iterative-retrieval

Name: iterative-retrieval
Availability: InStock
Author: danielkhigay

Refine retrieved materials across up to three DISPATCH, EVALUATE, REFINE, and LOOP cycles.

Updated Feb 19, 2026

Search Tags:#refinement #codebase #discovery #evaluation #multi-agent #context-management #iterative-retrieval

Ready to run

npx skills add https://github.com/danielkhigay/gaz --skill iterative-retrieval-danielkhigay

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/danielkhigay/gaz/tree/main/.claude/skills/archived/iterative-retrieval
Command: npx skills add https://github.com/danielkhigay/gaz --skill iterative-retrieval-danielkhigay

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Iterative retrieval addresses the context problem in multi-agent workflows by progressively refining the information provided to subagents.

Core Features & Use Cases

Phase-driven context discovery across DISPATCH, EVALUATE, REFINE, and LOOP.
Reduces context explosion by filtering and focusing on high-relevance files.
Enables predictable three-cycle limits for balanced performance and quality.

Quick Start

Start with a broad query, evaluate results for relevance, and iteratively refine search criteria for up to three cycles to assemble a high-quality context set.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I resolve the context problem in multi-agent workflows when subagents need unpredictable codebase information?▼

Iterative retrieval resolves multi-agent context problems by progressively refining retrieved codebase materials across multiple cycles, evaluating and filtering files to ensure subagents receive high-relevance context without causing context explosion.

How do I incrementally discover relevant files in a large codebase for subagent dispatch?▼

Incremental codebase discovery is achieved by starting with a broad query, evaluating retrieved materials for relevance, and iteratively refining search criteria through phased dispatch and evaluation cycles to assemble a focused context set.

What is the maximum number of retrieval cycles allowed for refining code context?▼

The maximum limit for refining code context is a hard cap of three cycles, which balances context quality and efficiency by preventing infinite looping while allowing sufficient incremental discovery and refinement.

Does iterative retrieval require any specific dependencies or external components to manage codebase context?▼

Iterative retrieval requires no specific dependencies or external components to manage codebase context, operating as a standalone workflow strategy for filtering and focusing on high-relevance files during multi-agent tasks.

When should I not use an iterative retrieval approach for context management?▼

Iterative retrieval should not be used when subagents require context that can be fully predicted upfront, as the phased discovery and refinement cycles are specifically designed for incremental discovery in unpredictable codebase or document workflows.