Agent skill

Gemini CLI

by majiayu000 in majiayu000/claude-skill-registry

Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution.

MITAuto-check: notesAI & LLM Engineering

Install Gemini CLI

skills CLI
$ npx skills add majiayu000/claude-skill-registry --skill gemini-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install majiayu000/claude-skill-registry gemini-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-llm/gemini-cli-adaptationio-skrillz .claude/skills/gemini-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gemini-cli
GitHub stars
666
Used in
1 other repo
Token cost
~4.1k tokens
SKILL.md length
455 words
Files
2
Skills in repo
971
Repo updated
First seen
Licence
MIT

At a glance

Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution.

  • Works in 3 steps: Install Gemini CLI → Setup Authentication → Basic Usage
  • Working with Gemini AI
  • SKILL.md covers When to Use, Quick Start, YOLO Mode - Use with Caution and Claude + Gemini Collaboration…, plus 2 more sections
  • Calls gemini, npm and jq; reaches aistudio.google.com and github.com; needs GEMINI_API_KEY and GOOGLE_APPLICATION_CREDENTIALS

What it does

Gemini CLI is an agent skill from majiayu000/claude-skill-registry. Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution. Use when working with Gemini AI, Google AI, multimodal tasks, or needing advanced AI capabilities.

Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).

It sits in AI & LLM Engineering, covering Computer vision. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.

When your agent uses it

  • Working with Gemini AI
  • Multimodal tasks
  • Needing advanced AI capabilities

Example prompts

  • “/gemini-cli”

Requirements

  • Python 3
  • Node.js
  • A credential in GEMINI_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Install Gemini CLI
  2. Setup Authentication
  3. Basic Usage

What it can do on your machine

Read from SKILL.md and the folder at commit 000116a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gemini
    • npm
    • jq
    • node
    • npx
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • aistudio.google.com
    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY
    • GOOGLE_APPLICATION_CREDENTIALS

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini CLI loads about 4.1k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 455 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:49
    # Or create ~/.gemini/.env file
  • NoteMentions a .env fileSKILL.md:50
    API_KEY="your-api-key-here"' > ~/.gemini/.env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/claude-skill-registry at commit 000116a, republished under its MIT licence (© majiayu000). 455 words, ~4,143 tokens.

Download SKILL.mdSave it as .claude/skills/gemini-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
gemini-cli
description
Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution. Use when working with Gemini AI, Google AI, multimodal tasks, or needing advanced AI capabilities.

Gemini CLI Integration

Integrates Google's Gemini CLI into Claude Code, enabling seamless AI collaboration between Claude and Gemini for enhanced capabilities.

When to Use

  • Working with Google AI/Gemini models
  • Need multimodal capabilities (text + images)
  • Complex reasoning with ReAct architecture
  • Web search and fetching capabilities
  • MCP server integration
  • Code analysis and generation with Gemini
  • Comparing AI model outputs

Quick Start

1. Install Gemini CLI
bash
# Check Node.js version (requires 18+, recommend 20+)
node --version

# Install globally via NPM
npm install -g @google/gemini-cli

# Or use without installation
npx @google/gemini-cli
2. Setup Authentication
bash
# Start Gemini and follow OAuth flow
gemini
# Will open browser for Google authentication
Option B: API Key
bash
# Get key from https://aistudio.google.com/
export GEMINI_API_KEY="your-api-key-here"

# Or create ~/.gemini/.env file
echo 'GEMINI_API_KEY="your-api-key-here"' > ~/.gemini/.env
3. Basic Usage
bash
# Quick prompt (manual approval required)
gemini -p "Explain this code: $(cat main.py)"

# YOLO mode (auto-approve all actions - RECOMMENDED for automation)
gemini --yolo -p "Analyze and optimize this codebase"

# Interactive session
gemini -i "Let's analyze my project"

# Include specific directories with YOLO
gemini --include-directories ./src,./tests --yolo -p "Review and improve this codebase"

# Use specific model with auto-execution
gemini -m gemini-2.5-flash --yolo -p "Generate tests for all functions"

YOLO Mode - Use with Caution

--yolo automatically approves all actions. USE SPARINGLY - it's powerful but risky.

