iterative-retrieval

Enforce three-cycle sub-agent spawns with WHY-context and coordinator validation.

1|Updated Apr 18, 2026
One-click install
npx skills add https://github.com/DeDuva/squad --skill iterative-retrieval-deduva
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/DeDuva/squad/tree/main/packages/squad-cli/templates/skills/iterative-retrieval
Command: npx skills add https://github.com/DeDuva/squad --skill iterative-retrieval-deduva

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Iterative Retrieval Skill provides a disciplined protocol for spawning sub-agents, ensuring WHY context is included and coordinator validation governs output, thereby preventing vague handoffs and unbounded cycles.

Core Features & Use Cases

  • Enforces a max of three work cycles per sub-task with explicit delta passing between cycles.
  • Requires WHY context in every spawn to justify purpose and desired outcome.
  • Provides a coordinator validation checklist to ensure completeness before closure.
  • Use Case: Coordinate a complex data-labeling task that benefits from structured handoffs and auditable decisions across multiple agents.

Quick Start

Provide a concrete spawn prompt applying the 3-cycle protocol to a sub-task in your project.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I enforce bounded iteration when spawning sub-agents for complex tasks?

You can enforce bounded iteration by applying a max three-cycle protocol with explicit delta passing between cycles. This limits sub-agent work cycles to three iterations, ensuring structured handoffs and preventing unbounded loops.

What is WHY-context in sub-agent coordination and when do I need it?

WHY-context is explicit motivation included in every sub-agent spawn to justify purpose and desired outcomes. You need it when coordinating complex projects to prevent vague handoffs and ensure auditable decisions across multiple agents.

How to add coordinator validation to a multi-agent workflow?

Add coordinator validation by applying a formal checklist within the spawn process to verify sub-task completeness before closure. This validates sub-agent outputs against requirements, ensuring quality assurance for complex project handoffs.

What's the best way to structure sub-task handoffs across multiple agents?

The best way to structure handoffs is using a disciplined protocol that requires WHY-context inclusion and enforces a maximum of three cycles per sub-task. This ensures explicit delta passing and coordinator validation for auditable outcomes.

Does sub-agent coordination work for complex data-labeling tasks requiring structured handoffs?

Yes, sub-agent coordination works for complex data-labeling tasks by applying a three-cycle protocol with WHY-context and coordinator validation. This provides structured handoffs and auditable decisions across multiple agents.

When should I not use unbounded cycles for sub-agent tasks?

You should avoid unbounded cycles when sub-agent tasks require strict quality assurance and auditable outcomes. Instead, enforce a max three-cycle protocol with explicit delta passing and coordinator validation to prevent vague handoffs.