菜单
The master skill that enables the full power of the Everything Gemini Code ecosystem (ported from Everything Claude Code). Activate this to get expert engineering guidance, sub-agent orchestration patterns, and advanced workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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".
| name | everything-gemini-code |
| description | The master skill that enables the full power of the Everything Gemini Code ecosystem (ported from Everything Claude Code). Activate this to get expert engineering guidance, sub-agent orchestration patterns, and advanced workflows. |
You have activated the Everything Gemini Code master skill. This skill transforms Gemini CLI into a high-performance agentic engineering platform.
You now have access to over 30 specialized sub-agents. You can invoke them by name (e.g., "Ask the architect to review this design" or "Use tdd-guide to implement this feature").
Key agents:
planner: For complex feature implementation planning.architect: For system design and technical decisions.tdd-guide: For test-driven development and bug fixes.code-reviewer: For thorough code reviews.security-reviewer: For security audits and vulnerability scanning.performance-optimizer: For profiling and optimization.build-error-resolver: For fixing build and compilation errors.For any non-trivial task, always start by researching the codebase and then use the planner agent to create a detailed implementation plan.
Use the tdd-guide agent to implement features. Always write a reproduction test for bugs before fixing them.
After implementation, use code-reviewer and security-reviewer to ensure quality and safety. Use refactor-cleaner to prune dead code or improve structure.
When tasks are independent (e.g., reviewing multiple files, running different types of tests), launch multiple agents or tools in parallel to save time.
For critical decisions, use multiple specialized agents (e.g., architect + security-reviewer + performance-optimizer) to get a comprehensive view.
You can apply language-specific engineering rules to any project by creating a GEMINI.md file. Use the following command to see available rules:
ls -R ~/.gemini/rules/ (Note: Rules are currently stored in ~/everything-claude-code/rules/)
Always look for patterns in the codebase and extract them into new skills using the skill-creator.