iterative-retrieval

Iteratively refine context retrieval across four phases for multi-agent workflows.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/thangvawn/agent_financial --skill iterative-retrieval-thangvawn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/thangvawn/agent_financial/tree/main/.cursor/skills/iterative-retrieval
Command: npx skills add https://github.com/thangvawn/agent_financial --skill iterative-retrieval-thangvawn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The Skill solves the "context problem" in multi-agent workflows where subagents need progressively refined context.

Core Features & Use Cases

  • Iterative Retrieval: Refines context in 4 phases for subagents in multi-agent workflows.
  • Progressive Refinement: Ensures that agents receive the context they need as they perform their tasks.
  • Use Case: Ideal for subagents that don't know what context they need upfront, such as in building multi-agent workflows where context evolves.

Quick Start

Run the skill to retrieve context for your multi-agent workflow task.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I refine context retrieval for subagents in a multi-agent workflow?

You refine context retrieval for multi-agent workflows by using a 4-phase iterative loop that progressively supplies subagents with the exact context they need as their tasks evolve.

What is the context problem in multi-agent workflows and how does iterative retrieval fix it?

The context problem in multi-agent workflows occurs when subagents lack upfront knowledge of required context. Iterative retrieval fixes this by progressively refining context across 4 phases as agent tasks evolve.

How do I optimize token usage during code exploration with multiple agents?

To optimize token usage during code exploration, implement iterative context retrieval to ensure subagents only receive progressively refined, necessary context rather than loading excessive upfront information.

When should I use iterative context refinement instead of static context loading for agent orchestration?

Use iterative context refinement for agent orchestration when subagents do not know what context they need upfront, requiring progressive retrieval to support evolving tasks in multi-agent workflows.

Does iterative context retrieval require any specific dependencies or framework setups?

Iterative context retrieval requires no external dependencies or specific framework setups, operating entirely through included scripts to manage the 4-phase progressive refinement loop.