gemini

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini Skill Guide

Gemini技能指南

When to Use This Skill

何时使用该技能

Primary Use Cases:

User explicitly requests
```
gemini
```
CLI execution (Mode 1: Direct CLI)
Large-context analysis requiring 1M token window (Mode 2: Gemini Delegation)
Repository-scale code reviews and architectural analysis
Multimodal analysis (code + images/diagrams)
Cross-module dependency tracking

Do NOT use for:

Simple code explanations (use Claude directly)
Small context tasks (<100K tokens)
Tasks not requiring Gemini-specific capabilities

主要使用场景:

用户明确要求执行
```
gemini
```
CLI（模式1：直接CLI调用）
需要100万token窗口的大上下文分析（模式2：Gemini委托）
仓库级代码评审与架构分析
多模态分析（代码 + 图片/图表）
跨模块依赖跟踪

请勿用于:

简单代码解释（直接使用Claude）
小上下文任务（<10万tokens）
不需要Gemini专属功能的任务

Execution Modes

执行模式

Mode 1: Direct CLI Execution

模式1：直接CLI执行

When: User explicitly asks to run gemini CLI

Workflow:

Gather configuration using structured questions:
- Model selection (gemini-3-pro-preview vs gemini-3-flash-preview)
- Approval mode (default, auto_edit, yolo)
- Output format (text, json, stream-json)

Execute:

bash

gemini "<PROMPT>" -m <MODEL> --approval-mode <MODE> --output-format <FORMAT>

Inform user: "You can resume with 'gemini --resume latest' anytime"

Resuming:

bash

gemini "<CONTINUATION PROMPT>" --resume latest

适用场景: 用户明确要求运行gemini CLI

工作流程:

通过结构化问题收集配置信息:
- 模型选择（gemini-3-pro-preview vs gemini-3-flash-preview）
- 审批模式（default、auto_edit、yolo）
- 输出格式（text、json、stream-json）

执行命令:

bash

gemini "<PROMPT>" -m <MODEL> --approval-mode <MODE> --output-format <FORMAT>

告知用户："您可随时通过'gemini --resume latest'恢复会话"

恢复会话:

bash

gemini "<CONTINUATION PROMPT>" --resume latest

Mode 2: Gemini Delegation for Large Context

模式2：大上下文场景下的Gemini委托

When: Task requires large context window (>100K tokens), multimodal input, or repository-scale analysis

Workflow:

Analyze context and identify what Gemini analysis would help
Formulate comprehensive query with all relevant context:
- Problem statement
- Current findings
- Code snippets or file references
- Specific questions
Leverage Gemini's 1M token context for comprehensive analysis

Execute:

gemini "<DETAILED CONTEXT>" --output-format json

Synthesize Gemini response into actionable insights
Report findings with:
- Clear summary of Gemini's analysis
- Specific recommendations or solutions
- Additional considerations or caveats
- Next steps if applicable

适用场景: 任务需要大上下文窗口（>10万tokens）、多模态输入，或仓库级分析

工作流程:

分析上下文，确定Gemini分析能提供的帮助
结合所有相关上下文制定全面查询:
- 问题说明
- 当前发现
- 代码片段或文件引用
- 具体问题
利用Gemini的100万token上下文进行全面分析

执行命令:

gemini "<DETAILED CONTEXT>" --output-format json

将Gemini的响应提炼为可执行的洞察
汇报发现内容，包含:
- Gemini分析的清晰摘要
- 具体建议或解决方案
- 其他注意事项或警告
- 适用的后续步骤

Error Handling

错误处理

Verify gemini binary exists before execution:
```
which gemini
```
Stop immediately on non-zero exit codes and report to user
Request direction before retrying failed commands
Before using high-autonomy flags, confirm with user:
- ```
--yolo
```
  (auto-approve all actions)
- ```
--approval-mode yolo
```

执行前验证gemini二进制文件是否存在：
```
which gemini
```
遇到非零退出码时立即停止并向用户报告
重试失败命令前需请求用户指示
使用高自主性标志前需与用户确认:
- ```
--yolo
```
  （自动批准所有操作）
- ```
--approval-mode yolo
```

