skills.rest
shakestzd
shakestzdCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini

Explore large codebases and analyze multimodal data with Google Gemini models.

3|3|Updated Dec 16, 2025
Search Tags:#code analysis#research#multimodal#exploration#gemini#large context
One-click install
npx skills add https://github.com/shakestzd/htmlgraph --skill gemini-shakestzd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/shakestzd/htmlgraph/tree/main/packages/claude-plugin/skills/gemini
Command: npx skills add https://github.com/shakestzd/htmlgraph --skill gemini-shakestzd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a robust way to leverage Google Gemini for large-context exploration, research, and multimodal tasks, with integrated event tracking for observability.

Core Features & Use Cases

  • Large Context Exploration: Analyze extensive codebases or documents with Gemini's 2M token context window.
  • Multimodal Processing: Extract information from images, PDFs, and other document types.
  • Event Tracking: All Gemini invocations are tracked within the HtmlGraph event hierarchy for detailed observability.
  • Use Case: Use this Skill to analyze a large codebase for security vulnerabilities, documenting the findings and Gemini's reasoning process within HtmlGraph.

Quick Start

Use the gemini skill to analyze authentication patterns in the codebase.

Frequently Asked Questions about gemini

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze a large codebase for security vulnerabilities using Gemini?▼

You can analyze large codebases for vulnerabilities by leveraging this Skill to process extensive code with Gemini's 2M token context window. It documents findings and reasoning within HtmlGraph for detailed observability.

Can I extract information from images and PDFs using large context models?▼

Yes, you can extract information from images and PDFs using multimodal processing. This Skill leverages Google Gemini models to perform multimodal data analysis on images, PDFs, and other document types.

What is the best way to track Gemini invocations during code exploration?▼

The best way to track Gemini invocations during code exploration is using HtmlGraph. This Skill integrates with HtmlGraph for full event tracking and observability of all subprocess invocations.

Does this Gemini Skill work with Claude's Explore agent?▼

Yes, the Gemini Skill works with Claude's Explore agent. It supports direct CLI invocation or can fallback to Claude's Explore agent for large-context code exploration and research tasks.

How do I explore authentication patterns in a codebase with Gemini?▼

To explore authentication patterns in a codebase with Gemini, use this Skill to analyze extensive code. It leverages Gemini 3 preview for large-context exploration and tracks the process within HtmlGraph.

Related Skills

Explore More Software Engineering Skills→
dige04dige04

ai-tools

Orchestrate Gemini and NotebookLM capabilities within Claude Code for multimodal tasks.

Community
Advanced
Shakes-tzdShakes-tzd
3

codex-skill

Track HtmlGraph sessions across Claude Code, Codex, and Gemini via git hooks.

Community
Advanced
Shakes-tzdShakes-tzd
3

codex

Generate code via Codex CLI with HtmlGraph event tracking and Claude fallback.

Community
Advanced
zzafergokzzafergok
1

gemini-skill

Access Google Gemini models via CLI or API for reasoning and multimodal tasks.

Community
Advanced