Token导航 LogoToken导航TokenDH.com
研究检索执行命令clawhub未标认证来源可访问clear审计通过

text-to-ppt文本转 PPT

Agent Skill

text-to-ppt 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

13,404

周安装

537

GitHub Stars

公开资料未说明

下载量

4,339
OpenClaw

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

MIT-0

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:text-to-ppt(文本转 PPT)
来源仓库:https://github.com/rendylong/text-to-ppt
安装命令:
openclaw skills install text-to-ppt
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install text-to-ppt

简介

将研究报告、摘要或计划等文本自动转换为基于 HTML 的演示文稿。

  • 适用于需要快速生成 PPT 的场景,如汇报准备、方案展示等。
  • 输入任意文本后自动生成结构化幻灯片,保留核心信息与逻辑层次。
  • 安装命令:openclaw skills install text-to-ppt,需确认是否触发文件写入操作。
  • 建议结合原始文档核验内容准确性,避免凭空补字段或修改事实。

SKILL.md

name
text-to-ppt
description
Convert any text input (research reports, summaries, proposals, plans, etc.) into a beautiful HTML-based presentation. Use when the user asks to create a PPT, slides, presentation, deck, or convert text/documents into slides. Also triggers on phrases like "做成PPT", "生成幻灯片", "做个演示文稿", "转成slides", "create presentation", "make slides", "text to presentation". Supports data visualization with Chart.js, Font Awesome icons, and modern design themes.

Text-to-PPT — 文本转 HTML 演示文稿

Convert any text input into a visually stunning, single-file HTML presentation.

CRITICAL: Two-Phase Generation

ALWAYS use the two-phase approach. NEVER generate the full HTML in one shot.

Phase 1: Plan (fast, single call)

Read the input text, then produce a slide-by-slide outline in JSON format:

{
  "title": "Presentation Title",
  "language": "zh-CN",
  "density": "detailed",
  "theme": "dark",
  "slides": [
    {
      "number": 1,
      "type": "title",
      "heading": "Main Title",
      "content": "Subtitle or tagline",
      "layout": "centered",
      "notes": "Visual: large title with accent underline"
    },
    {
      "number": 2,
      "type": "content",
      "heading": "Section Title",
      "points": ["Point 1", "Point 2", "Point 3"],
      "layout": "bullets",
      "hasData": false,
      "notes": "Use numbered badges for each point"
    },
    {
      "number": 3,
      "type": "chart",
      "heading": "Key Metrics",
      "chartType": "bar",
      "chartData": {
        "labels": ["A", "B", "C"],
        "datasets": [{"label": "Sales", "data": [100, 200, 150]}]
      },
      "points": ["Insight 1", "Insight 2"],
      "layout": "split",
      "hasData": true,
      "notes": "Left: chart, Right: insights as stat cards"
    }
  ]
}

Rules for Phase 1:

  • Output ONLY the JSON plan. No HTML. No explanation.
  • Identify data points → mark hasData: true and provide chartType + chartData
  • Choose layout: centered, bullets, split, grid, timeline, cards, fullchart, quote
  • Target 8-15 slides. Never exceed 20.
  • This should take <10 seconds.

Phase 2: Generate (parallel, page-by-page)

Read references/design-system.md — this is where the full design spec lives.

Then generate HTML for each slide independently. Each slide is a self-contained <div class="slide"> block.

For each slide, the agent should:

  1. Take ONE slide from the plan (by number)
  2. Read only the design system reference if not already loaded
  3. Generate ONLY that one slide's HTML <div class="slide">...</div>
  4. No <html>, no <head>, no <body> — just the slide div

BATCHING: Generate slides in parallel using sub-agents. Spawn up to 5 sub-agents simultaneously, each generating 1-2 slides.

Phase 3: Assemble

After all slides are generated:

  1. Read the shell template from references/shell-template.html
  2. Insert all slide divs into the shell
  3. Ensure chart canvas IDs are unique across all slides
  4. Save to Obsidian vault: ~/Documents/longhai/Longhai/
  5. Tell user the file path

Execution Strategy

When running as the main agent:

  1. Phase 1 yourself (fast, just JSON)
  2. Write the plan to a temp file
  3. Spawn sub-agents for Phase 2 (parallel slide generation)
  4. Collect results and assemble in Phase 3

Sub-agent task format (for Phase 2):

Generate HTML for slide {N} of a presentation.

SLIDE PLAN:
{JSON for this specific slide}

DESIGN SYSTEM: Read references/design-system.md for theme colors, components, and rules.

OUTPUT: Return ONLY a single <div class="slide" style="background-color: #0f172a;">...</div> block.
No <html>, <head>, or <body> tags. Use inline styles. Include <script> for Chart.js if this slide has charts.
Use unique canvas ID: chart-slide{N}-{random}.

Input Sources

  • Directly pasted text
  • A file path — read it first with read
  • A URL — fetch it first with web_fetch
  • An Obsidian note path — read it first

Output

  • Single self-contained HTML file
  • File naming: {topic-slug}.presentation.html
  • Default save location: ~/Documents/longhai/Longhai/
  • Tell the user the file path

Theme Options

ThemeBackgroundTextCardsAccent
dark (default)slate-900slate-50slate-800blue-500/amber-500
lightslate-50slate-900whiteblue-600/amber-600
techgray-950emerald-50gray-900cyan-500/violet-500
warmstone-900amber-50stone-800orange-500/rose-500

User can specify a theme. Default: dark.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenClaw

81.82%
按下载量换算3,550

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install text-to-ppt 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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