dan:research

Orchestrate parallel dan-researcher agents and merge findings into a final synthesis.

Updated Mar 29, 2026
One-click install
npx skills add https://github.com/RavBogard/DAN --skill dan-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dan:research
Source: https://github.com/RavBogard/DAN/tree/main/.claude/skills/dan-research
Command: npx skills add https://github.com/RavBogard/DAN --skill dan-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates parallel dan-researcher agents to investigate a topic or phase and then merges their findings into a coherent final synthesis.

Core Features & Use Cases

  • Parallel Research in Waves: Spawns multiple researchers to cover diverse angles and produce scoped findings for each angle.
  • Synthesis and Output: Launches a dan-synthesizer to merge findings into a phase or project level RESEARCH.md, updating planning state.
  • State-driven Workflow: Maintains and evolves a research state with max 4 passes, promoting convergence checks and deterministic output paths.

Quick Start

Provide a topic or phase and run the dan:research skill to begin parallel researchers and generate a final synthesis.

Frequently Asked Questions about dan:research

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

FAQPage Schema
How do I automate parallel research and synthesize findings for a project phase?

To automate parallel research, this Skill spawns multiple researcher agents to investigate a topic and then uses a synthesizer to merge their findings into a final RESEARCH.md file, updating the planning state and checking for convergence.

What is the best way to coordinate multiagent research across multiple project phases?

Multiagent research is coordinated by orchestrating parallel dan-researcher agents to cover diverse angles, producing scoped findings for each dimension before a synthesizer merges them into a phase-level or project-level synthesis.

How does state-driven workflow work when planning research synthesis?

State-driven research workflow maintains and evolves a research state with a maximum of 4 passes, reading prior context from PROJECT.md and ROADMAP.md, recording gaps, and checking convergence via the CLI to ensure deterministic outputs.

Can I use this parallel research approach for both project-level and phase-level scopes?

Yes, you can target both project-level and phase-level scopes. The Skill directs researchers to investigate the specified scope and merges their findings, producing per-dimension findings and a final synthesis in the planning directory.

What context do I need to provide before starting automated research synthesis?

Before starting automated research synthesis, you need to provide a topic or phase. The Skill reads prior context from PROJECT.md, ROADMAP.md, and STATE.md to initialize the research state and record any existing gaps.