Deep Research Gemini

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, techni...

Security Scan

The SKILL.md describes a Python-based Gemini research tool that needs a GEMINI_API_KEY and scripts, but the packaged skill contains no scripts, no requirements file, and the registry metadata does not declare the required env var — the pieces don't add up.

Purpose & Capability

The skill's name/description say it runs Google Gemini-based autonomous research and the SKILL.md requires Python, httpx, and a GEMINI_API_KEY. However, the published package contains only SKILL.md and skill.json (no scripts, no requirements.txt, no code). The registry metadata also lists no required env vars or credentials. Requiring a Gemini API key and local Python scripts is coherent for the claimed purpose, but those requirements are not reflected in the package metadata nor are the scripts included — this mismatch is a red flag.

Instruction Scope

Instructions direct the agent/user to run python3 scripts/research.py with many flags and to set GEMINI_API_KEY (or a .env file). The instructions themselves do not ask for unrelated system files or other credentials, but they assume the existence of local scripts and a requirements file that are not present in the bundle. That absence means the instructions are incomplete or the skill expects the user/agent to fetch external code (not described).

Install Mechanism

There is no install specification in the registry (instruction-only). SKILL.md tells users to run pip install -r requirements.txt, but no requirements.txt is included. Absence of an install spec lowers immediate risk, but the instructions imply installing packages from an unknown requirements file or external repo — this should be clarified before installation.

Credentials

SKILL.md requests a GEMINI_API_KEY environment variable (reasonable for a Gemini-integrating skill). However, the skill metadata declares no primary credential or required env vars, creating an inconsistency. The GEMINI_API_KEY is sensitive — the package should explicitly declare it and justify its use; the current omission is concerning.

Persistence & Privilege

The skill does not request persistent presence (always: false) and does not declare config paths or elevated privileges. It does not modify other skills or system-wide settings in the provided materials.

What to consider before installing

Do not install or run this skill as-is. Before using it: (1) Confirm that the repository/package actually includes the referenced scripts (scripts/research.py) and requirements.txt — the published bundle here does not. (2) Inspect the referenced scripts on the GitHub source for network endpoints, telemetry, or unexpected data exfiltration (look for arbitrary HTTP calls, external upload endpoints, or code that reads unrelated files). (3) Verify why the registry metadata omitted GEMINI_API_KEY and whether the skill author expects you to clone external code; if so, review that code thoroughly. (4) Keep your GEMINI_API_KEY secret — do not paste it into untrusted UIs or public repos; prefer injecting it into a controlled runtime environment. (5) If you need this capability, ask the maintainer to publish the complete package (including scripts and requirements) and to declare required env vars in skill.json, or run the code in an isolated sandbox after manual inspection.

Gemini Deep Research Skill

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

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

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)