skills.rest
Oruga420
Oruga420COMMUNITY
Explore all skills by this author →
Website𝕏@Oruga420GitHub

iterative-retrieval

Automate a 4-phase iterative retrieval loop for multi-agent code exploration.

Updated Mar 24, 2026
Search Tags:#context#codebase#discovery#multi-agent#retrieval#orchestration#iterative
One-click install
npx skills add https://github.com/Oruga420/claude-code-skills --skill iterative-retrieval-oruga420
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/Oruga420/claude-code-skills/tree/main/iterative-retrieval
Command: npx skills add https://github.com/Oruga420/claude-code-skills --skill iterative-retrieval-oruga420

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents in multi-agent workflows often operate with incomplete context, leading to wasted cycles and missing critical files or terminology. Iterative retrieval addresses this by progressively refining the search space to surface the most relevant code and documents without overfetching context.

Core Features & Use Cases

  • 4-phase loop that DISPATCHes queries, EVALUATEs relevance, REFINEs criteria, and LOOPs iterations to build context across a codebase.
  • Dynamic query refinement based on evaluation results to improve precision across large codebases.
  • Use cases include contextual code exploration, subagent orchestration, and efficient retrieval in RAG-like workflows.

Quick Start

Configure and run the iterative retrieval loop to progressively refine codebase context for subagents.

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 for subagents navigating a large codebase?▼

Multi-agent context retrieval uses a 4-phase loop: DISPATCH queries, EVALUATE relevance, REFINE criteria, and LOOP iterations. This dynamic query refinement progressively builds context across large codebases without overfetching.

Why do subagents miss critical files when exploring large repositories?▼

Subagents miss critical files due to incomplete initial context. Iterative retrieval addresses this by progressively refining the search space across the codebase, ensuring relevant code and documents are surfaced without overfetching.

Can I use iterative retrieval to refine RAG-like workflows for code exploration?▼

Yes, iterative retrieval supports efficient retrieval in RAG-like workflows for code exploration. It applies dynamic query refinement based on evaluation results to improve retrieval precision across large repositories.

What are the limitations of using a 3-cycle retrieval loop for codebase navigation?▼

The iterative retrieval loop is capped at a maximum of 3 cycles. This constraint prevents overfetching context but may limit discovery in deeply nested codebases requiring more extensive passes.

Related Skills

Explore More Software Engineering Skills→
michaelsvanbeekmichaelsvanbeek
1

anomaly-detection

Detect unusual patterns in time-series, logs, and metric data.

Community
Advanced
andrew-starosciakandrew-starosciak
2

iterative-retrieval

Refine subagent context through a four-stage iterative retrieval loop.

Community
Advanced
flag3flag3
1

iterative-retrieval

Guide subagents through a 4-phase retrieval loop to refine information.

Community
Basic
vrcmsvrcms
1

iterative-retrieval

Iteratively refine codebase search queries to identify relevant files.

Community
Advanced