This wraps Google's Gemini CLI for handling code reviews and analysis that need serious context windows (we're talking 200k+ tokens). The skill guide is refreshingly paranoid about approval modes, which is earned: there's a whole section on not hanging your process when running in background mode. Use yolo mode for automated reviews, default only when you're actually at a terminal. Ships with Gemini 3 Pro as the flagship model (76.2% on SWE-bench), plus Flash variants when you need speed over thoroughness. The practical bit is the timeout wrappers and process killing commands, because apparently this thing will hang silently if you misconfigure it. Good for whole-codebase analysis or architectural reviews where you need the LLM to see everything at once.

skills.sh installs
4K
GitHub stars
2.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add softaworks/agent-toolkit --skill gemini --agent claude-code

Installs into .claude/skills of the current project.

Files

Gemini Skill Guide

When to Use Gemini

  • WHEN ASKED TO BE ACTIVATED
  • Code Review: Comprehensive code reviews across multiple files
  • Plan Review: Analyzing architectural plans, technical specifications, or project roadmaps
  • Big Context Processing: Tasks requiring >200k tokens of context (entire codebases, documentation sets)
  • Multi-file Analysis: Understanding relationships and patterns across many files

⚠️ Critical: Background/Non-Interactive Mode Warning

NEVER use --approval-mode default in background or non-interactive shells (like Claude Code tool calls). It will hang indefinitely waiting for approval prompts that cannot be provided.

For automated/background reviews:

  • ✅ Use --approval-mode yolo for fully automated execution
  • ✅ OR wrap with timeout: timeout 300 gemini ...
  • ❌ NEVER use --approval-mode default without interactive terminal

Symptoms of hung Gemini:

  • Process running 20+ minutes with 0% CPU usage
  • No network activity
  • Process state shows 'S' (sleeping)

Fix hung process:

# Check if hung
ps aux | grep gemini | grep -v grep

# Kill if necessary
pkill -9 -f "gemini.*gemini-3-pro-preview"

Sponsors

Details

Repository
github.com/softaworks/agent-toolkit
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building, Productivity & Planning, CLI & Terminal

More from softaworks/agent-toolkit

All 43
1openai avatarsecurity-ownership-mapopenai/skillsAnalyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph4Kskills.sh installs
2inngest avatarinngest-stepsinngest/inngest-skillsUse when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external e4Kskills.sh installs
3yaklang avatarapi-recon-and-docsyaklang/hack-skillsAPI reconnaissance and documentation review playbook. Use when discovering endpoints, schemas, versions, OpenAPI specs, hidden docs, and surface area for API te4Kskills.sh installs
4softaworks avatardaily-meeting-updatesoftaworks/agent-toolkitInteractive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare 4Kskills.sh installs
5longbridge avatarlongbridge-earningslongbridge/skillsEarnings analysis — pre- and post-earnings. Pre-earnings preview: prior-guidance review, recent-events tracking, last call's Q&A, and a key-things-to-watch fram3.9Kskills.sh installs
6coralogix avatarcx-platform-admincoralogix/cx-cliUse this skill when the user asks "who has access", "audit permissions", "check user roles", "list API keys", "review access controls", "rotate API keys", "crea3.9Kskills.sh installs