Skills for Real Engineers. Straight from my .agents directory.
gemini
Agent skill fromsoftaworks/agent-toolkit
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
How to install gemini
npx skills add softaworks/agent-toolkit# or add only this skill to Claude Code: copy the folder
skills/gemini/
# into
~/.claude/skills/gemini/ (all projects)
.claude/skills/gemini/ (one project)
1# Gemini Skill Guide23## When to Use Gemini4- WHEN ASKED TO BE ACTIVATED5- **Code Review**: Comprehensive code reviews across multiple files6- **Plan Review**: Analyzing architectural plans, technical specifications, or project roadmaps7- **Big Context Processing**: Tasks requiring >200k tokens of context (entire codebases, documentation sets)8- **Multi-file Analysis**: Understanding relationships and patterns across many files910## ⚠️ Critical: Background/Non-Interactive Mode Warning1112**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.1314**For automated/background reviews:**15- ✅ Use `--approval-mode yolo` for fully automated execution16- ✅ OR wrap with timeout: `timeout 300 gemini ...`17- ❌ NEVER use `--approval-mode default` without interactive terminal1819**Symptoms of hung Gemini:**20- Process running 20+ minutes with 0% CPU usage21- No network activity22- Process state shows 'S' (sleeping)2324**Fix hung process:**25```bash26# Check if hung27ps aux | grep gemini | grep -v grep2829# Kill if necessary30pkill -9 -f "gemini.*gemini-3-pro-preview"31```3233## Running a Task34351. Ask the user (via `AskUserQuestion`) which model to use in a **single prompt**. Available models:36 - `gemini-3-pro-preview` ⭐ (flagship model, best for coding & complex reasoning, 35% better at software engineering than 2.5 Pro)37…
Excerpt shown under the repository's MIT license.
More skills in agent-toolkit
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
