Tooluck logoTooluck
SKILL.md

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

install gemini
# install the agent-toolkit pack with the skills CLI
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)

skills/gemini/SKILL.md

MITFull file
1# Gemini Skill Guide
2
3## When to Use Gemini
4- WHEN ASKED TO BE ACTIVATED
5- **Code Review**: Comprehensive code reviews across multiple files
6- **Plan Review**: Analyzing architectural plans, technical specifications, or project roadmaps
7- **Big Context Processing**: Tasks requiring >200k tokens of context (entire codebases, documentation sets)
8- **Multi-file Analysis**: Understanding relationships and patterns across many files
9
10## ⚠️ Critical: Background/Non-Interactive Mode Warning
11
12**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.
13
14**For automated/background reviews:**
15- ✅ Use `--approval-mode yolo` for fully automated execution
16- ✅ OR wrap with timeout: `timeout 300 gemini ...`
17- ❌ NEVER use `--approval-mode default` without interactive terminal
18
19**Symptoms of hung Gemini:**
20- Process running 20+ minutes with 0% CPU usage
21- No network activity
22- Process state shows 'S' (sleeping)
23
24**Fix hung process:**
25```bash
26# Check if hung
27ps aux | grep gemini | grep -v grep
28
29# Kill if necessary
30pkill -9 -f "gemini.*gemini-3-pro-preview"
31```
32
33## Running a Task
34
351. 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

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates