The Gemini AI skill integrates Google's powerful Gemini Pro model into your workflow, leveraging its massive 1M token context window for high-fidelity research, synthesis, and complex reasoning. It serves as a versatile assistant for processing vast amounts of information, performing real-time web searches, and providing evidence-based analysis for data-intensive tasks.

When should I use gemini?

gemini is useful in the following scenarios: • Deep-Dive Web Research: Conduct comprehensive research on complex topics by synthesizing facts from multiple web sources while distinguishing between verified data and speculation. • Large-Scale Document Summarization: Utilize the 1M context window to summarize extensive reports, long-form articles, or entire books without losing critical context or nuance. • Technical Code Analysis: Analyze source code files to identify logic errors, perform security reviews, or generate architectural explanations through piped CLI commands. • Automated Fact-Checking: Verify claims and statements against real-time information to ensure accuracy in content creation, citing sources and noting context. • Structured Data Extraction: Transform unstructured text from documents or web pages into organized formats like JSON, tables, or lists for programmatic use or reporting.

name	gemini
description	Use Gemini AI for research, analysis, summarization, web search, and complex reasoning. Use when you need AI-powered research, code analysis, content summarization, or web search with synthesis.

Gemini AI Assistant

Leverage Google's Gemini Pro model with its 1M context window for research, analysis, and reasoning tasks.

Prerequisites

Install the Gemini CLI:

pip install google-generativeai

Set your API key:

export GEMINI_API_KEY=your_api_key

Get an API key at: https://makersuite.google.com/app/apikey

CLI Reference

Basic Usage

# Simple question
gemini -m pro "Your question here"

# With text output (no markdown)
gemini -m pro -o text "Your question"

# Disable extensions for programmatic use
gemini -m pro -o text -e "" "Your question"

# Pipe content as stdin
echo "content to analyze" | gemini -m pro -o text -e "" "Summarize this"
cat file.txt | gemini -m pro -o text -e "" "Analyze this code"

Common Operations

Research

Deep research with critical analysis:

gemini -m pro -o text -e "" "You are an expert research analyst. Research: [topic]. Provide specific facts, distinguish opinions from facts, note uncertainties, and give actionable insights."

Summarization

cat document.txt | gemini -m pro -o text -e "" "Summarize this content, focusing on: [focus area]"

Code Analysis

cat code.ts | gemini -m pro -o text -e "" "Analyze this code and answer: [question]"

Web Search with Synthesis

gemini -m pro -o text -e "" "Search and synthesize: [query]. Include specific facts, dates, and distinguish confirmed from speculative information."

Fact-Checking

gemini -m pro -o text -e "" "Fact-check this claim: [claim]. State true/false/partial, cite sources, note context."

Step-by-Step Reasoning

gemini -m pro -o text -e "" "Think through this problem step by step: [problem]. Constraints: [constraints]. Provide reasoning and conclusion."

Data Extraction

cat content.txt | gemini -m pro -o text -e "" "Extract [what to extract] from this content. Format as [json/list/table]."

News Lookup

gemini -m pro -o text -e "" "Latest news about: [topic] from [timeframe]. Summarize important developments."

Prompt Templates

Research Prompt

You are an expert research analyst. Your goal is to provide genuinely useful, accurate research.

RESEARCH OBJECTIVE: [topic]

QUALITY STANDARDS:
- Be specific and concrete, not vague
- Distinguish between facts, expert opinions, and speculation
- Note when information is uncertain, contested, or evolving
- Identify what's NOT known or what gaps exist
- Provide actionable insights, not just information

Analysis Prompt

Analyze the following and provide:
1. Key findings
2. Implications
3. Recommendations
4. Uncertainties or gaps

Content: [content]

Best Practices

Use -o text -e "" for programmatic usage to get clean output
Pipe large content via stdin rather than command line args
Be specific in prompts - vague questions get vague answers
Ask for structure - request lists, tables, or JSON for parseable output
Request citations when accuracy matters
Set timeouts for long operations (gemini can take 30-120s)

Error Handling

Error	Solution
"command not found"	Install: `pip install google-generativeai`
"API key" / "unauthorized"	Set `GEMINI_API_KEY` environment variable
"rate limit" / "quota"	Wait and retry, or check quota at Google Cloud Console
Timeout	Break into smaller queries or increase timeout

gemini

When & Why to Use This Skill

Use Cases