in desplega-ai/ai-toolbox. It has 39 recorded installs.
More from desplega-ai/ai-toolbox
planning
desplega-ai/ai-toolbox
Open the skill to read its SKILL.md instructions.
tdd-planning
desplega-ai/ai-toolbox
TDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.
wts-expert
desplega-ai/ai-toolbox
Git worktree management expert for @desplega.ai/wts. Use when the user asks about git worktrees, wts commands, worktree workflows, or wants help managing multiple branches simultaneously.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available