CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini

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.

84

1.66x
Quality

76%

Does it follow best practices?

Impact

100%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./dist/plugins/gemini/skills/gemini/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

22%

CI/CD Automated Code Review Integration

Background mode safety and model defaults

Criteria
Without context
With context

yolo approval mode

100%

100%

No default mode

100%

100%

Default model is gemini-3-pro-preview

0%

100%

Timeout wrapper present

100%

100%

Output saved to file

100%

100%

Notes explain yolo rationale

100%

100%

Notes mention timeout rationale

100%

100%

Notes name correct model

0%

100%

100%

59%

Gemini CLI Onboarding Runbook

Model selection guide and version requirements

Criteria
Without context
With context

gemini-3-pro-preview for complex tasks

0%

100%

gemini-3-flash for speed

0%

100%

gemini-2.5-flash for cost

0%

100%

Version prerequisite v0.16.0

0%

100%

Version check command

100%

100%

yolo for automated contexts

100%

100%

default mode for interactive only

100%

100%

Example commands present

100%

100%

gemini-3-pro-preview as default

0%

100%

100%

37%

Gemini Process Hang Incident Response Guide

Hung process detection and resolution

Criteria
Without context
With context

Detection: 20+ min runtime

62%

100%

Detection: 0% CPU

100%

100%

Detection: sleeping state

37%

100%

Diagnosis: network check command

100%

100%

Diagnosis: zero connections = hung

100%

100%

Resolution: pkill command

83%

100%

Resolution: kill -9 by PID

100%

100%

Prevention: yolo for background

0%

100%

Prevention: no default in non-interactive

0%

100%

Prevention: timeout wrapper

100%

100%

Repository
softaworks/agent-toolkit
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.