ahel
Start free

Gemini Deep Research Skill

SkillSearch

deep-research is a skill that lets an AI agent run autonomous research tasks. The agent plans what to investigate, searches for sources, reads them, and synthesizes the findings into comprehensive reports. It suits anyone who wants an agent to handle multi-step research work end to end.

Available today. Use it from your connected AI after setup.

Have an AI agent that supports loading skills.

Then ask your AI: use the Gemini Deep Research Skill skill

What your AI can do with it

  • Plan an autonomous research task before gathering information
  • Search for sources relevant to the research question
  • Read and evaluate the sources it finds
  • Synthesize findings into comprehensive reports
  • Run the full research workflow without step-by-step prompting

Getting started

  1. Have an AI agent that supports loading skills.
  2. Add the deep-research skill to the agent's available skills.
  3. Ask the agent to research a topic and let it plan, search, read, and synthesize a report.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/ai-research/deep-research/SKILL.md and read by ahel’s review.

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

When to Use This Skill

Use this skill when:

  • Performing market analysis
  • Conducting competitive landscaping
  • Creating literature reviews
  • Doing technical research
  • Performing due diligence
  • Need detailed, cited research reports

Requirements

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

Setup

  1. Get a Gemini API key from Google AI Studio
  2. 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

MetricValue
Time2-10 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

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

Exit Codes

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

Signals

GitHub stars
32k
Forks
4k
Last commit
Sep 2026
Hacker News mentions
1

ahel review

  • K1binfo
    installs-packages

Automated review, not a security audit. Ruleset v1+k2.

Questions

What is the deep research skill?
It is a skill that lets an AI agent run autonomous research tasks: the agent plans the work, searches for sources, reads them, and synthesizes the results into comprehensive reports.
How does the agent decide what to research?
The skill has the agent plan the research task first, then search and read sources based on that plan before writing the report.
What does the output look like?
The skill produces comprehensive reports that synthesize the information gathered during the research process.
Advanced
Item type
skill
Key
deep-research-davila7
Source
github.com/davila7/claude-code-templates

github.com/davila7/claude-code-templates

More in Search

dashboard
Skill · nexu-ioazure-ai
Skill · microsoftknowledge-ops
Skill · affaan-mnanoclaw-repl
Skill · affaan-mvideodb
Skill · affaan-mflags
Skill · vercel