✅ Safe YOLO Operations
bash
# Read-only analysis (safe)
gemini --yolo -p "Analyze code quality in @./src and generate report"

# Documentation generation (low risk)
gemini --yolo -p "Add JSDoc comments to all functions in ./src"

# Small, atomic operations (verifiable)
gemini --yolo -p "Fix ESLint errors in @./utils.js"

# Idempotent operations (safe to retry)
gemini --yolo -p "Format all JavaScript files with Prettier"
⚠️ Use YOLO with Safeguards
bash
# Always create backups first
git stash push -m "pre-yolo-backup"
gemini --yolo -p "Refactor authentication module"

# Use checkpointing for rollback
gemini --checkpointing --yolo -p "Major code modernization"

# Combine with dry-run preview
gemini --dry-run -p "Database migration"  # Review first
gemini --yolo -p "Execute reviewed migration"  # Then automate
❌ NEVER Use YOLO For
  • Complex, multi-step workflows - Break into sequential steps instead
  • Production system modifications - Always manual review
  • Database operations - Require human verification
  • Security configurations - Too critical for automation
  • File deletions - Risk of data loss
  • Unknown/untested operations - Test manually first
Better Alternative: Iterative Workflows

Instead of large YOLO tasks, use Claude-orchestrated loops:

bash
# ❌ RISKY: One giant YOLO task
gemini --yolo -p "Complete Express.js to Fastify migration"

# ✅ SAFE: Claude-guided sequential steps
gemini -p "Step 1: Analyze Express dependencies"  # Review
gemini --yolo -p "Step 2: Install Fastify packages"  # Safe
gemini -p "Step 3: Convert first route"  # Review
gemini --yolo -p "Step 4: Run tests"  # Safe
# Continue iteratively...

Claude + Gemini Collaboration Patterns

AI-to-AI Integration: Claude and Gemini work best together with structured, iterative workflows.

The Think-Act-Observe Loop

Claude orchestrates, Gemini executes - the most powerful pattern for AI collaboration:

bash
# 1. Claude THINKS: Analyze the goal
# "I need to refactor the auth module. First, understand the structure."

# 2. Claude directs Gemini to ACT:
gemini -p "List all functions and their signatures in @./src/auth.js" > auth_analysis.txt

# 3. Claude OBSERVES the results
cat auth_analysis.txt
# Claude reviews and decides next step

# 4. Claude directs specific, atomic action:
gemini --yolo -p "Add try-catch error handling to the 'login' function in @./src/auth.js"

# 5. Claude verifies:
gemini --yolo -p "Run tests in tests/auth.test.js and report results"

# 6. Claude iterates based on test results
Structured Output for AI Parsing

Use --output-format json for machine-readable results:

bash
# Get structured data Claude can parse
gemini --output-format json -p "List all Python files in ./src" > files.json

# Claude can now reliably process the JSON
cat files.json | jq '.files[]'

# Structured analysis
gemini --output-format json -p "Analyze security issues in @./src/auth.js" > security_report.json

# Claude parses specific fields
jq '.vulnerabilities[] | .severity' security_report.json
Safe Automation with Dry-Run

Preview operations before execution:

bash
# Claude previews the plan first
gemini --dry-run -p "Refactor the authentication system"
# Output shows planned tool calls without executing

# After Claude reviews and approves:
gemini --yolo -p "Execute the reviewed refactoring plan"
Sequential Task Decomposition

Break complex tasks into atomic, verifiable steps:

bash
#!/bin/bash
# Claude-orchestrated workflow

# BAD: Too complex, unpredictable
# gemini --yolo -p "Create a complete Express.js API with authentication"

# GOOD: Sequential, verifiable steps
echo "Step 1: Initialize project"
gemini --yolo -p "Initialize Node.js project and create server.js"

echo "Step 2: Install dependencies"
gemini --yolo -p "Install express, cors, and body-parser"

echo "Step 3: Basic server"
gemini --yolo -p "Create basic Express server in server.js with hello world route"

echo "Step 4: Add authentication (review this step)"
gemini -p "Add JWT authentication middleware to server.js"
# Claude reviews before proceeding

echo "Step 5: Verify"
gemini --yolo -p "Run tests and report results"
Tool Discovery and Schema

Claude learns available tools:

bash
# Discover what tools Gemini has
gemini tools list

# Get detailed tool schema
gemini tools describe fileSystem
gemini tools describe shell
gemini tools describe google_web_search

# Claude can then construct precise tool calls
Error Handling Patterns

Robust automation with proper error handling:

bash
#!/bin/bash
set -e  # Exit on error

# Claude-managed error recovery
if ! gemini --yolo -p "Run test suite"; then
  echo "Tests failed. Analyzing..."
  gemini -p "Analyze test failures and suggest fixes" > fixes.txt
  cat fixes.txt
  # Claude decides whether to apply fixes
fi
Context Management

Efficient context for large projects:

bash
# Let Claude select relevant context
gemini --include-directories ./src/auth,./tests/auth \
       -p "Focus only on authentication module"

