deep-research

Orchestrate iterative web searches, parallel synthesis, and dual-reviewer claim verification for cited reports.

1|Updated May 17, 2026

Search Tags:#fact-checking #research #parallel processing #iterative search #dual-reviewer

Ready to run

npx skills add https://github.com/djimit/djimitflo --skill deep-research-djimit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/djimit/djimitflo/tree/main/.opencode/skills/deep-research
Command: npx skills add https://github.com/djimit/djimitflo --skill deep-research-djimit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires search_api, external_tools, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for comprehensive, fact-checked research by orchestrating a protocol that includes iterative web searches, parallel synthesis, and dual-reviewer claim verification.

Core Features & Use Cases

Iterative Web Search: Perform targeted searches and gather evidence iteratively.
Parallel Synthesis: Dispatch parallel synthesis workers for evidence-grounded answers.
Dual-Reviewer Verification: Validate claims with two reviewers to ensure accuracy.
Use Case: When you need to conduct in-depth research on a complex topic, this Skill can help you gather and verify information efficiently.

Quick Start

Initiate a deep research session with the command: deep-research "What are the latest advancements in quantum computing?"

Frequently Asked Questions about deep-research

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

FAQPage Schema

How do I conduct fact-checked research with automated claim verification?▼

Conduct fact-checked research by orchestrating iterative web searches, parallel synthesis, and dual-reviewer claim verification over external sources. This protocol validates high-stakes claims through a critic challenge mechanism to ensure evidence-grounded accuracy.

What is dual-reviewer verification and how does it work for research?▼

Dual-reviewer verification validates research claims by using two independent reviewers to cross-check evidence gathered from iterative web searches. This mechanism challenges high-stakes claims to mitigate bias and ensure factual accuracy before generating a cited report.

Can I use external search APIs to gather evidence for complex topics?▼

Yes, you can use external search APIs to gather evidence iteratively. The research protocol dispatches parallel synthesis workers to process the retrieved external sources, grounding the final answers and cited report in verified evidence.

Do I need external research tools to perform parallel synthesis?▼

Yes, external research tools and search APIs are required dependencies. The parallel synthesis workers rely on these external tools to retrieve and process evidence iteratively, ensuring the dual-reviewer verification protocol has sufficient data to validate high-stakes claims.

What is the best way to generate a cited report after iterative web searches?▼

The best way to generate a cited report is through an orchestrated research protocol combining iterative web searches, parallel synthesis, and dual-reviewer verification. This approach cross-validates high-stakes claims through a critic challenge before producing the final cited document.

When should I not use a dual-reviewer research protocol?▼

Avoid using this dual-reviewer research protocol when external search APIs and research tools are unavailable, or when tasks do not require high-stakes claim verification. The iterative search and parallel synthesis overhead makes it unsuitable for simple, single-query lookups.