Menu
Initial setup and configuration for Everything Gemini Code. Run this to ensure your environment is fully optimized.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | everything-gemini-setup |
| description | Initial setup and configuration for Everything Gemini Code. Run this to ensure your environment is fully optimized. |
This skill helps you configure your Gemini CLI environment to use the full power of the Everything Gemini Code ecosystem.
To use the 30+ expert sub-agents, you must enable the experimental agents feature.
I have already done this for you in ~/.gemini/settings.json.
The sub-agents are stored in ~/.gemini/agents/. Gemini CLI automatically discovers them.
You can see the list of agents by running:
ls ~/.gemini/agents/
The skills are stored in ~/.gemini/skills/. You can activate them using the activate_skill tool or by asking me to "activate skill X".
I have already imported 119+ skills for you.
To enable the "Everything Gemini Code" philosophy in your project, you should have a GEMINI.md file in your project root.
I have created a template for you at ~/GEMINI.md. You can copy it to any project:
cp ~/GEMINI.md /path/to/your/project/
Language-specific rules are available in ~/.gemini/rules/. You can incorporate these into your GEMINI.md.
To verify your setup, try asking me:
frontend-patterns skill?"architect to explain our current system design."Start a new task and see how the specialized agents and skills improve your workflow!
For more details, activate the everything-gemini-code master skill.
Head-to-head comparison of coding agents (Gemini Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
Capture architectural decisions made during Gemini Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
Patterns and architectures for autonomous Gemini Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".