# Use @ syntax for precise file references
gemini -p "Compare @./src/auth-old.js with @./src/auth-new.js"

# Web context
gemini -p "Compare my implementation @./src/api.js with @https://example.com/best-practices"
Checkpoint and Restore

Safe experimentation with rollback:

bash
# Claude creates checkpoint before risky operations
gemini --checkpointing --yolo -p "Major refactoring of core module"

# If something goes wrong:
gemini checkpoint list
gemini checkpoint restore <checkpoint-id>

Core Workflows

Code Analysis Workflow
bash
# Analyze entire project (auto-execute)
gemini --include-directories . \
       --exclude-directories node_modules,.git \
       --yolo -p "Analyze this codebase and suggest improvements"

# Code review with auto-fixes
gemini --yolo -p "Review and fix security issues: @./src/auth.js"

# Generate tests automatically
gemini --yolo -p "Generate comprehensive tests for: @./src/utils.js"

# Manual review (when unsure)
gemini -p "Explain the architecture of this complex module: @./src/core.js"
Documentation Generation
bash
# Generate README (auto-create files)
gemini --include-directories . --yolo -p "Generate a comprehensive README.md for this project"

# API documentation (auto-generate)
gemini --yolo -p "Generate complete API documentation for: @./src/api/"

# Code comments (bulk operation)
gemini --yolo -p "Add detailed JSDoc comments to all functions in: @./src/"

# Manual review for complex docs
gemini -p "Explain the documentation strategy for: @./complex_algorithm.py"
Multimodal Analysis
bash
# Analyze images (read-only, safe for YOLO)
gemini --yolo -p "Describe this architecture diagram: @./docs/architecture.png"

# Compare designs (analysis only)
gemini --yolo -p "Compare these UI designs and suggest improvements: @./design1.png @./design2.png"

# Extract and format text
gemini --yolo -p "Extract and format the text from: @./screenshot.png"
Web Research
bash
# Research with web search (auto-execute)
gemini --yolo -p "Research best practices for React performance optimization and create summary"

# Fetch and analyze (read-only)
gemini --yolo -p "Analyze this documentation: @https://docs.example.com/api"

# Compare implementations (analysis)
gemini --yolo -p "Compare my implementation with: @https://github.com/example/repo and suggest improvements"

Advanced Features

Interactive Commands
bash
# In interactive mode:
/help              # Show all commands
/tools             # List available tools
/mcp               # Show MCP servers
/compress          # Summarize conversation
/copy              # Copy last response
/clear             # Clear context
/checkpoint        # Save project state
/restore           # Restore checkpoint
/ide install       # Setup VS Code
/ide enable        # Connect to VS Code
Tool Execution
bash
# Auto-approve tool calls (careful!)
gemini --yolo -p "Create a Python script that processes all CSV files"

# Sandbox mode (safer)
gemini --sandbox -p "Set up a new React project"

# Manual approval (default)
gemini -p "Organize my project files"
MCP Server Integration
bash
# List MCP servers
gemini mcp list

# Add MCP server
gemini mcp add

# Remove MCP server
gemini mcp remove <name>

# Use with MCP tools
gemini -p "Use the database MCP server to query user data"
Checkpointing
bash
# Enable checkpointing
gemini --checkpointing -p "Refactor this entire module"

# List checkpoints
gemini checkpoint list

# Restore checkpoint
gemini checkpoint restore <id>

Configuration

Settings File (~/.gemini/settings.json)
json
{
  "model": "gemini-2.5-pro",
  "defaultFlags": {
    "checkpointing": true,
    "includeDirectories": ["./src", "./tests"],
    "excludeDirectories": ["node_modules", ".git", "dist"]
  },
  "tools": {
    "shell": {
      "enabled": false,
      "requireConfirmation": true
    },
    "fileSystem": {
      "enabled": true,
      "allowedPaths": ["./"]
    },
    "web": {
      "enabled": true,
      "allowedDomains": ["github.com", "docs.google.com"]
    }
  }
}
Environment Variables
bash
# Authentication
export GEMINI_API_KEY="your-key"

# Vertex AI (Enterprise)
export GOOGLE_CLOUD_PROJECT="your-project"
export GOOGLE_CLOUD_LOCATION="us-central1"
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"

# Model selection
export GEMINI_MODEL="gemini-2.5-pro"

# Default directories
export GEMINI_INCLUDE_DIRS="./src,./lib"
export GEMINI_EXCLUDE_DIRS="node_modules,.git"

Integration Patterns

Claude + Gemini Collaboration
bash
# Use Claude for planning, Gemini for execution
echo "Claude, create a plan for refactoring auth module"
# ... get plan from Claude ...

