Token导航 LogoToken导航TokenDH.com
运维和基础设施需要联网github未标认证来源可访问许可证需确认审计通过

ai-slidesAI 幻灯片

Agent Skill

ai-slides 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

16,488

周安装

701

GitHub Stars

89

下载量

5,776
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:ai-slides(AI 幻灯片)
来源仓库:https://github.com/claude-office-skills/skills
仓库路径:skills/ai-slides
安装命令:
npx skills add https://github.com/claude-office-skills/skills --skill ai-slides
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/claude-office-skills/skills --skill ai-slides

简介

记录任务执行中的错误与经验,辅助生成结构化演示文稿。

  • 支持 Docker 最佳实践展示与幻灯片制作规范指导。
  • 可结合 Marp、Slidev 或 reveal.js 渲染 Markdown 格式的 PPT。
  • 适用于知识沉淀与团队分享场景,提升协作效率。ai-slides 属于运维和基础设施类 Skill,可作为该场景下的辅助能力补充。
  • 需注意内容准确性,避免将临时结论写入正式文档。

SKILL.md

AI Slides Skill

Overview

This skill enables AI-powered presentation generation. Provide a topic or outline, and get a complete, polished presentation with proper structure, content, and formatting.

How to Use

  1. Provide a topic, outline, or rough notes
  2. Specify audience and presentation length
  3. I'll generate a complete presentation

Example prompts:

  • "Create a 10-slide presentation about machine learning"
  • "Generate a pitch deck for a SaaS startup"
  • "Build training slides on cybersecurity basics"
  • "Make a quarterly review presentation from this data"

Domain Knowledge

Presentation Structure

# Effective presentation structure
structure:
  - title_slide:
      title: "Clear, compelling title"
      subtitle: "Context or tagline"
      author: "Presenter name"

  - agenda:
      items: 3-5 main topics

  - introduction:
      hook: "Attention-grabbing opening"
      context: "Why this matters"

  - main_content:
      sections: 3-5 key points
      each_section:
        - heading
        - 3-5 bullets or visual
        - supporting data

  - conclusion:
      summary: "Key takeaways"
      call_to_action: "What to do next"

  - closing:
      thank_you: true
      contact_info: true
      qa_prompt: true

Content Generation Pattern

def generate_presentation(topic, audience, slide_count=10):
    """AI-powered presentation generation."""

    # 1. Generate outline
    outline = generate_outline(topic, slide_count)

    # 2. Expand each section
    slides = []
    for section in outline:
        slide_content = expand_section(section, audience)
        slides.append(slide_content)

    # 3. Add visuals suggestions
    for slide in slides:
        slide['visuals'] = suggest_visuals(slide['content'])

    # 4. Format as Marp markdown
    presentation = format_as_marp(slides)

    return presentation

def generate_outline(topic, count):
    """Generate presentation outline."""
    # Typical structure
    outline = [
        {'type': 'title', 'title': topic},
        {'type': 'agenda'},
        # Main content (60% of slides)
        # ... content slides
        {'type': 'summary'},
        {'type': 'closing'}
    ]
    return outline

Marp Output

def format_as_marp(slides):
    """Convert slides to Marp markdown."""

    marp = """---
marp: true
theme: gaia
paginate: true
---

"""

    for slide in slides:
        if slide['type'] == 'title':
            marp += f"""<!-- _class: lead -->

# {slide['title']}

{slide.get('subtitle', '')}

---

"""
        elif slide['type'] == 'content':
            marp += f"""# {slide['heading']}

"""
            for point in slide['points']:
                marp += f"- {point}\n"
            marp += "\n---\n\n"

    return marp

Example: Generate Tech Talk

topic = "Introduction to Docker"
audience = "Developers new to containers"
slides = 10

# Generated presentation
presentation = """---
marp: true
theme: gaia
paginate: true
---

<!-- _class: lead -->

# Introduction to Docker

Containerization Made Simple

---

# Agenda

1. What is Docker?
2. Core Concepts
3. Getting Started
4. Best Practices
5. Demo

---

# What is Docker?

- Container platform for packaging applications
- Lightweight alternative to VMs
- "Build once, run anywhere"
- 15M+ developers, 7M+ applications

---

# Why Containers?

| VMs | Containers |
|-----|------------|
| GB size | MB size |
| Minutes to start | Seconds to start |
| Full OS | Shared kernel |

---

# Core Concepts

- **Image**: Blueprint/template
- **Container**: Running instance
- **Dockerfile**: Build instructions
- **Registry**: Image storage (Docker Hub)

---

# Getting Started

Pull an image

docker pull nginx

Run a container

docker run -p 8080:80 nginx

List containers

docker ps


---

# Your First Dockerfile

FROM node:18 WORKDIR /app COPY package*.json ./ RUN npm install COPY . . EXPOSE 3000 CMD ["npm", "start"]


---

# Best Practices

- Use official base images
- Minimize layers
- Don't run as root
- Use.dockerignore
- Multi-stage builds

---

# Summary

✅ Docker simplifies deployment ✅ Containers are lightweight & fast ✅ Easy to get started ✅ Industry standard

---

# Questions?

Resources: docs.docker.com """

Best Practices

  1. Know Your Audience: Tailor complexity and examples
  2. One Idea Per Slide: Keep focused
  3. 6x6 Rule: Max 6 bullets, 6 words each
  4. Visual First: Suggest images/diagrams
  5. Strong Opening/Closing: Hook and call-to-action

Resources

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

33.81%
按下载量换算1,953

Claude

29.35%
按下载量换算1,695

Cursor

18.01%
按下载量换算1,040

Gemini CLI

10.18%
按下载量换算588

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。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