deep-dive
Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.
Best for Technical research projectsWorks with GitHub
⌘source
- author
@rohitg00- language
- JavaScript
★1.3kstars
407forks
Apr 19, 2026
✦overview.md
Key Features
- ·DAG-based query planning for research decomposition
- ·Parallel subagent execution for faster research
- ·Gap-driven iteration to refine findings
- ·No external API dependencies required
- ·Autonomous deep research capability
Use Cases
- →Investigating complex technical topics requiring multiple angles
- →Researching competitive landscape analysis for product decisions
- →Exploring emerging technologies with multiple interdependent aspects
- →Conducting literature reviews on academic or technical subjects
Best for
- ✓Technical research projects
- ✓Comprehensive topic investigations
- ✓Multi-faceted analysis tasks
Not ideal for
- !Simple fact-checking questions
- !Real-time data queries
- !Tasks requiring external API integration
FAQs
name
deep-dive
description
Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.
user-invocable:true
argument:The research question or topic to investigate deeply
Deep Dive
Autonomous deep research using the same DAG-based planning pattern as Google's Deep Research — but running entirely on Claude Code with no external dependencies.
How it works
- Plan — decompose the question into a DAG of sub-questions with dependencies
- Fan out — run independent sub-questions in parallel via Agent subagents
- Gap analysis — each subagent returns findings + identified gaps
- Iterate — gaps become new sub-questions, fed back into the DAG
- Synthesize — once all nodes complete, produce a final report
Steps
1. Decompose into a DAG
Given the research question, generate a DAG of sub-questions. Each node has:
- id: short identifier (e.g.,
q1,q2a) - question: the specific sub-question to research
- depends_on: list of node IDs whose answers are needed first (empty = no dependencies)
Rules for decomposition:
- Start with foundational/context-setting questions that have no dependencies
- Build toward analytical/comparative questions that depend on foundational answers
- Aim for 4-8 nodes. If the topic needs more, cap at 12.
- Each node should be answerable with 1-3 web searches
$install
1-click copynpx skills add rohitg00/awesome-claude-code-toolkit --skill deep-diveSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.