omega-gemini-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini CLI Skill

Gemini CLI 技能

Headless wrapper for Google Gemini CLI. Sends prompts via stdin to

gemini -p "" --yolo

. Free tier available — no API key required (Google OAuth only).

Google Gemini CLI的无头封装。通过标准输入将提示词发送到

gemini -p "" --yolo

。提供免费套餐 — 无需API密钥（仅需Google OAuth）。

When to Use

适用场景

Get a Google Gemini perspective on any question
Free-tier AI consultation (no API key costs)
Code review from Gemini's model
Brainstorming and analysis tasks
Cross-validation of Claude's own responses
Large files or codebases that benefit from Gemini's context window
Sandbox execution (run/test code via Gemini)

针对任何问题获取Google Gemini的观点
免费AI咨询（无API密钥成本）
Gemini模型提供的代码审查
头脑风暴和分析任务
交叉验证Claude自身的响应
可受益于Gemini上下文窗口的大文件或代码库
沙箱执行（通过Gemini运行/测试代码）

Response Times

响应时间

Gemini CLI runs as a subprocess and includes model startup time:

Simple Q&A / news query: ~2 minutes
Codebase or large-file review: ~5–10 minutes

Set expectations with the user before running long tasks.

Gemini CLI作为子进程运行，耗时包含模型启动时间：

简单问答/新闻查询：约2分钟
代码库或大文件审查：约5–10分钟

运行长耗时任务前请先告知用户预期耗时。

Usage

使用方法

Ask a question

提问

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "What is the best caching strategy for a Node.js API?"

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "What is the best caching strategy for a Node.js API?"

Specify model (short or long flag)

指定模型（短标志或长标志）

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" --model gemini-2.5-flash
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" -m gemini-2.5-flash

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" --model gemini-2.5-flash
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" -m gemini-2.5-flash

JSON output

JSON输出

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "List 5 design patterns" --json

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "List 5 design patterns" --json

Returns: {"response":"..."} on success, {"error":"...","raw":"..."} on parse failure

成功返回：{"response":"..."}，解析失败返回：{"error":"...","raw":"..."}

undefined

undefined

Code sandbox (short or long flag)

代码沙箱（短标志或长标志）

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" --sandbox
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" -s

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" --sandbox
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" -s

Stdin usage

标准输入用法

bash

echo "Explain recursion" | node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs

bash

echo "Explain recursion" | node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs

File review (embed content in prompt)

文件审查（将内容嵌入提示词）

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Review this code: $(cat src/auth.ts)"

bash

node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Review this code: $(cat src/auth.ts)"

Availability Check

可用性检查

bash

node .claude/skills/omega-gemini-cli/scripts/verify-setup.mjs

bash

node .claude/skills/omega-gemini-cli/scripts/verify-setup.mjs

Exit 0 = available (Node 18+ and Gemini CLI found)

退出码0 = 可用（已安装Node 18+和Gemini CLI）

Exit 1 = not installed or too old

退出码1 = 未安装或版本过低

undefined

undefined

Scripts

脚本

Script	Purpose
`ask-gemini.mjs`	Core headless wrapper — sends prompt via stdin
`parse-args.mjs`	Argument parser (--model/-m, --json, --sandbox/-s)
`verify-setup.mjs`	Availability check (Node 18+, Gemini CLI via PATH or npx)
`format-output.mjs`	Output normalization (JSON envelope handling)

脚本名称	用途
`ask-gemini.mjs`	核心无头封装 — 通过标准输入发送提示词
`parse-args.mjs`	参数解析器（支持--model/-m、--json、--sandbox/-s）
`verify-setup.mjs`	可用性检查（Node 18+，PATH或npx可调用Gemini CLI）
`format-output.mjs`	输出标准化（JSON封装处理）

Flags

参数标志

Flag	Short	Description
`--model MODEL`	`-m`	Gemini model (e.g., gemini-2.5-flash, gemini-2.5-pro)
`--json`		Machine-readable JSON output: `{"response":"..."}` envelope
`--sandbox`	`-s`	Code execution sandbox mode

标志	短标志	描述
`--model MODEL`	`-m`	Gemini模型（例如gemini-2.5-flash、gemini-2.5-pro）
`--json`		机器可读JSON输出： `{"response":"..."}` 封装格式
`--sandbox`	`-s`	代码执行沙箱模式

Models (2026)

支持模型（2026年）

Model ID	Notes
`gemini-3-pro-preview`	Latest (2026), highest capability
`gemini-3-flash-preview`	Latest (2026), faster
`gemini-2.5-pro`	Stable, high capability
`gemini-2.5-flash`	Recommended: lower quota/latency
`gemini-2.5-flash-lite`	Lightest, fastest, lowest quota usage

模型ID	说明
`gemini-3-pro-preview`	最新版（2026年），能力最强
`gemini-3-flash-preview`	最新版（2026年），速度更快
`gemini-2.5-pro`	稳定版，能力优秀
`gemini-2.5-flash`	推荐使用：配额消耗更低、延迟更小
`gemini-2.5-flash-lite`	最轻量、速度最快、配额消耗最低

