recursive-decomposition

Decompose large tasks into smaller subproblems via recursive self-invocation.

Updated Mar 17, 2026

Search Tags:#automation #scalability #decomposition #ai-agent #codebase-analysis #recursive #task-planning

Ready to run

npx skills add https://github.com/Avi977/ace-claude-toolkit --skill recursive-decomposition-avi977

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: recursive-decomposition
Source: https://github.com/Avi977/ace-claude-toolkit/tree/main/skills/recursive-decomposition
Command: npx skills add https://github.com/Avi977/ace-claude-toolkit --skill recursive-decomposition-avi977

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Handling tasks that exceed context limits by recursively decomposing problems into smaller, manageable pieces and coordinating sub-agents to combine results.

Core Features & Use Cases

Recursive task decomposition: split large problems into smaller subproblems and orchestrate sub-agents.
Context-aware aggregation: gather results from partial analyses and synthesize a final answer.
Use Case: Analyze a codebase for cross-cutting concerns like security or performance across 10+ files.

Quick Start

Instruct the agent to decompose a large task into smaller subproblems and aggregate results through recursive self-invocation.

Frequently Asked Questions about recursive-decomposition

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

FAQPage Schema

How do I break down large codebase analysis tasks that exceed a single prompt limit?▼

Recursive decomposition handles tasks that exceed context limits by splitting large problems into smaller subproblems and orchestrating sub-agents to combine partial results into a synthesized final answer.

How does recursive decomposition work for multi-file research and project-wide planning?▼

Recursive decomposition manages multi-file research by applying recursive self-invocation to split context-heavy inputs into staged explorations, allowing sub-agents to process chunks and synthesize aggregated results.

Can I analyze cross-cutting concerns like security across 10+ files in a codebase?▼

Yes, you can analyze cross-cutting concerns like security across 10+ files by applying recursive task decomposition to split the codebase analysis into manageable subproblems and aggregating the partial findings.

What is the best way to orchestrate sub-agents for context-aware aggregation?▼

The best way to orchestrate sub-agents for context-aware aggregation is to use recursive self-invocation to delegate structured subproblems, gather partial analyses, and synthesize a final answer through robust staged exploration.

What are the limitations of using recursive self-invocation for task planning?▼

Recursive self-invocation for task planning is limited by its reliance on structured delegation and controlled context management, making it unsuitable for simple tasks that fit within single-prompt limits or require no multi-file synthesis.

Do I need any specific dependencies to automate task decomposition for an AI agent?▼

No specific dependencies are required to automate task decomposition; the skill operates independently by using recursive self-invocation to manage context and coordinate sub-agents for scalable project planning.