claude-deep-research-skill

Enterprise-grade deep research capabilities, supporting an 8-stage pipeline, source credibility scoring, and automated verification.

Agent SkillResearchOpen source

View source →

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 1.0k
Source: skill-github
Repository: github.com/199-biotechnologies/claude-deep-research-skill

Overview

Claude Code's enterprise-grade deep research engine generates cited reports with source credibility scores, supports multi-provider search and automated validation. This skill is ideal for complex topic research and critical decision-making, offering multiple research modes (quick, standard, deep, ultra-deep) and automated verification with continuous improvement mechanisms. Suitable for users requiring high-quality, verified research reports.

Capabilities

▪8-stage research pipeline
▪Source credibility scoring
▪Multi-provider search
▪Automated verification
▪Multiple research modes
▪Continuous improvement mechanism

Use cases

In-depth research on complex topicsSupport for critical decision-makingGeneration of high-quality research reportsVerification of information from multiple sources

Setup

Requires: API Key

git clone https://github.com/199-biotechnologies/claude-deep-research-skill.git ~/.claude/skills/deep-research

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to configure multi-provider search?

Install search-cli and configure at least one provider's API Key.

What research modes are available?

Four modes: quick, standard, deep, and ultra-deep.

Where are the reports saved?

Reports are saved in the ~/Documents/[Topic]_Research_[Date]/ directory.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP