iterative-retrieval

Implement a 4-phase iterative retrieval pattern for subagent context management.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/PAISHU-AI/PAI-zong-NB --skill iterative-retrieval-paishu-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/PAISHU-AI/PAI-zong-NB/tree/main/skills/iterative-retrieval
Command: npx skills add https://github.com/PAISHU-AI/PAI-zong-NB --skill iterative-retrieval-paishu-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of providing subagents with the right context at the right time, solving the "context problem" in multi-agent workflows.

Core Features & Use Cases

  • Context Refinement: Progressively refines context for subagents in multi-agent workflows.
  • Subagent Orchestration: Helps in designing RAG-like retrieval pipelines for code exploration.
  • Token Optimization: Optimizes token usage in agent orchestration.
  • Use Case: When building multi-agent workflows where context is progressively refined, this Skill can help in avoiding "context too large" or "missing context" failures.

Quick Start

To use the iterative-retrieval skill, activate it with the following command: iterative-retrieval task "Your task description here".

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I manage context size for subagents in multi-agent workflows?

Multi-agent workflows require progressive context refinement to prevent subagent failures. This Skill applies a 4-phase iterative retrieval pattern to deliver the right context at the right time, avoiding token overload and missing information.

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

RAG-like retrieval pipelines for code exploration need iterative context extraction. This Skill provides a 4-phase pattern to progressively refine context, ensuring subagents receive relevant code snippets without exceeding token limits.

How do I fix missing context or context too large errors in agent orchestration?

Agent orchestration failures from context issues require iterative context refinement. This Skill applies a 4-phase retrieval pattern to progressively filter and deliver context, resolving both missing context and token overflow errors.

Can I use iterative retrieval to optimize token usage in multi-agent systems?

Iterative retrieval optimizes token usage by progressively refining context for subagents. This Skill implements a 4-phase pattern that filters unnecessary information, reducing token consumption in complex multi-agent workflows.

When do I need progressive context refinement for subagent orchestration?

Subagent orchestration needs progressive context refinement when subagents require specific, filtered information across multiple stages. This Skill provides a 4-phase iterative retrieval pattern for scenarios like RAG pipelines or complex multi-agent workflows.

Does iterative retrieval require dependencies for context management?

Iterative retrieval for context management requires no external dependencies. This Skill uses scripts to implement a 4-phase pattern that integrates directly into multi-agent workflows for progressive context refinement.