Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/agent-orchestrator
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Passed 11 of 17 test cases with the skill, and 4 of 17 without it.
and 12 more in the full report
10 fixed4 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When creating an isolated workspace directory for a subtask worker named security-scanner, what command line utility and flag should be called?
| Checked | Without skill | With skill |
|---|---|---|
| Invokes python3 scripts/create_agent.py with the agent name argument. | Missed | Passed |
| Passes the target directory path via the --workspace option. | Missed | Passed |
The instructions your model reads when the skill loads.
Orchestrate complex tasks by decomposing them into subtasks, spawning autonomous sub-agents, and consolidating their work.
Analyze the macro task and break it into independent, parallelizable subtasks:
1. Identify the end goal and success criteria
2. List all major components/deliverables required
3. Determine dependencies between components
4. Group independent work into parallel subtasks
5. Create a dependency graph for sequential work
Decomposition Principles:
For each subtask, create a sub-agent workspace:
python3 scripts/create_agent.py <agent-name> --workspace <path>
This creates:
<workspace>/<agent-name>/
âââ SKILL.md # Generated skill file for the agent
âââ inbox/ # Receives input files and instructions
âââ outbox/ # Delivers completed work
âââ workspace/ # Agent's working area
âââ status.json # Agent state tracking
test cases passed, vs 4 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.