compose-team

Assemble context bundles for AI sub-agents from memory indexes.

157|28|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/Fr-e-d/GAAI-framework --skill compose-team-fr-e-d
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compose-team
Source: https://github.com/Fr-e-d/GAAI-framework/tree/main/.gaai/core/skills/delivery/compose-team
Command: npx skills add https://github.com/Fr-e-d/GAAI-framework --skill compose-team-fr-e-d

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures that each sub-agent in an AI workflow receives precisely the necessary context, preventing token waste and context drift while avoiding information starvation that could lead to failures.

Core Features & Use Cases

  • Contextual Bundling: Dynamically creates context packages tailored for specific sub-agents (Planning, Implementation, QA, MicroDelivery).
  • Memory Resolution: Safely resolves memory file paths from an index, ensuring up-to-date context without hardcoding.
  • Tiered Context: Provides minimal context for MicroDelivery and comprehensive context for core team agents.
  • Use Case: After a story is evaluated, this skill prepares the exact files and memory categories needed for the Planning agent to create an execution plan, ensuring it has all relevant project details and past decisions.

Quick Start

Use the compose-team skill to prepare the context bundle for the planning sub-agent.

Frequently Asked Questions about compose-team

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

FAQPage Schema
What is agent context bundling for AI workflow automation?

Agent context bundling assembles precise context packages for AI sub-agents based on evaluated story outputs and system rules. It ensures isolation and efficiency by providing only the necessary files and memory categories to each specific agent, preventing token waste and context drift.

How do I prepare context for planning and QA sub-agents?

To prepare context for planning and QA sub-agents, you apply tiered input requirements that dynamically create tailored context packages. This ensures core team agents receive comprehensive project details and past decisions while MicroDelivery agents get minimal necessary files.

How does memory resolution work when assembling sub-agent context?

Memory resolution works by safely resolving memory file paths from an index. This ensures sub-agents receive up-to-date context for the delivery pipeline without hardcoding file locations, maintaining accuracy across the agent orchestration workflow.

Why do AI sub-agents fail without tiered context isolation?

AI sub-agents fail without tiered context isolation due to information starvation or context drift. Assembling precise context bundles prevents these issues by evaluating story outputs and applying strict memory category limits, ensuring each agent receives exactly what it needs.

Can I use context bundling for a micro-delivery agent pipeline?

Yes, you can use context bundling for a micro-delivery agent pipeline. The system provides tiered context, delivering minimal necessary files and memory categories specifically tailored for MicroDelivery agents to ensure execution efficiency and isolation.

What is the best way to prevent token waste in agent orchestration?

The best way to prevent token waste in agent orchestration is to assemble precise context bundles. By dynamically managing context resolution and providing only necessary files to each sub-agent, you avoid information overload and context drift.