Gemini Cli
A lightweight wrapper that calls the local Gemini CLI directly instead of going through MCP. Reach for this when you need a second opinion, want to analyze large codebases with path references, or need structured change-mode edits that output deterministic OLD/NEW blocks you can apply with confidence. The included wrapper script handles chunked responses with cache keys, supports sandbox execution for safe testing, and can run brainstorming sessions with specific methodologies like SCAMPER. The main constraint is that Gemini can only read files under its current working directory, so you'll need to run commands from the right location or pass the cwd flag. Most useful when you're already using the Gemini CLI locally and want Claude to delegate context-heavy work without fighting token limits.
- skills.sh installs
- 229
- GitHub stars
- 2
- last updated
- Aug 21, 2026
Install
$ npx -y skills add x-zero-l/agent-skills --skill gemini-cli --agent claude-codeInstalls into .claude/skills of the current project.
Files
Gemini CLI Skill
Use Google’s gemini CLI as an external “second brain” when you need a very large context window, a second opinion, or safe sandbox execution. This skill does not use MCP; it runs the local CLI directly.
When To Use
Use this skill when the user asks to:
- “Ask Gemini” / “Use Gemini”
- Analyze or summarize large files or directories (especially with
@pathreferences) - Brainstorm options with a specific framework (SCAMPER, design thinking, etc.)
- Generate structured edit suggestions (“change mode”) that can be applied deterministically
Prerequisites
geminiCLI is installed and configured (e.g.gemini --versionworks)- You are allowed to run local shell commands in this environment
- For sandbox execution, Gemini CLI supports
-s/--sandbox(seegemini --help)
Core Commands
One-shot query (plain)
gemini "Explain what this code does: @src/main.ts"
Choose a model
gemini -m gemini-3-pro-preview "..."
gemini -m gemini-3-flash-preview "..."
Sandbox mode
gemini -s "Safely test @scripts/example.py and explain the results."
Helper Script (Recommended)
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/x-zero-l/agent-skills
- Categories
- DevOps & CI/CD, AI & Agent Building, CLI & Terminal
- First seen
- Jun 3, 2026
Recommended
More DevOps & CI/CD
lead-scoringguia-matthieu/clawfu-skillsBuild and apply lead scoring models combining firmographic fit, behavioral signals, and intent data for sales prioritization226skills.sh installs
hugging-face-tool-builderhuggingface/skillsUse this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when226skills.sh installshugging-face-trackiohuggingface/skillsTrack and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retr226skills.sh installs
product-strategistncklrs/startup-os-skillsExpert product strategist for vision, strategy, and market positioning. Use when defining product vision, assessing product-market fit, sizing market opportunit225skills.sh installs
vibe-workflowkhazp/vibe-coding-prompt-templateComplete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says223skills.sh installs
terrasharklukasniessen/terrasharkPrevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and complian223skills.sh installs