Exit Codes

退出码

Code	Meaning
0	Success
1	Error (CLI failure, auth issue, JSON parse failure with --json)
9009	Windows: command not found (falls back to npx automatically)

代码	含义
0	成功
1	错误（CLI执行失败、认证问题、--json模式下解析失败）
9009	Windows环境：未找到命令（自动回退到npx执行）

Slash Commands (when installed in a project with .claude/commands/)

斜杠命令（安装在包含.claude/commands/的项目中时可用）

Command	Purpose
`/analyze`	Run headless script with user's prompt (and any @ file refs)
`/sandbox`	Run with --sandbox; execute or test code
`/omega-gemini`	Alias: run headless for analysis, sandbox, or brainstorm as appropriate
`/brainstorm`	Brainstorm mode (build prompt with challenge + optional methodology)
`/omega-gemini-setup`	Verify Node and Gemini CLI; guide user to install and auth. No MCP.

命令名称	用途
`/analyze`	结合用户提示词（及任意@文件引用）运行无头脚本
`/sandbox`	启用--sandbox模式运行；执行或测试代码
`/omega-gemini`	别名：根据场景自动运行分析、沙箱或头脑风暴模式
`/brainstorm`	头脑风暴模式（基于需求+可选方法论构建提示词）
`/omega-gemini-setup`	校验Node和Gemini CLI；引导用户完成安装和认证。无MCP依赖。

Anti-Patterns & Iron Laws

反模式与铁则

ALWAYS use verify-setup.mjs before first use
NEVER pass prompt as positional arg to raw gemini CLI — use ask-gemini.mjs wrapper
ALWAYS validate model parameter (wrapper validates via regex
```
^[a-zA-Z0-9._-]+$
```
on Windows)
NEVER assume gemini is on PATH — wrapper handles npx
```
@google/gemini-cli
```
fallback automatically
ALWAYS handle exit code 1 and 9009 gracefully
ALWAYS set user expectations about response time before running (2–10 minutes typical)

首次使用前必须运行verify-setup.mjs校验环境
禁止直接将提示词作为位置参数传递给原生gemini CLI — 必须使用ask-gemini.mjs封装
必须校验model参数（Windows环境下封装层会通过正则
```
^[a-zA-Z0-9._-]+$
```
校验）
不要假设gemini已加入PATH — 封装层会自动处理npx
```
@google/gemini-cli
```
回退逻辑
必须优雅处理退出码1和9009
运行前必须告知用户预期响应时间（通常为2–10分钟）

Integration Notes

集成说明

Auth: One-time Google OAuth via
```
gemini
```
interactive session (run
```
gemini
```
once to sign in)
Rate limits: Governed by Gemini API quotas (generous for personal use on free tier)
Platform: Full cross-platform; Windows uses
```
shell: true
```
with model validation; non-Windows uses array args (no shell)
npx fallback: On PATH miss, automatically retries with
```
npx -y @google/gemini-cli
```
No timeout flag: Unlike other omega wrappers, gemini wrapper has no --timeout-ms
Stdin delivery: Prompt always sent via stdin to avoid shell argument length limits (8191-char cmd.exe limit on Windows, ARG_MAX on Linux/macOS)
JSON envelope:
```
--json
```
wraps output as
```
{"response":"..."}
```
on success or
```
{"error":"...","raw":"..."}
```
on failure

认证： 通过
```
gemini
```
交互式会话完成一次性Google OAuth认证（运行一次
```
gemini
```
即可登录）
速率限制： 受Gemini API配额约束（个人用户免费套餐配额充足）
平台： 全跨平台支持；Windows使用
```
shell: true
```
搭配模型校验；非Windows使用数组参数（无shell）
npx回退： 未在PATH中找到命令时，自动重试
```
npx -y @google/gemini-cli
```
无超时参数： 与其他omega封装不同，gemini封装没有--timeout-ms参数
标准输入传递： 提示词始终通过标准输入发送，避免shell参数长度限制（Windows cmd.exe上限为8191字符，Linux/macOS为ARG_MAX上限）
JSON封装：
```
--json
```
模式下成功输出会封装为
```
{"response":"..."}
```
，失败则封装为
```
{"error":"...","raw":"..."}
```

Requirements

依赖要求

Node.js 18+ to run the scripts
Google Gemini CLI (
```
npm install -g @google/gemini-cli
```
) with one-time Google sign-in

Node.js 18+ 用于运行脚本
Google Gemini CLI（
```
npm install -g @google/gemini-cli
```
）并完成一次性Google登录

Memory Protocol

记忆协议

Before work: Read

.claude/context/memory/learnings.md

After work: Append findings to learnings or issues as needed.

Note: Use
pnpm search:code
to discover references to this skill codebase-wide.

工作前：读取

.claude/context/memory/learnings.md

工作后：按需将发现追加到学习记录或问题列表中。

注意：使用
pnpm search:code
可查询全代码库中对该技能的引用。