deep-research

Generates cited, multi-source research reports using a filesystem-backed, resumable workflow.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/MuhammadUA/Axe --skill deep-research-muhammadua
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/MuhammadUA/Axe/tree/main/.kortix/opencode/skills/GENERAL-KNOWLEDGE-WORKER/deep-research
Command: npx skills add https://github.com/MuhammadUA/Axe --skill deep-research-muhammadua

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the burden of disorganized, uncited research by providing a systematic, evidence-based workflow to produce thorough, source-backed reports on any topic, saving hours of manual effort and ensuring scientific rigor.

Core Features & Use Cases

  • Systematic Multi-Source Investigation: Decomposes research questions into sub-queries, searches academic databases, government sources, and peer-reviewed literature, and cross-references findings for accuracy.
  • Context-Efficient Workflow: Uses the filesystem as working memory to store scraped content and notes, keeping the LLM context lean and making research resumable and searchable.
  • Use Case: If you need a literature review on the efficacy of mindfulness-based stress reduction, this Skill will compile all relevant studies, extract key findings, resolve conflicting evidence, and generate a fully cited report with confidence levels for each claim.

Quick Start

Use the deep-research skill to generate a cited report on the current state of quantum computing error correction research.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I generate a cited literature review without exceeding the LLM context window?▼

To generate a cited literature review without exceeding the LLM context window, this Skill uses a filesystem-backed workflow that stores scraped content and extracted notes to disk, keeping the context lean and research resumable.

What is the best way to fact-check and cross-reference multiple academic sources?▼

The best way to fact-check academic sources is a systematic workflow that decomposes research questions into sub-queries, cross-references findings from multiple databases, and resolves conflicting evidence to generate fully cited reports with confidence levels.

Can I resume an evidence synthesis task if my research session is interrupted?▼

Yes, you can resume evidence synthesis tasks because the workflow operates using the filesystem as working memory, storing scraped content, notes, and source metadata to disk for searchable and context-efficient research operations.

Does this multi-source research workflow require any specific external dependencies or components?▼

No specific external dependencies or components are required to use this multi-source research workflow, as it operates independently to decompose queries, extract notes, and compile evidence-based reports.

How does systematic investigative research handle conflicting evidence from peer-reviewed literature?▼

Systematic investigative research handles conflicting evidence by cross-referencing findings from peer-reviewed literature, resolving discrepancies during evidence synthesis, and assigning confidence levels to each claim in the final cited report.