iterative-retrieval

Name: iterative-retrieval
Availability: InStock
Author: fabio29t

Iteratively search and evaluate files to refine context retrieval for sub-agents.

Updated Mar 4, 2026

Search Tags:#refinement #context retrieval #multi-agent systems #codebase navigation #sub-agent #iterative search

Ready to run

npx skills add https://github.com/Fabio29T/Everything-Claude --skill iterative-retrieval-fabio29t

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/Fabio29T/Everything-Claude/tree/main/docs/ja-JP/skills/iterative-retrieval
Command: npx skills add https://github.com/Fabio29T/Everything-Claude --skill iterative-retrieval-fabio29t

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the "context problem" in multi-agent workflows where sub-agents lack sufficient information to start their tasks, preventing them from knowing which files or code patterns are relevant.

Core Features & Use Cases

Iterative Context Refinement: A 4-phase loop (Dispatch, Evaluate, Refine, Loop) to progressively narrow down relevant files.
Dynamic Query Building: Adapts search patterns, keywords, and exclusions based on relevance evaluation.
Use Case: When a sub-agent needs to fix a bug in a complex codebase, this Skill can intelligently identify the most relevant files related to authentication and session management, even if the initial query is broad.

Quick Start

Use the iterative-retrieval skill to find files relevant to fixing the 'authentication token expiry bug'.

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 for sub-agents in a complex codebase?▼

Refine context retrieval for sub-agents by iteratively searching and evaluating files through a four-phase loop. This progressively narrows down relevant files based on task relevance, ensuring sub-agents receive precise actionable information without exceeding context limits.

What is iterative context refinement for multi-agent systems?▼

Iterative context refinement is a four-phase loop of Dispatch, Evaluate, Refine, and Loop that progressively narrows down relevant files. It solves the context problem in multi-agent workflows where sub-agents lack sufficient information to identify relevant files or code patterns.

Why does my sub-agent fail to find relevant files with broad search queries?▼

Sub-agents fail with broad queries because initial searches lack specific keywords. This skill handles this by adapting search criteria, dynamically building new search patterns, keywords, and exclusions based on relevance evaluation across multiple iterations.

Can I use iterative search to fix bugs related to authentication and session management?▼

Yes, you can use iterative search to fix authentication and session management bugs. The skill intelligently identifies the most relevant files related to these specific areas even when the initial query is too broad, adapting search patterns to find precise code patterns.

What's the best way to navigate a codebase when initial queries exceed context limits?▼

The best way to navigate a codebase without exceeding context limits is using dynamic query building. It adapts search patterns, keywords, and exclusions based on relevance evaluation, ensuring sub-agents receive only precise actionable information rather than excessive file data.

When should I not use iterative file retrieval for sub-agent tasks?▼

Iterative file retrieval is unnecessary when sub-agents already have specific keywords or know exactly which files are relevant. It is designed for scenarios where initial queries are too broad or lack specific keywords, requiring adaptive search criteria to find relevant code patterns.