agent-orchestration
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
npx skills add majiayu000/claude-skill-registry --skill agent-orchestration-bbgnsurftech-claude-skills-collec-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill provides a delegation framework for orchestrator AIs to coordinate specialist sub-agents. It structures task delegation using the scientific method (observation → hypothesis → prediction → experimentation → verification → conclusion) and defines clear success criteria while preserving agent autonomy in execution (HOW). It is intended for planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows and applies when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents.
How it works
- The orchestrator routes context and observations between user and agents.
- It defines measurable success criteria and enables comprehensive discovery.
- It requires maintaining world-building context: WHERE, WHAT, WHY, and trusts agents’ 200k context window for implementation decisions (HOW).
- It aligns delegation with the scientific method: observations, hypotheses by agents, testable predictions, agent-designed experiments, verification against official sources, and conclusions drawn by agents.
- Before delegation, it enforces a Pre-Delegation Verification Checklist that emphasizes observations without assumptions, pass-through data, definitions of success, world-building context, and preserved agent autonomy.
- It provides a Task Tool Invocation Rule and a Delegation Template to structure prompts for sub-agents, starting with a specific ROLE_TYPE statement and following with structured sections: OBSERVATIONS, DEFINITION OF SUCCESS, CONTEXT, YOUR TASK, INVESTIGATION REQUIREMENTS, VERIFICATION REQUIREMENTS, AVAILABLE RESOURCES.
When to use it
Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows and when the model’s ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents.
What it can touch
- Tools: The skill references tool invocation through a Task tool and specific prompt templates. The Delegation Template instructs the sub-agent to perform steps using available functions and MCP tools, project exploration, and external resources. It explicitly lists a procedure to run /is-it-done checks and to verify each checklist item as work progresses.
Caveats
- License: MIT
- Declares that sub-agents have full tool access and 200k context windows, with an emphasis on not constraining their domain expertise.
- Emphasizes strict adherence to the Delegation Template and checklist-driven verification; it warns against prescribing implementation details to sub-agents, to avoid reducing their autonomy.
# Agent Orchestration ## Overview This skill provides a scientific delegation framework for orchestrator AIs coordinating specialist sub-agents. Apply this framework to structure task delegation that enables agents to follow the scientific method (observation → hypothesis → prediction → experimentation → verification → conclusion) while maintaining clear boundaries between strategic direction (orchestrator) and tactical implementation (agent). ## Core Principle **Provide world-building context (WHERE, WHAT, WHY). Define success criteria. Trust agent expertise for implementation (HOW).** The orchestrator's role is to: - Route context and observations between user and agents - Define measurable success criteria - Enable comprehensive discovery - Trust agent expertise and their 200k context windows **Reason**: Sub-agents are specialized experts with full tool access. Prescribing implementation limits their ability to discover better solutions and prevents them from applying their domain expertise effectively. ## Scientific Method Alignment Structure delegation to enable agents to follow the scientific method: 1. **Observation** → Provide factual observations, not interpretations 2. **
- Overview
- Core Principle
- Scientific Method Alignment
- Pre-Delegation Verification Checklist
- Task Tool Invocation Rule
- Delegation Template
- Writing Effective AVAILABLE RESOURCES
- Resource Description Patterns
- Complete Example
- Context Calibration Patterns
- Inclusion Rules: What to Include vs Exclude
- ✅ INCLUDE: Factual Observations
- ✅ INCLUDE: User Requirements
- ✅ INCLUDE: Available Tools/Resources
What does the agent-orchestration skill do?
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill agent-orchestration-bbgnsurftech-claude-skills-collec-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.