skills.rest
KuaaMU
KuaaMUCOMMUNITY
Explore all skills by this author →
𝕏@X_SwarmMindGitHub

iterative-retrieval

Iteratively search and evaluate files to refine context retrieval in multi-agent workflows.

4|Updated Feb 14, 2026
Search Tags:#context retrieval#agent workflow#RAG#codebase exploration#iterative search#subagent problem
One-click install
npx skills add https://github.com/KuaaMU/omnihive --skill iterative-retrieval-kuaamu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/KuaaMU/omnihive/tree/main/library/ecc-skills/iterative-retrieval
Command: npx skills add https://github.com/KuaaMU/omnihive --skill iterative-retrieval-kuaamu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenge where subagents lack the necessary context to perform their tasks, especially when that context is not known upfront and needs to be discovered progressively within a codebase.

Core Features & Use Cases

  • Progressive Context Refinement: Iteratively searches and evaluates files to build the most relevant context for an agent.
  • Handles Unknown Context: Ideal for scenarios where the exact files or code snippets needed are not predictable.
  • Use Case: When an agent needs to fix a bug in an unfamiliar codebase, this Skill can help it discover the relevant files and code sections by starting with broad searches and narrowing down based on relevance and identified gaps.

Quick Start

Use the iterative-retrieval skill to find relevant files for the task "Implement user authentication flow".

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I retrieve unknown codebase context for subagents in an agent workflow?▼

To retrieve unknown codebase context for subagents, use iterative search techniques to progressively discover and evaluate files, building relevant context dynamically rather than relying on upfront predictions.

What is the best way to refine context retrieval for complex codebase exploration?▼

Refining context retrieval for codebase exploration involves executing broad initial searches, scoring file relevance, and iteratively narrowing results to resolve the subagent context problem in multi-agent workflows.

How does progressive context discovery work in RAG-like agent pipelines?▼

Progressive context discovery in RAG-like pipelines works by iteratively searching the codebase, evaluating identified gaps, and refining subsequent search queries to extract only the most relevant code sections.

When do I need iterative search for a multi-agent workflow?▼

You need iterative search for a multi-agent workflow when subagents must fix bugs or explore unfamiliar codebases where the exact files and code snippets required cannot be predicted before execution begins.

Can I use dynamic context discovery to help an agent fix bugs in an unfamiliar codebase?▼

Yes, dynamic context discovery helps agents fix bugs in unfamiliar codebases by starting with broad searches and progressively narrowing down files based on relevance scoring and identified context gaps.

Related Skills

Explore More Software Engineering Skills→
thanhquan3010thanhquan3010

iterative-retrieval

Refine codebase context retrieval through iterative query evaluation loops.

Community
Advanced
angrysky56angrysky56

coder

Review codebase context before editing to ensure minimal, verified code changes.

Community
Intermediate
sayasaya8039sayasaya8039
2

iterative-retrieval

Retrieve relevant codebase context for subagents through iterative refinement cycles.

Community
Intermediate
TakMczkTakMczk
1

iterative-retrieval

Iteratively retrieve and evaluate codebase files for multi-agent context refinement.

Community
Advanced