skills.rest
rudi193-cmd
rudi193-cmdCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

iterative-retrieval

Implements a 4-phase loop to progressively refine retrieval context for subagents.

Updated Aug 27, 2026
Search Tags:#context#codebase#subagents#multi-agent#retrieval#iterative-retrieval
One-click install
npx skills add https://github.com/rudi193-cmd/Aionic-Claude-Skills --skill iterative-retrieval-rudi193-cmd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/rudi193-cmd/Aionic-Claude-Skills/tree/main/skills/iterative-retrieval
Command: npx skills add https://github.com/rudi193-cmd/Aionic-Claude-Skills --skill iterative-retrieval-rudi193-cmd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents are spawned with incomplete context and cannot predict what information they will need, leading to inefficient retrieval and missing context. This pattern provides a structured approach to progressively refine and curate context to guide subagents effectively.

Core Features & Use Cases

  • Iterative 4-phase loop (DISPATCH, EVALUATE, REFINE, LOOP) to incrementally narrow down relevant files and context.
  • Supports dynamic discovery of code patterns, terminology, and gaps to improve relevance in multi-agent workflows.
  • Suitable for resolving context-too-large or missing-context failures and for building RAG-like retrieval pipelines in code exploration.

Quick Start

Start with a broad context search, evaluate results for relevance, refine keywords and patterns, and loop up to three cycles to assemble a concise, high-relevance 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 provide relevant codebase context to subagents when the initial retrieval is missing information?▼

Yes, iterative retrieval resolves context-too-large failures by evaluating initial retrieval results for relevance, identifying missing terminology or code patterns, and refining subsequent searches to assemble a concise, high-relevance context set for subagents.

How does iterative retrieval work in multi-agent workflows?▼

Iterative retrieval in multi-agent workflows uses a structured loop to dispatch subagents, evaluate returned context for relevance, refine keywords based on discovered gaps, and loop to incrementally narrow down the exact files needed for the task.

What is the best way to build a RAG-like retrieval pipeline for code exploration?▼

Building a RAG-like retrieval pipeline for code exploration is best achieved by starting with a broad context search, evaluating results for relevance, refining keywords, and looping up to three cycles to assemble a concise, high-relevance context set.

Why do spawned subagents fail to find the right files without iterative context refinement?▼

Spawned subagents fail because they receive incomplete context and cannot predict what information they will need, leading to inefficient retrieval and missing context that requires progressive refinement to resolve.

Related Skills

Explore More Software Engineering Skills→
ysyecustysyecust
40

iterative-retrieval

Refine subagent context through DISPATCH, EVALUATE, REFINE, and LOOP cycles.

Community
Basic
derekhu0002derekhu0002

iterative-retrieval

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

Community
Advanced
Michae2xlMichae2xl

iterative-retrieval

Refine codebase context for subagents through iterative retrieval loops.

Community
Advanced
Oruga420Oruga420

iterative-retrieval

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

Community
Advanced