skills.rest
zzafergok
zzafergokCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

deep-research

Coordinate multi-agent staged research with graduated depth levels and structured reports.

1|1|Updated Mar 22, 2026
Search Tags:#research#troubleshooting#multi-agent#vcv rack#deep-research#level-based
One-click install
npx skills add https://github.com/zzafergok/skills --skill deep-research-zzafergok
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/zzafergok/skills/tree/main/01-ai-intelligence/deep-research
Command: npx skills add https://github.com/zzafergok/skills --skill deep-research-zzafergok

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates a multi-agent, graduated-depth research workflow to tackle complex technical problems that exceed quick local lookups.

Core Features & Use Cases

  • Graduated-depth research workflow: Level 1 quick check, Level 2 moderate investigation, Level 3 deep parallel exploration.
  • Parallel subagent orchestration: Spawn 2-3 focused subagents to explore different angles simultaneously.
  • Structured output and decision gates: Returns a formatted research report with recommendations and escalation options.
  • Safe handoff to implementation: Clear separation between research and execution, with a built-in handoff protocol.
  • Use cases: Debugging hard integration issues, architecture questions, and exotic DSP problems in modular contexts.

Quick Start

Provide a Level 1 quick-check plan for a given problem and outline escalation to Level 2 if confidence is insufficient.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I debug complex technical problems that need deep research beyond a quick lookup?▼

Complex technical research requires a multi-agent approach with graduated depth, starting with local documentation checks and escalating to parallel subagent exploration of SDKs, docs, and community sources to return structured recommendations.

What is the best way to investigate difficult DSP or system design issues using multiple agents?▼

Multi-agent investigation solves difficult DSP and system design issues by spawning focused parallel subagents to explore different angles simultaneously, returning a formatted research report with clear escalation options.

Can I use parallel subagents to research integration problems across external documentation?▼

Parallel subagents research integration problems by orchestrating focused agents to investigate external documentation and community sources simultaneously, graduating from quick local checks to extended thinking deep-dives.

When do I need to escalate technical troubleshooting to a Level 3 deep parallel exploration?▼

Level 3 deep parallel exploration is needed when confidence from Level 1 local docs and Level 2 broader documentation is insufficient for complex technical troubleshooting, triggering extended thinking subagents.

Does the research workflow separate investigation from implementation handoff?▼

The research workflow separates investigation from implementation using a safe handoff protocol, ensuring structured reports with recommendations are finalized before any execution begins.

How to structure a graduated-depth investigation for exotic modular system problems?▼

Graduated-depth investigation structures exotic modular system problems through staged workflows: Level 1 quick local checks, Level 2 broader external sources, and Level 3 parallel subagent research yielding a structured report.

Related Skills

Explore More Education & Research Skills→
fyrsmithlabsfyrsmithlabs

research:orchestration

Coordinate parallel research agents and synthesize findings into a consolidated report.

Official
Advanced
henrique-simoeshenrique-simoes
13

heuristic-evaluation

Evaluate UI designs against Nielsen's 10 heuristics with severity scoring.

Community
Intermediate
Jamie-CuiJamie-Cui
28

research-explore

Decompose research questions, delegate sub-tasks to an explore agent, and synthesize findings into a structured report.

Community
Advanced
glittercowboyglittercowboy
206

deep-research

Investigate complex JUCE plugin development problems with graduated research and parallel subagents.

Community
Basic