gemini -p "Execute this refactoring plan: [paste plan]"
Parallel Analysis
bash
# Get different perspectives
echo "Analyze security of auth.js" | tee \
  >(claude-cli) \
  >(gemini -p -)
Model Comparison
bash
# Compare outputs
PROMPT="Generate unit tests for utils.js"
echo "Claude:" && claude-cli "$PROMPT"
echo "Gemini:" && gemini -p "$PROMPT"

Best Practices

Security
  1. API Key Management

    • Never commit API keys
    • Use environment variables
    • Rotate keys regularly
  2. Tool Execution

    • Avoid --yolo for untrusted prompts
    • Use --sandbox for experiments
    • Review tool calls before approval
  3. MCP Server Trust

    • Only trust known servers
    • Use include/exclude tool lists
    • Set appropriate timeouts
Show full SKILL.md (208 more words)Show less
Performance
  1. Model Selection

    • Use gemini-2.5-flash for quick tasks
    • Use gemini-2.5-pro for complex reasoning
    • Consider token limits (1M context window)
  2. Directory Management

    • Exclude unnecessary directories
    • Use specific includes for large projects
    • Leverage checkpointing for long tasks
  3. Rate Limiting

    • OAuth: 60 req/min, 1000 req/day
    • API Key: Varies by tier
    • Implement retry logic
Workflow Optimization
  1. Batch Operations

    bash
    # Process multiple files efficiently
    gemini -p "Analyze and improve: @./src/*.js"
  2. Context Preservation

    bash
    # Use interactive mode for related tasks
    gemini -i "Let's refactor the auth system"
  3. Output Formatting

    bash
    # Get JSON output for parsing
    gemini --json -p "List all functions in: @./utils.js"

Troubleshooting

Common Issues
  1. Authentication Failed

    bash
    # Clear cached credentials
    rm -rf ~/.gemini/auth
    # Re-authenticate
    gemini
  2. Rate Limiting

    bash
    # Check usage
    gemini usage
    # Switch to different auth method if needed
  3. Tool Execution Errors

    bash
    # Check tool availability
    gemini -i
    /tools
    # Verify permissions
  4. MCP Server Issues

    bash
    # Check server status
    gemini mcp status
    # Restart server
    gemini mcp restart <name>

Examples

Complete Project Analysis (Automated)
bash
#!/bin/bash
# Comprehensive project analysis with auto-execution

gemini --include-directories . \
       --exclude-directories node_modules,.git,dist \
       --checkpointing --yolo \
       -p "Perform comprehensive analysis and create reports:
1. Code quality assessment with fixes
2. Security vulnerability scan and patches
3. Performance optimization suggestions
4. Generate missing tests
5. Create complete documentation
6. Update dependencies safely
7. Implement CI/CD pipeline"
Automated Documentation Suite
bash
#!/bin/bash
# Generate complete documentation suite (fully automated)

gemini --yolo -p "Generate complete documentation ecosystem:
1. README.md with badges and quick start
2. API.md with OpenAPI specification
3. CONTRIBUTING.md with dev workflow
4. CHANGELOG.md with version history
5. JSDoc comments for all functions
6. Architecture diagrams in Mermaid
7. Test documentation and coverage reports
8. Deployment and operations guide"
Framework Migration (Auto-Pilot)
bash
#!/bin/bash
# Automated framework migration

gemini --checkpointing --yolo \
       -p "Fully automated Express.js to Fastify migration:
1. Analyze current Express structure
2. Create detailed migration plan  
3. Update package.json dependencies
4. Convert all routes and middleware
5. Update error handling patterns
6. Migrate and update all tests
7. Create docker configuration
8. Verify functionality with test suite
9. Generate migration report"
Daily Development Automation
bash
#!/bin/bash
# Daily automated development tasks

gemini --yolo -p "Execute daily development workflow:
1. Pull latest changes safely
2. Update dependencies to latest stable
3. Run full test suite and fix failures  
4. Update documentation for any changes
5. Optimize code performance
6. Run security audit and fix issues
7. Generate daily progress report
8. Commit and push changes with proper messages"
  • gemini-auth: Authentication management
  • gemini-chat: Interactive chat sessions
  • gemini-tools: Tool execution workflows
  • gemini-mcp: MCP server management
  • gemini-code: Code-specific operations

Updates

This skill tracks Gemini CLI updates. Check for new features:

bash
# Update Gemini CLI
npm update -g @google/gemini-cli

# Check version
gemini --version

# View changelog
gemini changelog

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/ai-llm/gemini-cli-adaptationio-skrillz of majiayu000/claude-skill-registry.

