iterative-retrieval

Refine subagent context through an iterative four-phase retrieval loop.

3|Updated Jan 29, 2026

Search Tags:#context #subagents #evaluation #retrieval #phases #iterative #code-search

Ready to run

npx skills add https://github.com/peopleforrester/claude-dotfiles --skill iterative-retrieval-peopleforrester

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/peopleforrester/claude-dotfiles/tree/main/skills/optimization/iterative-retrieval
Command: npx skills add https://github.com/peopleforrester/claude-dotfiles --skill iterative-retrieval-peopleforrester

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents often lack the necessary context to perform tasks effectively. This skill introduces a four-phase Iterative Retrieval loop to build and refine the contextual data fed to subagents, reducing wasted effort and context gaps.

Core Features & Use Cases

4-Phase Loop: DISPATCH, EVALUATE, REFINE, LOOP to progressively narrow context.
Context Gap Identification: Detects missing terms and files to guide further searches.
Applicable for unfamiliar codebases and architectural analysis: Ideal for delegating research and exploratory tasks.

Quick Start

Start the loop by providing a topic and initial keywords; iteratively dispatch searches, evaluate results, refine criteria, and loop until stopping criteria are met or enough high-quality context is gathered.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I improve subagent context when exploring an unfamiliar codebase?▼

Subagent context improves by applying an iterative retrieval loop that progressively narrows contextual data through four phases: DISPATCH, EVALUATE, REFINE, and LOOP. This reduces wasted effort and context gaps during delegation.

What is the best way to identify context gaps during architectural analysis?▼

Identifying context gaps during architectural analysis is best handled by iterative retrieval, which detects missing terms and files to guide targeted searches and converge on high-value context.

How do I start an iterative retrieval loop for code search?▼

To start an iterative retrieval loop for code search, provide a topic and initial keywords. Iteratively dispatch searches, evaluate results, refine criteria, and loop until stopping criteria are met or enough high-quality context is gathered.

When should I use iterative retrieval for subagent delegation?▼

Iterative retrieval for subagent delegation is used when the context needed evolves as work progresses, such as during research tasks, exploration of unfamiliar codebases, or architectural analysis.

How does the four-phase retrieval workflow refine contextual data?▼

The four-phase workflow refines contextual data by dispatching searches, evaluating results for gaps, refining search criteria with targeted file reading, and looping until explicit stopping criteria are met.

Why do subagents lack necessary context for exploratory tasks?▼

Subagents lack necessary context because exploratory tasks require evolving information. Iterative retrieval solves this by progressively refining contextual data through an explicit loop, reducing wasted effort and context gaps.