deep-research

Orchestrate iterative subagent research waves with auditable source verification.

1|1|Updated Jun 11, 2026
One-click install
npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill deep-research-valtterimelkko
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/valtterimelkko/agent-workflow-skills/tree/main/skills/deep-research
Command: npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill deep-research-valtterimelkko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the problem of shallow or unreliable AI research by providing a structured, iterative, and auditable workflow for complex, high-stakes topics that require broad source coverage and rigorous synthesis.

Core Features & Use Cases

  • Iterative Research Waves: Orchestrates scout and analyst subagents to ensure breadth and depth without overloading the system.
  • Blocked-Source Registry: Systematically tracks and evaluates inaccessible sources to determine if they materially weaken the research.
  • Use Case: Use this for due diligence, market analysis, or academic synthesis where missing a single dimension or failing to verify a claim could lead to significant errors in judgment.

Quick Start

Use the deep-research skill to conduct a comprehensive analysis on the current state and future regulatory landscape of AI alignment.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I conduct auditable research for high-stakes due diligence?

You can conduct publication-grade synthesis by orchestrating iterative waves of scout and analyst subagents. This multi-dimensional research workflow ensures broad source coverage, transparent verification, and contradiction resolution across 40+ sources for rigorous outputs.

What's the best way to synthesize 40+ sources for publication-grade analysis?

You can conduct publication-grade synthesis by orchestrating iterative waves of scout and analyst subagents. This multi-dimensional research workflow ensures broad source coverage, transparent verification, and contradiction resolution across 40+ sources for rigorous outputs.

How does iterative subagent research resolve contradictions in source material?

Iterative subagent research resolves contradictions by systematically evaluating multiple sources across successive waves. It tracks inaccessible sources in a blocked-source registry to determine if missing data materially weakens the final synthesis and flags explicit gaps.

Can I use this multi-dimensional research workflow for market analysis?

Yes, this multi-dimensional research workflow applies directly to market analysis. It provides the structured, iterative methodology needed to verify claims and ensure broad source coverage, preventing missed dimensions that could lead to significant errors.

How are blocked or inaccessible sources handled during synthesis?

Inaccessible sources are tracked in a blocked-source registry during synthesis. The system evaluates these missing sources to determine if their absence materially weakens the research conclusions, ensuring transparent gap analysis.