home / skills / sarfraznawaz2005 / agent-skills-collection / research

research skill

/research

This skill conducts deep topic research using Gemini CLI via a sub-agent, delivering thorough insights to inform decisions, writing, or learning.

npx playbooks add skill sarfraznawaz2005/agent-skills-collection --skill research

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.0 KB
---
name: research
description: Deep research via Gemini CLI — runs in background sub-agent.
---

# Research Skill

Conduct deep research on any topic using Gemini CLI via a spawned sub-agent.

## How It Works

**When user says "Research: [topic]" or asks for deep research:**

### Step 1: Clarifying Questions (Always)

Before running any research, ask 2-5 quick questions to focus the work:

**Start with the goal:**
> "Before I dive in - what's your goal here? Are you learning about this topic, making a decision, writing something, or just curious?"

**Then adapt based on their answer:**

If learning/curious:
- "Any specific aspect you're most interested in?"
- "How technical should I go? (High-level overview vs deep technical detail)"

If decision-making:
- "What decision are you trying to make?"
- "Any specific criteria or constraints I should focus on?"

If writing/creating:
- "What's the output? (Blog post, report, presentation?)"
- "Who's the audience?"

**Keep it natural — 2-5 questions max.** Don't interrogate.

### Step 2: Conduct Research Using Sub-Agents

Conduct research using sub-agent(s) (if available) using web search or any other relevant tools available at your disposal. 
Research must include:

1. Overview & Core Concepts - what is this, terminology, why it matters
2. Current State - latest developments, major players
3. Technical Deep Dive - how it works, mechanisms, key techniques
4. Practical Applications - real-world use cases, tools available
5. Challenges & Open Problems - technical, ethical, barriers
6. Future Outlook - trends, predictions, emerging areas
7. Resources - key papers, researchers, communities, courses

Save the output to: `C:\Users\Sarfraz\OneDrive\Documents\AI-Generated-Researches\<slug>\research.md`

Be thorough (aim for 500+ lines). Include specific examples and citations.

## Tips

- Research typically takes 3-10 minutes depending on complexity
- Check `C:\Users\Sarfraz\OneDrive\Documents\AI-Generated-Researches` for all past research

Overview

This skill performs deep, structured research by spawning a background sub-agent via the Gemini CLI. It focuses the work with brief clarifying questions, then runs multi-step investigations to produce thorough, evidence-backed research. The output emphasizes practical insights, technical detail, and curated resources.

How this skill works

On request, the skill first asks 2–5 concise clarifying questions to pin down the goal, audience, and scope. It then launches a Gemini CLI sub-agent to perform web search, literature review, and technical analysis across seven research sections. The sub-agent compiles findings, examples, and citations into a single research document and stores the result for later review.

When to use it

  • Preparing a deep-dive report or whitepaper on a technical topic
  • Making a data-driven decision that needs current industry context
  • Researching academic or developer resources and tools
  • Gathering background for writing blog posts, talks, or proposals
  • Exploring future trends and open problems in a field

Best practices

  • Answer the clarifying questions succinctly to focus research and save time
  • Specify desired depth (high-level vs deep technical) and audience to tailor the output
  • Provide constraints or decision criteria when research supports a choice
  • Ask for intermediate updates if the topic is broad or evolving
  • Review citations and verify links before using findings in critical work

Example use cases

  • Produce a 2,000-word technical brief on a new ML architecture with cited papers and code links
  • Compare vendor solutions and summarize trade-offs for a purchasing decision
  • Create lecture notes and recommended readings for an advanced course
  • Survey the latest developments and tools in a fast-moving research area
  • Compile reproducible examples, commands, and references for developer onboarding

FAQ

How long does a typical research run take?

Most topics finish in 3–10 minutes; complex or broad topics may take longer.

Can I control the level of technical detail?

Yes — the initial clarifying questions include depth and audience so the output matches your needs.

Will the research include citations and source links?

Yes — the skill collects citations, examples, and links so you can verify and follow up on findings.