iterative-retrieval

Refines context retrieval for subagents through iterative search cycles.

86|21|Updated Feb 9, 2026

Search Tags:#context #search #retrieval #subagent #relevance #iterative

Ready to run

npx skills add https://github.com/Jamkris/everything-gemini-code --skill iterative-retrieval-jamkris

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/Jamkris/everything-gemini-code/tree/main/skills/iterative-retrieval
Command: npx skills add https://github.com/Jamkris/everything-gemini-code --skill iterative-retrieval-jamkris

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents are spawned with limited context and don't know what files or patterns are relevant until they start working, leading to inefficient or incorrect retrieval.

Core Features & Use Cases

Four-phase iterative retrieval loop (DISPATCH, EVALUATE, REFINE, LOOP) to progressively refine context and improve relevance.
Automatically identifies gaps in context and updates search criteria to focus on missing areas.
Scales across codebases and documentation, enabling smarter subagent collaboration in multi-agent workflows.

Quick Start

Provide a task and initiate an iterative retrieval process; the system will dispatch, evaluate, and refine up to three cycles, returning high-relevance results.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I improve context retrieval relevance for subagents with limited initial context?▼

Iterative context retrieval improves subagent relevance by running a four-phase loop that evaluates search results, refines queries, and expands or excludes candidates based on relevance scores.

What is the best way to automate context search for subagents in a multi-agent workflow?▼

Automating context search in multi-agent workflows is best handled by an iterative retrieval loop that dispatches queries, evaluates results, and refines criteria across up to three cycles for high-relevance output.

How does iterative search refinement handle missing context in large codebases?▼

Iterative search refinement handles missing context by automatically identifying gaps during the evaluation phase and updating search criteria in subsequent loops to focus on missing areas across codebases.

Can I use iterative retrieval to scale subagent context search across codebases and documentation?▼

Yes, iterative retrieval scales across codebases and documentation by using a four-phase loop that progressively expands or excludes search candidates based on relevance scores.

Why do subagents return irrelevant files when performing initial context searches?▼

Subagents return irrelevant files because they are spawned with limited context and lack awareness of relevant patterns until an iterative retrieval loop evaluates and refines search criteria.

What are the limitations of using a fixed cycle count for iterative context retrieval?▼

A fixed cycle count limits iterative context retrieval to three refinement loops, which may not fully resolve complex missing context gaps across highly fragmented codebases.