Context Management

上下文管理

Gemini excels at large context (up to 1M tokens)
For massive contexts (>500K tokens), consider module-by-module summaries
Use
```
--include-directories
```
to add additional workspace paths
Leverage session resume for iterative refinement

Gemini擅长处理大上下文（最多100万tokens）
对于超大规模上下文（>50万tokens），考虑按模块生成摘要
使用
```
--include-directories
```
添加额外工作区路径
利用会话恢复功能进行迭代优化

Configuration Gathering Patterns

配置收集模式

Initial Configuration (Mode 1, Step 1)

初始配置（模式1，步骤1）

At the start of Mode 1 execution, gather model, approval mode, and output format:

Standard configuration question:

text

Select gemini configuration (model, approval mode, and output format):

1. "gemini-3-pro-preview / default / json (Recommended)" - High quality, safe mode
2. "gemini-3-pro-preview / auto_edit / json" - High quality, auto-approve edits
3. "gemini-3-flash-preview / default / json" - Fast, safe mode
4. "gemini-3-flash-preview / auto_edit / json" - Fast, auto-approve edits
5. "gemini-3-pro-preview / yolo / json" - High quality, fully autonomous
6. "gemini-3-flash-preview / yolo / json" - Fast, fully autonomous
7. "Custom" - User will specify model, approval, and format separately

在模式1执行开始时，收集模型、审批模式和输出格式信息:

标准配置问题:

text

选择gemini配置（模型、审批模式和输出格式）:

1. "gemini-3-pro-preview / default / json（推荐）" - 高质量、安全模式
2. "gemini-3-pro-preview / auto_edit / json" - 高质量、自动批准编辑
3. "gemini-3-flash-preview / default / json" - 快速、安全模式
4. "gemini-3-flash-preview / auto_edit / json" - 快速、自动批准编辑
5. "gemini-3-pro-preview / yolo / json" - 高质量、完全自主
6. "gemini-3-flash-preview / yolo / json" - 快速、完全自主
7. "自定义" - 用户将单独指定模型、审批模式和格式

High-Impact Flags Confirmation

高影响标志确认

Before executing with --yolo or autonomous flags:

text

Ready to execute with these flags: [LIST FLAGS]. Proceed?

1. "Execute now" - Run as configured
2. "Modify configuration" - Change settings
3. "Cancel" - Abort

在使用--yolo或自主标志执行前:

text

即将使用以下标志执行：[标志列表]。是否继续？

1. "立即执行" - 按配置运行
2. "修改配置" - 更改设置
3. "取消" - 终止操作

Post-Execution Follow-up

执行后跟进

After gemini command completes:

text

Gemini completed. [SUMMARY]. Next steps?

1. "Resume with additional prompt" - Continue session
2. "Analyze results" - Review output
3. "Complete" - Finished
4. "Retry with different config" - Adjust settings

gemini命令完成后:

text

Gemini执行完成。[摘要]。下一步操作？

1. "使用新提示恢复" - 继续会话
2. "分析结果" - 查看输出
3. "完成" - 结束任务
4. "使用不同配置重试" - 调整设置

Error Recovery

错误恢复

When command fails or has warnings:

text

Error: [SPECIFIC ERROR]. How to proceed?

1. "Resume with adjustments" - Fix and continue
2. "Retry with different config" - Change model/approval/format
3. "Accept partial results" - Use what worked
4. "Invoke heal-skill" - Fix outdated SKILL.md

当命令失败或出现警告时:

text

错误: [具体错误信息]。如何处理？

1. "调整后恢复" - 修复问题后继续
2. "使用不同配置重试" - 更改模型/审批模式/格式
3. "接受部分结果" - 使用可用的有效结果
4. "调用heal-skill" - 更新过时的SKILL.md

Running a Task

任务执行步骤

Gather configuration using the patterns above
Assemble the command with the appropriate options:
- ```
-m, --model <MODEL>
```
  (gemini-3-pro-preview or gemini-3-flash-preview)
- ```
--approval-mode <MODE>
```
  (default, auto_edit, yolo)
- ```
-o, --output-format <FORMAT>
```
  (text, json, stream-json)
- ```
--include-directories <DIRS>
```
  (additional workspace paths)
- ```
-r, --resume <SESSION>
```
  (latest or session index)
Run the command, capture output, and summarize for the user
After Gemini completes, inform the user: "You can resume this Gemini session at any time by saying 'gemini resume' or asking me to continue."

使用上述模式收集配置信息
组装带有适当选项的命令:
- ```
-m, --model <MODEL>
```
  （gemini-3-pro-preview或gemini-3-flash-preview）
- ```
--approval-mode <MODE>
```
  （default、auto_edit、yolo）
- ```
-o, --output-format <FORMAT>
```
  （text、json、stream-json）
- ```
--include-directories <DIRS>
```
  （额外工作区路径）
- ```
-r, --resume <SESSION>
```
  （latest或会话索引）
运行命令，捕获输出并为用户生成摘要
Gemini完成后，告知用户："您可随时通过说'gemini resume'或要求我继续来恢复此Gemini会话。"

Quick Reference

快速参考

Use case	Approval mode	Key flags
Safe analysis	`default`	`--approval-mode default --output-format json`
Auto-approve edits	`auto_edit`	`--approval-mode auto_edit --output-format json`
Fully autonomous	`yolo`	`--yolo --output-format json`
Resume recent session	Inherited	`--resume latest`
Add workspace directories	Match task	`--include-directories <DIRS>`
Interactive continuation	default	`-i "<PROMPT>"` (stays interactive after)

使用场景	审批模式	关键标志
安全分析	`default`	`--approval-mode default --output-format json`
自动批准编辑	`auto_edit`	`--approval-mode auto_edit --output-format json`
完全自主	`yolo`	`--yolo --output-format json`
恢复最近会话	继承原有配置	`--resume latest`
添加工作区目录	匹配任务需求	`--include-directories <DIRS>`
交互式续接	default	`-i "<PROMPT>"` （续接后保持交互状态）

Model Selection

模型选择

Model	Use Case	Context	Speed
`gemini-3-pro-preview`	Complex reasoning, architecture review	1M tokens	Slower
`gemini-3-flash-preview`	Quick analysis, simple tasks	1M tokens	Faster

模型	使用场景	上下文容量	速度
`gemini-3-pro-preview`	复杂推理、架构评审	100万tokens	较慢
`gemini-3-flash-preview`	快速分析、简单任务	100万tokens	较快

Session Management

会话管理

bash

undefined

bash

undefined

List available sessions

列出可用会话

gemini --list-sessions

Resume most recent session

恢复最近的会话

gemini --resume latest

Resume specific session by index

通过索引恢复特定会话

gemini --resume 5

Delete a session

删除会话

gemini --delete-session 3

undefined

gemini --delete-session 3

undefined

MCP Server Integration

MCP服务器集成

bash

undefined

bash

undefined

List configured MCP servers

列出已配置的MCP服务器

gemini mcp list

Add an MCP server

添加MCP服务器

gemini mcp add <name> <command> [args...]

Remove an MCP server

删除MCP服务器

gemini mcp remove <name>

Limit to specific MCP servers

限制使用特定MCP服务器

gemini "<PROMPT>" --allowed-mcp-server-names mcp-skillset

undefined

gemini "<PROMPT>" --allowed-mcp-server-names mcp-skillset

undefined

Extension System

扩展系统

bash

undefined

bash

undefined

List installed extensions

列出已安装的扩展

gemini extensions list

Install extension from git or path

从git或路径安装扩展

gemini extensions install <source> [--auto-update] [--pre-release]

Update extensions

更新扩展

gemini extensions update [--all]

Disable/enable extension

禁用/启用扩展

gemini extensions disable <name> gemini extensions enable <name>

undefined

gemini extensions disable <name> gemini extensions enable <name>

undefined

Following Up

后续跟进

After every
```
gemini
```
command, offer follow-up options
When resuming, use:
```
gemini "<new prompt>" --resume latest
```
The resumed session automatically uses the same context from the original
Restate the chosen model and approval mode when proposing follow-up actions

每次
```
gemini
```
命令执行后，提供后续操作选项
恢复会话时使用：
```
gemini "<new prompt>" --resume latest
```
恢复后的会话会自动沿用原会话的上下文
提议后续操作时，重申所选的模型和审批模式

Error Handling Guidelines

错误处理指南

Stop and report failures whenever
```
gemini --version
```
or a
```
gemini
```
command exits non-zero; request direction before retrying
Confirm high-impact flags before execution
When output includes warnings or partial results, offer error recovery options

当
```
gemini --version
```
或任意
```
gemini
```
命令返回非零退出码时，立即停止并报告失败，重试前需请求用户指示
执行高影响标志前需确认
当输出包含警告或部分结果时，提供错误恢复选项

Comparison with Codex Skill

与Codex技能的对比

Feature	Gemini	Codex
Context window	1M tokens	~200K tokens
Primary models	gemini-3-pro/flash	gpt-5.2-codex
Approval modes	default/auto_edit/yolo	never/on-request/on-failure
Sandbox	Boolean (--sandbox)	read-only/workspace-write/danger-full-access
Resume	--resume latest/index	codex exec resume --last
Stderr handling	N/A	2>/dev/null for thinking tokens
Output format	text/json/stream-json	json flag

特性	Gemini	Codex
上下文窗口	100万tokens	~20万tokens
主要模型	gemini-3-pro/flash	gpt-5.2-codex
审批模式	default/auto_edit/yolo	never/on-request/on-failure
沙箱	布尔值（--sandbox）	read-only/workspace-write/danger-full-access
恢复会话	--resume latest/index	codex exec resume --last
标准错误处理	N/A	2>/dev/null用于处理思考令牌
输出格式	text/json/stream-json	json标志

Integration Patterns

集成模式

With Other CLI Agents

与其他CLI Agent集成

bash

undefined

bash

undefined

Use gemini for large context, codex for GPT-specific

使用gemini处理大上下文，codex处理GPT专属任务

gemini "Analyze entire codebase architecture" --output-format json codex exec "Implement specific feature based on analysis" --full-auto

Chain with research CLI

与research CLI联动

research docs -t "framework API" --format json | gemini "Apply this to codebase"

undefined

research docs -t "framework API" --format json | gemini "Apply this to codebase"

undefined

Multimodal Analysis

多模态分析

bash

undefined

bash

undefined

Gemini can process images inline with code

Gemini可同时处理图片和代码

gemini "Analyze this architecture diagram and compare with implementation"
--include-directories ./docs ./src

undefined

gemini "Analyze this architecture diagram and compare with implementation"
--include-directories ./docs ./src

undefined

Heal-Skill Integration

Heal-Skill集成

When gemini CLI API changes are detected (command failures, unexpected output formats, or deprecated flags):

Detection: Notice command failures or API mismatches during execution
Trigger: Flag skill for healing via
```
/heal-skill gemini
```
Analysis: Healing agent analyzes current CLI with
```
gemini --help
```
and
```
gemini --version
```
Update: Updates skill documentation to match current API
Validation: Re-validates agent configuration for compatibility
Model Verification: Ensures only gemini-3 models are referenced
Context Window Verification: Confirms 1M token context window specifications

Common Changes to Monitor:

New or deprecated command flags
Changes to approval modes or output formats
Model availability updates (gemini-3 family)
MCP server integration API changes
Session management API modifications
Extension system updates
Context window specification changes

当检测到gemini CLI API变更时（命令失败、意外输出格式或已弃用标志）:

检测: 执行过程中发现命令失败或API不匹配
触发: 通过
```
/heal-skill gemini
```
标记技能需要修复
分析: 修复Agent通过
```
gemini --help
```
和
```
gemini --version
```
分析当前CLI
更新: 更新技能文档以匹配当前API
验证: 重新验证Agent配置的兼容性
模型验证: 确保仅引用gemini-3系列模型
上下文窗口验证: 确认100万token上下文窗口的规格

需监控的常见变更:

新增或已弃用的命令标志
审批模式或输出格式的变更
模型可用性更新（gemini-3系列）
MCP服务器集成API变更
会话管理API修改
扩展系统更新
上下文窗口规格变更