Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
sanjay3290 avatar

Deep Research

  • 471 installs
  • 364 repo stars
  • Updated July 9, 2026
  • sanjay3290/ai-skills

deep-research is a coding-agent skill that runs autonomous multi-step research through the Google Gemini Deep Research Agent for developers who need cited market, technical, or literature reports in minutes.

About

deep-research is a sanjay3290/ai-skills agent skill (metadata version 1.0, Apache-2.0) that executes autonomous research via the Google Gemini Deep Research Agent. The workflow plans queries, searches sources, reads results, and synthesizes findings into detailed cited reports suitable for market analysis, competitive landscaping, literature reviews, technical research, and due diligence. Runs typically complete in two to ten minutes at an estimated two to five dollars per task depending on scope. Output formats include human-readable Markdown reports, structured JSON for programmatic use, and raw API responses when requested. Install with `npx skills add sanjay3290/ai-skills --skill deep-research` and configure GEMINI_API_KEY in the environment. Developers reach for deep-research when a coding agent must produce sourced long-form research rather than a single search snippet, especially before architecture, vendor selection, or product decisions that require citations.

  • deep-research

Deep Research by the numbers

  • 471 all-time installs (skills.sh)
  • +9 installs in the week ending Jul 26, 2026 (Skillselion tracking)
  • Ranked #866 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/sanjay3290/ai-skills --skill deep-research

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs471
repo stars364
Last updatedJuly 9, 2026
Repositorysanjay3290/ai-skills

How do you run autonomous cited research reports?

Use deep-research for development tasks

Who is it for?

Developers and tech leads needing multi-source cited research on markets, competitors, or papers before committing to an implementation plan.

Skip if: Quick factual lookups answerable in one search, or environments without a configured GEMINI_API_KEY and API budget.

When should I use this skill?

User requests deep research, market analysis, competitive landscaping, literature review, technical research, or due diligence with cited reports.

What you get

Cited Markdown research report, optional JSON export, and saved interaction history from Gemini Deep Research runs.

  • Cited Markdown research report
  • Optional JSON structured export

By the numbers

  • Typical research runtime of 2-10 minutes per task
  • Estimated cost of $2-5 per deep-research task
  • Skill metadata version 1.0 under Apache-2.0 license

Files

SKILL.mdMarkdownGitHub ↗

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

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)

Related skills

Forks & variants (1)

Deep Research has 1 known copy in the catalog totaling 26 installs. They canonicalize to this original listing.

How it compares

Pick deep-research for multi-step cited reports; use lightweight web search skills when a single answer snippet is enough.

FAQ

How long does deep-research take to finish?

deep-research typically completes in two to ten minutes depending on query breadth. The skill uses the Google Gemini Deep Research Agent to plan, search, read, and synthesize sources into a detailed cited report rather than returning instant snippets.

What output formats does deep-research support?

deep-research can return human-readable Markdown reports, structured JSON for programmatic pipelines, or raw API responses. Developers choose the format based on whether stakeholders need readable briefs or downstream automation.

How do you configure deep-research?

Install deep-research with `npx skills add sanjay3290/ai-skills --skill deep-research` and export a valid GEMINI_API_KEY. The skill metadata lists version 1.0 under Apache-2.0 and targets market, technical, and literature research tasks.

Backend & APIsbackendintegrations

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.