  • SKILL.md
  • metadata.json

Open the folder on GitHubat commit 000116a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Gemini CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gemini CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gemini CLI this skillmajiayu000/claude-skill-registry6661 repos~4.1kAutomated safety check: NotesMIT
Gemini Video Understandingeinverne/dotfiles1211 repos~2.6kAutomated safety check: NotesMIT
Yolo ChorusChorus-AIDLC/Chorus1.2k—~7.8kAutomated safety check: PassAGPL-3.0
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k9 repos~3.3kAutomated safety check: PassMIT
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k8 repos~1.7kAutomated safety check: PassMIT
Yolo Master AgentTencent/YOLO-Master742—~755Automated safety check: PassAGPL-3.0

Similar skills

  • Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs.

    121 GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check: notes
  • Yolo Chorus

    Chorus-AIDLC/Chorus

    Full-auto AI-DLC pipeline — drive a single prompt from Idea through Proposal, Execution, and Verification to Done.

    1.2k GitHub stars~7.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 9 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed
  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 8 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Yolo Master Agent

    Tencent/YOLO-Master

    A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.

    742 GitHub stars~755 tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed
  • Video Understand

    jjyaoao/HelloAgents

    Implement specialized video understanding capabilities using the z-ai-web-dev-sdk.

    3.2k GitHub starsUsed in 1 repo~6.2k tokens
    AI & LLM EngineeringAuto-check passed

More from majiayu000/claude-skill-registry

All 971 skills in this repo
  • Deep Research

    majiayu000/claude-skill-registry

    Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 6 repos~1.1k tokens
    Auto-check passed
  • Exa Search

    majiayu000/claude-skill-registry

    Neural search via Exa MCP for web, code, and company research.

    666 GitHub starsUsed in 5 repos~856 tokens
    Auto-check passed
  • Fal AI Media

    majiayu000/claude-skill-registry

    Unified media generation via fal.ai MCP — image, video, and audio.

    666 GitHub starsUsed in 5 repos~1.7k tokens
    Auto-check passed
  • Bgpt Paper Search

    majiayu000/claude-skill-registry

    Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.

    666 GitHub starsUsed in 4 repos~619 tokens
    Auto-check: notes
  • Bio Alignment Pairwise

    majiayu000/claude-skill-registry

    Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.

    666 GitHub starsUsed in 4 repos~1.7k tokens
    Auto-check passed
  • Open Notebook

    majiayu000/claude-skill-registry

    Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.

    666 GitHub starsUsed in 4 repos~2.4k tokens
    Auto-check passed

Questions about Gemini CLI

What does Gemini CLI do?

Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution. Gemini CLI is an agent skill from majiayu000/claude-skill-registry. Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution.

When should I use Gemini CLI?

Gemini CLI fits situations like: working with Gemini AI; multimodal tasks; needing advanced AI capabilities.

How do I install Gemini CLI in Claude Code?

Run `npx skills add majiayu000/claude-skill-registry --skill gemini-cli -a claude-code`. Or copy the skill folder (skills/ai-llm/gemini-cli-adaptationio-skrillz in majiayu000/claude-skill-registry) into .claude/skills/gemini-cli in your project. Claude Code loads it when a task matches its description.

How do I install Gemini CLI in Codex?

Run `npx skills add majiayu000/claude-skill-registry --skill gemini-cli -a codex`. Or copy the skill folder (skills/ai-llm/gemini-cli-adaptationio-skrillz in majiayu000/claude-skill-registry) into .agents/skills/gemini-cli in your project. Codex loads it when a task matches its description.

Can I use Gemini CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/claude-skill-registry --skill gemini-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gemini-cli, .gemini/skills/gemini-cli, .github/skills/gemini-cli and .opencode/skills/gemini-cli in your project.

What does Gemini CLI need to run?

Going by SKILL.md and its folder, Gemini CLI needs the command-line tools its instructions call (gemini, npm, jq, node, npx and git) and credentials named GEMINI_API_KEY and GOOGLE_APPLICATION_CREDENTIALS. Our summary lists: Python 3; Node.js; A credential in GEMINI_API_KEY.

Does Gemini CLI access the network?

SKILL.md names 2 domains. In commands or code: aistudio.google.com and github.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Gemini CLI safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Gemini CLI use?

Gemini CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gemini CLI use?

About 4.1k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gemini CLI?

Skills that share tags, products or a category with Gemini CLI: Gemini Video Understanding (einverne/dotfiles, 121 stars), Yolo Chorus (Chorus-AIDLC/Chorus, 1.2k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gemini CLI?

majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 971 skills in this directory. The repository was last updated on October 7, 2026.

Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.