skills.rest
AtlasRoX
AtlasRoXCOMMUNITY
Explore all skills by this author →
GitHub

iterative-retrieval

Iteratively refine search queries to retrieve relevant code context for AI agents.

Updated Jan 27, 2026
Search Tags:#context retrieval#information retrieval#ai agent#pattern matching#codebase navigation#subagent communication
One-click install
npx skills add https://github.com/AtlasRoX/super-fiesta --skill iterative-retrieval-atlasrox
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/AtlasRoX/super-fiesta/tree/main/skills/iterative-retrieval
Command: npx skills add https://github.com/AtlasRoX/super-fiesta --skill iterative-retrieval-atlasrox

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of providing subagents with the precise code context they need to perform tasks, overcoming limitations of sending too much or too little information.

Core Features & Use Cases

  • Progressive Context Refinement: Iteratively searches and evaluates files to pinpoint the most relevant code snippets.
  • Dynamic Query Adjustment: Learns from initial search results to refine keywords, patterns, and exclusions for subsequent searches.
  • Use Case: When debugging a complex issue, this Skill can intelligently identify the specific files and functions related to the bug, even if the initial search terms are not exact matches.

Quick Start

Use the iterative retrieval skill to find all files related to user authentication.

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 code context for an AI agent without sending too much information?▼

Progressive context retrieval solves this by iteratively dispatching broad search queries, evaluating file relevance, and refining search criteria to gather precise code snippets for AI agents.

What is the iterative search process for finding specific files related to a complex codebase bug?▼

The process dispatches an initial broad search, evaluates retrieved file relevance, refines search criteria based on the evaluation, and loops up to three times to pinpoint exact files and functions.

Can I use dynamic query adjustment when initial codebase navigation search terms are not exact matches?▼

Yes, dynamic query adjustment learns from initial search results to refine keywords, pattern matching criteria, and exclusions for subsequent searches to find relevant code context.

Does progressive context retrieval work for subagent communication in complex software engineering tasks?▼

Yes, it specifically solves the subagent context problem by iteratively refining search queries to provide subagents with the precise code context needed for complex software engineering tasks.

What are the limitations of iterative context retrieval when searching a large codebase?▼

The main limitation is that the progressive search loop runs a maximum of three times, meaning highly dispersed or deeply nested code context across a massive codebase might not be fully gathered.

Related Skills

Explore More Software Engineering Skills→
nubivnubiv

iterative-retrieval

Refine context retrieval iteratively across up to three query loops.

Community
Advanced
tdiminotdimino
41

codex-orchestrator

Orchestrate OpenAI Codex CLI subagents with custom personas for development tasks.

Community
Advanced
fakhriaditiarahmanfakhriaditiarahman
1

writing-plans

Generate step-by-step implementation plans with file modifications and commands.

Community
Intermediate
beratcelik1beratcelik1
1

iterative-retrieval

Iteratively search, score, and refine file retrieval for subagent context.

Community
Intermediate