What is Gemini Deep Research Agent?

The engine used to run autonomous, multi-step research tasks via the Gemini API to produce comprehensive, cited reports.

What outputs are available?

Default is a human-readable Markdown report; use --json for structured data; --raw for unprocessed API output.

How long does it take and what does it cost?

Each task takes 2-10 minutes and costs $2-5, depending on complexity.

deep-research

Scanned

npx machina-cli add skill w95/awesome-claude-corporate-skills/deep-research --openclaw

Files (1)

SKILL.md

2.7 KB

Gemini Deep Research Skill

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Requirements

Python 3.8+
httpx: pip install -r requirements.txt
GEMINI_API_KEY environment variable

Setup

Get a Gemini API key from Google AI Studio
Set the environment variable:
```
export GEMINI_API_KEY=your-api-key-here
```
Or create a .env file in the skill directory.

Usage

Start a research task

python3 scripts/research.py --query "Research the history of Kubernetes"

With structured output format

python3 scripts/research.py --query "Compare Python web frameworks" \
  --format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"

Stream progress in real-time

python3 scripts/research.py --query "Analyze EV battery market" --stream

Start without waiting

python3 scripts/research.py --query "Research topic" --no-wait

Check status of running research

python3 scripts/research.py --status <interaction_id>

Wait for completion

python3 scripts/research.py --wait <interaction_id>

Continue from previous research

python3 scripts/research.py --query "Elaborate on point 2" --continue <interaction_id>

List recent research

python3 scripts/research.py --list

Output Formats

Default: Human-readable markdown report
JSON (--json): Structured data for programmatic use
Raw (--raw): Unprocessed API response

Cost & Time

Metric	Value
Time	2-10 minutes per task
Cost	$2-5 per task (varies by complexity)
Token usage	~250k-900k input, ~60k-80k output

Best Use Cases

Market analysis and competitive landscaping
Technical literature reviews
Due diligence research
Historical research and timelines
Comparative analysis (frameworks, products, technologies)

Workflow

User requests research → Run --query "..."
Inform user of estimated time (2-10 minutes)
Monitor with --stream or poll with --status
Return formatted results
Use --continue for follow-up questions

Exit Codes

0: Success
1: Error (API error, config issue, timeout)
130: Cancelled by user (Ctrl+C)

Source

git clone https://github.com/w95/awesome-claude-corporate-skills/blob/main/01-executive-leadership/deep-research/SKILL.md

View on GitHub

Overview

Gemini Deep Research Skill runs autonomous, multi-step research tasks to build comprehensive reports. It targets market analysis, competitive landscaping, literature reviews, technical research, and due diligence. Reports are detailed, cited, and produced in roughly 2-10 minutes, at a cost of $2-5 per task.

How This Skill Works

The skill plans, searches, reads, and synthesizes data via the Gemini Deep Research API to produce a comprehensive report. By default it outputs human-readable markdown; with --json it provides structured data for programmatic use, and you can monitor progress with --stream or resume via --continue or --wait.

When to Use It

Market analysis and competitive landscaping
Technical literature reviews
Due diligence research
Historical research and timelines
Comparative analysis of frameworks, products, or technologies

Quick Start

Step 1: Set GEMINI_API_KEY in your environment
Step 2: Run a task: python3 scripts/research.py --query Research the history of Kubernetes
Step 3: Retrieve results with --wait <interaction_id> or --json for structured output

Best Practices

Start with a clearly scoped query to limit task scope and time
Use the --json option for programmatic integrations
Expect 2-10 minutes per task and plan for cited, sourced outputs
Verify sources and cross-check key findings within the report
Monitor progress with --stream or --status and use --continue for follow-ups

Example Use Cases

Analyze the global EV battery market and major suppliers
Compare Django, Flask, and FastAPI for project needs
Research the history and milestones of Kubernetes
Due diligence on a SaaS vendor's security posture
Literature review of transformers in NLP (2020-2024)

Frequently Asked Questions

Add this skill to your agents