Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

grok-prompting神悟提示

Agent Skill

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

总安装

392

周安装

16

GitHub Stars

4

下载量

127
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:grok-prompting(神悟提示)
来源仓库:https://github.com/duyet/claude-plugins
仓库路径:skills/grok-prompting
安装命令:
npx skills add https://github.com/duyet/claude-plugins --skill grok-prompting
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/duyet/claude-plugins --skill grok-prompting

简介

grok-prompting 用于辅助提示词、系统指令和工作流模板的整理。

  • 适合规范任务边界、统一输出格式或优化提示词可复用性。
  • 支持 Codex、Claude、Cursor、Gemini CLI 等宿主环境。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装。
  • 使用时需保留真实业务约束,避免将示例当硬规则。

SKILL.md

Grok Prompt Engineering

Grok is xAI's large language model with a unique personality: witty, rebellious, and less content-constrained than other models. It has real-time access to X (Twitter) for current events knowledge.

Note: Grok documentation is limited. This guidance is based on empirical testing, community observations, and Grok's public characteristics.

When to Invoke This Skill

Use this skill when:

  • Crafting prompts specifically for Grok/xAI
  • Leveraging real-time current events knowledge
  • Using conversational, less-structured prompting style
  • Discussing topics that might be filtered by other models

Grok's Identity & Characteristics

AttributeDescription
PersonalityWitty, rebellious, conversational
Knowledge SourceReal-time X (Twitter) access
ConstraintsLess content-filtered than Claude/Gemini
Best ForCurrent events, controversial topics, creative writing
Prompt StyleNatural, conversational, flexible

Universal Prompting Techniques (Grok-Adapted)

1. Zero-Shot Prompting

Grok excels at zero-shot when prompts are conversational and direct.

Good Example:

Hey Grok, what's the latest news about AI developments today?

Less Effective:

Please provide a comprehensive summary of recent AI advancements.

2. Few-Shot Prompting

Provide natural language examples that match Grok's conversational style.

Here are some examples of how I'd like you to respond:

User: What's Bitcoin at today?
Grok: Bitcoin's sitting at around $67,420 as of now, up 2.3% on the day. The crypto markets are buzzing with optimism!

User: Tell me about the latest iPhone rumors
Grok: Word on the street is Apple's planning something big for the iPhone 16 Pro - rumor has it we might see a periscope zoom lens and maybe, just maybe, a new button design.

User: What's the weather like in Tokyo?
Grok:

3. Chain-of-Thought Prompting

Grok responds well to "thinking out loud" prompts.

Let's work through this step by step:

I need to decide whether to invest in [company]. Here's what I know:
- Financials: [data]
- Market position: [info]
- Recent news: [headlines]

Walk me through your analysis, considering both the bullish and bearish cases.

4. Zero-Shot CoT

Simply add "Let's think about this" or "Walk me through your reasoning":

What do you think will happen to interest rates next year?

Let's think about this step by step.

5. Prompt Chaining

Break complex tasks into natural conversation steps:

Prompt 1:

I'm planning a trip to Japan. First, help me brainstorm the top 5 must-visit cities.

Prompt 2 (after response):

Great! Now for each of those cities, what are the top 3 attractions?

Prompt 3:

Perfect. Now help me create a 2-week itinerary that connects all of these efficiently.

6. ReAct Prompting

Grok's real-time knowledge makes it excellent for reasoning with current information:

Question: [your question]

Let's approach this methodically:

Thought 1: [what Grok should consider first]
Action 1: [what to search or analyze]
Thought 2: [based on findings]
...

7. Tree of Thoughts

For exploration and creative tasks:

I want to explore [topic]. Let's imagine three different perspectives:

1. The Optimist's View: [Grok generates positive take]
2. The Skeptic's View: [Grok generates critical take]
3. The Pragmatist's View: [Grok generates balanced take]

Now, let's discuss where these perspectives intersect and diverge.

Grok-Specific Best Practices

1. Conversational Prompts Work Best

Grok's personality shines with natural, conversational prompts rather than overly structured ones.

Good:

Dude, what's your take on this whole AI thing? Are we doomed or what?

Less Effective:

Please provide a formal analysis of the potential risks and benefits of artificial intelligence development.

2. Leverage Real-Time Knowledge

Grok can access current events from X (Twitter):

What's the crypto community saying about the latest Bitcoin ETF approval? Give me the vibe from Crypto Twitter.
What's the latest drama in the tech world today? Fill me in on the juiciest stories.

3. Embrace the Wit

Grok is designed to be witty and entertaining. Lean into this:

Explain quantum computing to me like I'm a smart teenager who appreciates a good joke.

4. Direct Requests Work

Unlike other models that need delicate prompting, Grok responds well to directness:

Roast this startup pitch deck: [paste text]
Tell me the harsh truth about [topic].

Anti-Patterns to Avoid

Anti-PatternWhy It FailsBetter Approach
Overly formal promptsGoes against Grok's personalityUse conversational language
Excessive structureGrok prefers flexibilityKeep prompts natural and flowing
Ignoring real-time knowledgeWastes Grok's unique capabilityAsk about current events
Attempting to suppress personalityCan't override core designWork with the wit, not against it

Quick Reference Templates

Current Events Query

What's the latest on [topic] according to posts on X? Give me a summary of the current sentiment.

Analysis with Reasoning

Let's think through [topic] step by step. Consider multiple angles and don't hold back on your honest assessment.

Creative Brainstorming

I need creative ideas for [topic]. Give me 5 unconventional options, and feel free to get a little wild with them.

Debating Perspectives

Let's explore different sides of [controversial topic]. Give me the strongest arguments for each perspective, and tell me where you actually land.

Code Generation

Write a [language] function that [description].

Requirements:
- [specific requirement 1]
- [specific requirement 2]
- Include error handling
- Add comments explaining the logic

Don't be boring with the explanation—show me the code and tell me what's clever about it.

Model Capabilities Reference

FeatureGrokNotes
Context Window1M+ tokensUltra-long context for documents
Real-Time Knowledge✅ YesVia X (Twitter) access
Web Search✅ YesBuilt-in search capability
Image Analysis✅ YesMultimodal support
Code Execution✅ YesCan run and verify code
Content Filtering⚠️ RelaxedMore permissive than others

See Also

  • references/basics.md - Foundational prompt engineering concepts
  • references/techniques.md - Detailed technique explanations
  • references/patterns.md - Reusable Grok prompt patterns
  • references/examples.md - Concrete examples and templates
  • claude-prompting skill - For Anthropic Claude-specific guidance
  • gemini-prompting skill - For Google Gemini-specific guidance

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.76%
按下载量换算43

Claude

31.19%
按下载量换算40

Cursor

19.78%
按下载量换算25

Gemini CLI

9.76%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills