iterative-retrieval

Name: iterative-retrieval
Availability: InStock
Author: lllooollpp

Refine codebase context for subagents through a four-phase iterative retrieval loop.

Updated Aug 27, 2026

Search Tags:#workflow #context #codebase #subagents #retrieval #iterative-retrieval

Ready to run

npx skills add https://github.com/lllooollpp/solopreneur- --skill iterative-retrieval-lllooollpp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/lllooollpp/solopreneur-/tree/main/solopreneur/data/skills/iterative-retrieval
Command: npx skills add https://github.com/lllooollpp/solopreneur- --skill iterative-retrieval-lllooollpp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents often start with limited context and need to retrieve relevant files without overloading prompts. This Skill provides a four-phase iterative loop to progressively refine codebase context for subagents, enabling accurate discovery while reducing token usage.

Core Features & Use Cases

Four-phase loop: DISPATCH, EVALUATE, REFINE, LOOP to surface high-relevance files.
Context-aware refinement: adapt queries based on evaluation of retrieved results.
Use cases: codebase exploration, multi-agent workflows, and token-limited retrieval scenarios.

Quick Start

Provide an initial broad query and let the system iteratively refine its search to surface high-relevance files.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I retrieve relevant codebase context for subagents without overloading token limits?▼

Iterative retrieval progressively surfaces high-relevance files for subagents without overloading token limits. It uses a four-phase DISPATCH, EVALUATE, REFINE, and LOOP cycle to dynamically refine codebase context based on relevance scoring.

What is the best way to refine subagent context in multi-agent workflows?▼

Refining subagent context in multi-agent workflows is best handled by an iterative loop that evaluates retrieved results and adapts queries. This context-aware refinement progressively narrows down high-relevance files across multiple cycles.

How do I start iterative codebase exploration to surface high-relevance files?▼

To start iterative codebase exploration, provide an initial broad query. The system dispatches the query, evaluates the retrieved results, refines the search based on relevance scoring, and loops until high-relevance files are surfaced.

Can I set a maximum number of cycles for progressive context refinement?▼

Yes, progressive context refinement supports a configurable maximum cycle limit. The four-phase loop stops after reaching the maximum cycles or when the evaluation phase determines the retrieved codebase context is sufficiently relevant.

Why does my subagent retrieve irrelevant files when exploring a large codebase?▼

Subagents retrieve irrelevant files when exploring a large codebase due to limited initial context. Applying iterative retrieval solves this by dynamically refining queries based on evaluation scoring to progressively surface only high-relevance files.

Does iterative retrieval work for token-limited scenarios requiring codebase context?▼

Iterative retrieval works effectively for token-limited scenarios by progressively refining codebase context. It reduces token usage by adapting queries and retrieving only high-relevance files instead of loading entire codebases into subagent prompts.