Gemini CLI — Code & Large-Context Analysis

Trust Score 86/100

Run the Gemini CLI for large-context code reviews, plan reviews, and multi-file analysis; includes safety guidance for background and interactive modes.

triggers:geminicode reviewbig contextapproval-modebackground analysis

GitHub SKILL.md

What it does

This skill provides a complete guide for invoking the Gemini CLI to perform comprehensive code reviews, architectural plan reviews, and big-context analysis across multiple files or repositories. It explains model selection, approval modes, recommended flags for automated runs, timeout safeguards, and troubleshooting for hung processes.

When to use it

Use this skill when a user explicitly requests Gemini for: codebase security or quality reviews, architectural or plan analysis, processing very large context (>200k tokens), or any multi-file automated analysis where Gemini's large-window models help. Prefer yolo approval mode for non-interactive/background tasks and default only for interactive terminal sessions.

What's included

Scripts: none in the repo path for this SKILL.md (has_scripts=false)
References: none (has_references=false)
Instructions: step-by-step guidance for assembling Gemini CLI commands, model and approval-mode selection, safety boundaries, timeout wrappers, and troubleshooting commands to detect and kill hung Gemini processes.

Compatible agents

Best fit for agents or tooling that can run CLI tools (Codex/Gemini CLI, Claude Code, Cursor) and for automation pipelines that accept --approval-mode yolo and timeouts.

Audit Summary

Gemini CLI wrapper skill providing detailed guidance for running Gemini models in background and interactive modes. No bundled scripts — purely instructional SKILL.md with comprehensive model selection tables, approval mode guidance, and troubleshooting for hung processes. Well-written safety boundaries and error handling sections.

Watch Out

--approval-mode yolo is recommended for background tasks but could auto-approve destructive Gemini tool calls if not carefully scoped
Requires Gemini CLI v0.16.0+ installed and configured with API key
No resume functionality — sessions are one-shot

Notes

Clean skill with no executable code. The pkill commands in troubleshooting are diagnostic guidance only, not auto-executed. Safety boundaries are well-documented. Would benefit from a references/ directory to reduce SKILL.md length.

Information

Repository: agent-skills
Stars: 231

Trust Score

Overall86

Security95

Code Quality82

Architecture68

Usefulness72

More from agent-skills

Codex CLI Skill

Guides safe, sandboxed use of the Codex CLI for code analysis, refactoring, and automated edits, with recommended flags and safety boundaries.

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills