mcpField
G
gemini

gemini

github.com/johnlindquist生产力2641 次安装45 周前更新
代码仓库

关于 gemini

gemini 是通过 Gemini CLI 使用 Google Gemini Pro 进行研究、分析和推理的技能,提供摘要、代码分析和事实核查等任务的命令示例与提示词模式。

主要功能

  1. 01Gemini CLI 命令指南
  2. 02研究与综合提示词
  3. 03文档摘要
  4. 04代码分析
  5. 05事实核查与信息提取
  6. 06输出和错误处理建议

适用场景

  1. 01研究主题并整理事实
  2. 02通过标准输入总结文档
  3. 03从命令行分析代码
  4. 04提取结构化数据

安装

复制下面的命令,在终端中运行。

$npx skills add https://github.com/johnlindquist/claude --skill gemini

安装后在 Claude Code 中输入/gemini确认已加载。

详细介绍

Gemini AI 助手

利用 Google 的 Gemini Pro 模型及其 100 万 token 上下文窗口,完成研究、分析和推理任务。

前置条件

安装 Gemini CLI:

pip install google-generativeai

设置你的 API key:

export GEMINI_API_KEY=your_api_key

在以下地址获取 API key:https://makersuite.google.com/app/apikey

CLI 参考

基本用法
# Simple question
gemini -m pro "Your question here"

# With text output (no markdown)
gemini -m pro -o text "Your question"

# Disable extensions for programmatic use
gemini -m pro -o text -e "" "Your question"

# Pipe content as stdin
echo "content to analyze" | gemini -m pro -o text -e "" "Summarize this"
cat file.txt | gemini -m pro -o text -e "" "Analyze this code"

常见操作

研究

带有批判性分析的深度研究:

gemini -m pro -o text -e "" "You are an expert research analyst. Research: [topic]. Provide specific facts, distinguish opinions from facts, note uncertainties, and give actionable insights."
摘要
cat document.txt | gemini -m pro -o text -e "" "Summarize this content, focusing on: [focus area]"
代码分析
cat code.ts | gemini -m pro -o text -e "" "Analyze this code and answer: [question]"
带综合归纳的网页搜索
gemini -m pro -o text -e "" "Search and synthesize: [query]. Include specific facts, dates, and distinguish confirmed from speculative information."
事实核查
gemini -m pro -o text -e "" "Fact-check this claim: [claim]. State true/false/partial, cite sources, note context."
逐步推理
gemini -m pro -o text -e "" "Think through this problem step by step: [problem]. Constraints: [constraints]. Provide reasoning and conclusion."
数据提取
cat content.txt | gemini -m pro -o text -e "" "Extract [what to extract] from this content. Format as [json/list/table]."
新闻查询
gemini -m pro -o text -e "" "Latest news about: [topic] from [timeframe]. Summarize important developments."

提示词模板

研究提示词
You are an expert research analyst. Your goal is to provide genuinely useful, accurate research.

RESEARCH OBJECTIVE: [topic]

QUALITY STANDARDS:
- Be specific and concrete, not vague
- Distinguish between facts, expert opinions, and speculation
- Note when information is uncertain, contested, or evolving
- Identify what's NOT known or what gaps exist
- Provide actionable insights, not just information
分析提示词
Analyze the following and provide:
1. Key findings
2. Implications
3. Recommendations
4. Uncertainties or gaps

Content: [content]

最佳实践

  1. 使用 -o text -e "" 进行程序化调用,以获得干净的输出
  2. 通过 stdin 传入大段内容,而不是使用命令行参数
  3. 在提示词中要具体 - 模糊的问题只会得到模糊的回答
  4. 要求结构化输出 - 请求列表、表格或 JSON,以便解析
  5. 在准确性很重要时要求引用来源
  6. 为长时间操作设置超时(gemini 可能需要 30-120 秒)

错误处理

错误解决方案
"command not found"安装:pip install google-generativeai
"API key" / "unauthorized"设置 GEMINI_API_KEY 环境变量
"rate limit" / "quota"稍等后重试,或在 Google Cloud Console 检查配额
超时拆分为更小的查询,或增加超时时间

评论

支持 Markdown