What is the Deep Research skill for Claude Code?

It is a specialized workflow that allows Claude to break down complex research goals into sub-tasks, execute them in parallel using sub-processes, and aggregate the findings into a polished report.

Which tools does this skill use for gathering data?

It prioritizes installed Claude skills first, then utilizes MCP tools like Firecrawl and Exa for advanced web scraping and searching, falling back to WebFetch when necessary.

Does this skill work in non-interactive mode?

Yes, while the main process seeks initial user confirmation, the research sub-tasks run in non-interactive mode (`claude -p`) to ensure speed and efficiency.

How are the final research results delivered?

The skill produces a standalone, structured Markdown report saved within a dedicated `.research/` directory in your project, ensuring your chat remains clean.

Can I track the progress of the agents?

Yes, the skill maintains detailed logs in the `.research/` folder, allowing you to monitor dispatchers and individual sub-process logs in real-time.

Deep Research Workflow

Name: Deep Research Workflow
Author: feiskyer

byfeiskyer

•

1,158

Web Scraping y Recopilación de Datos

Orchestrates multi-agent parallel workflows to perform comprehensive web research, competitive analysis, and data synthesis into structured reports.

Acerca de

This skill transforms Claude Code into a high-performance research engine by decomposing complex queries into parallelizable sub-tasks. It manages the entire lifecycle of a research project—from goal clarification and automated tool orchestration (utilizing Firecrawl, Exa, and WebFetch) to programmatic data aggregation and multi-stage report polishing. By leveraging non-interactive sub-processes, it handles large-scale information gathering and synthesis, delivering a final, insight-driven Markdown document instead of a simple chat summary, ensuring all evidence is traceable and structured.

Características Principales

1,158 GitHub stars
Programmatic result aggregation and iterative multi-stage refinement for professional reports
Automated sub-goal decomposition and task scheduling with real-time progress logging
Isolated project workspace management under .research/ directory for full data traceability
Multi-agent parallel orchestration using non-interactive sub-processes for high-throughput research
Advanced web scraping prioritization using Firecrawl, Exa MCP tools, and native search skills

Casos de Uso

Comprehensive market research and competitive landscape analysis with cited evidence
Deep technical audits and documentation synthesis for complex software systems
Large-scale information retrieval and shard-based data extraction from web sources

Acerca de

Características Principales

1,158 GitHub stars
Programmatic result aggregation and iterative multi-stage refinement for professional reports
Automated sub-goal decomposition and task scheduling with real-time progress logging
Isolated project workspace management under .research/ directory for full data traceability
Multi-agent parallel orchestration using non-interactive sub-processes for high-throughput research
Advanced web scraping prioritization using Firecrawl, Exa MCP tools, and native search skills

Casos de Uso

Comprehensive market research and competitive landscape analysis with cited evidence
Deep technical audits and documentation synthesis for complex software systems
Large-scale information retrieval and shard-based data extraction from web sources