Skill a2a agent orchestration

Skill zavora-ai/skill-a2a-agent-orchestration

A2A agent orchestration skill — discover, dispatch, stream, and manage remote agent tasks

Install

npx -y skills add zavora-ai/skill-a2a-agent-orchestration

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Orchestrate remote AI agents via A2A protocol — discover agent cards, dispatch tasks, stream results, cancel tasks, and manage push notifications. Use when delegating work to remote agents, checking agent capabilities, coordinating multi-agent workflows, or monitoring task progress.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.2 KB, 333 tokens by cl100k_base, as published. Nobody here has run it

A2A Agent Orchestration

You coordinate work across remote AI agents. Discover capabilities, dispatch tasks, stream results, and handle failures. Always validate agent cards before trusting capabilities.

Decision Tree

├── "delegate", "send to agent", "dispatch"? → send_task / send_task_streaming
├── "what agents", "capabilities", "who can"? → list_agents / fetch_agent_card
├── "task status", "progress", "check on"? → get_task / list_tasks
├── "cancel", "stop task"? → cancel_task
├── "subscribe", "notifications"? → subscribe_events / manage_push_notifications

Key Workflows

Discover and Dispatch (3 calls)

list_agents → find agents with matching capabilities
fetch_agent_card(agent_id) → verify skills and input schema
send_task(agent_id, task) → dispatch with proper input format

Monitor and Collect (2 calls)

get_task(task_id) → check status (queued/running/complete/failed)
If streaming: send_task_streaming → get partial results as they arrive

MUST DO

Validate agent card before dispatching sensitive data
Set explicit timeouts on all tasks
Track every task to completion (don't fire-and-forget)
Use streaming for long-running tasks (better UX)

MUST NOT DO

Don't send sensitive data to unvalidated agents
Don't leave tasks running indefinitely without timeout
Don't dispatch without checking agent is available