deep-learn

Orchestrate parallel-agent research and synthesize findings into a Markdown knowledge file.

1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/ourines/claude-code-learn --skill deep-learn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-learn
Source: https://github.com/ourines/claude-code-learn/tree/main/skills/deep-learn
Command: npx skills add https://github.com/ourines/claude-code-learn --skill deep-learn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enable fast, deep understanding of complex topics by orchestrating parallel-agent research that culminates in a single, comprehensive knowledge file stored under ~/.claude/learnings/.

Core Features & Use Cases

  • Parallel-agent research: launches multiple agents to explore distinct dimensions of a topic simultaneously.
  • Synthesis & persistence: merges findings into a structured knowledge file for reuse and recall.
  • Flexible orchestration: supports Subagents and Team Agents modes to match topic complexity and collaboration needs.

Quick Start

Analyze a topic by providing its name and let the system run a deep, parallel investigation and save the results locally.

Frequently Asked Questions about deep-learn

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

FAQPage Schema
How do I conduct deep parallel research on a complex topic?

You can conduct deep parallel research by orchestrating multiple agents to explore distinct dimensions of a topic simultaneously. The system merges findings into a structured knowledge file for reuse and recall.

What is the best way to synthesize knowledge from multi-dimensional topic research?

The best way to synthesize knowledge from multi-dimensional topic research is to use parallel-agent orchestration that merges findings into a structured Markdown file. This creates a persistent knowledge base for reuse and recall.

Does deep research with parallel agents support different orchestration modes?

Yes, deep research with parallel agents supports flexible orchestration with two modes: Subagents and Team Agents. These modes match topic complexity and collaboration needs during multi-dimensional exploration.

How do I save and persist synthesized research results locally?

To save and persist synthesized research results locally, the system automatically writes the compiled knowledge file to ~/.claude/learnings/ as a slugged Markdown file. This ensures findings are stored for later reuse.

When should I use agent-based research for topic exploration?

You should use agent-based research for topic exploration when dealing with complex or broad topics that benefit from multi-dimensional exploration and cross-agent synthesis. It enables fast understanding by investigating distinct dimensions simultaneously.