iterative-retrieval

Iteratively refine context through a 4-phase retrieval loop for multi-agent workflows.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/TymorIbrahim/UniPilot --skill iterative-retrieval-tymoribrahim
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/TymorIbrahim/UniPilot/tree/main/.cursor/skills/iterative-retrieval
Command: npx skills add https://github.com/TymorIbrahim/UniPilot --skill iterative-retrieval-tymoribrahim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of subagents in multi-agent workflows, which may not know what context they need until they begin their tasks.

Core Features & Use Cases

  • Iterative Retrieval: Progressively refines context through a 4-phase loop (DISPATCH, EVALUATE, REFINE, LOOP) for enhanced relevance and reduced redundancy.
  • Use Case: Useful in scenarios like subagents requiring codebase context in multi-agent workflows or for designing retrieval pipelines in code exploration.

Quick Start

To initiate iterative retrieval for a task, activate the 'iterative-retrieval' skill with your specific task prompt.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I refine context retrieval in multi-agent workflows when subagents don't know what they need initially?

Iterative context retrieval refines context dynamically by using a 4-phase loop: DISPATCH, EVALUATE, REFINE, and LOOP. This allows subagents to progressively adjust and retrieve relevant context during task execution.

How does iterative retrieval work for codebase exploration tasks?

Iterative retrieval for codebase exploration works by dispatching subagents to evaluate initial context, refining their queries based on evaluation results, and looping until the relevant code context is gathered without redundancy.

When do I need dynamic context adjustment in multi-agent workflows?

Dynamic context adjustment is needed when subagents cannot determine the required context until they begin their tasks. This is common in complex codebase exploration where dependencies and relevant files are discovered during execution.

Can I use iterative retrieval to design pipelines for complex code exploration?

Yes, you can use iterative retrieval to design retrieval pipelines for code exploration. It supports scenarios requiring progressive context refinement, enabling agents to dynamically adjust what codebase context they retrieve.

What is the best way to reduce context redundancy in multi-agent codebase interactions?

The best way to reduce context redundancy is using an iterative retrieval loop. By continuously evaluating and refining the context fetched during multi-agent interactions, the workflow discards irrelevant data and enhances task relevance.

Does iterative retrieval require specific dependencies to manage context in multi-agent workflows?

No specific dependencies are required to use iterative retrieval for context management. The skill operates independently to provide the progressive context refinement loop for multi-agent workflows.