Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Wan-Video/Wan-skillsnpx agentmods add skills/wan-video/wan-skills/wan-pptx-generatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wan-video/wan-skills/wan-pptx-generator)<a href="https://agentmods.dev/skills/wan-video/wan-skills/wan-pptx-generator"><img src="https://agentmods.dev/badge/skills/wan-video/wan-skills/wan-pptx-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wan-video/wan-skills/wan-pptx-generator"><img src="https://agentmods.dev/badge/skills/wan-video/wan-skills/wan-pptx-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00231 | $0.02286 |
| Opus 5 | $0.00115 | $0.01143 |
| Sonnet 5 | $0.00046 | $0.00457 |
| Haiku 4.5 | $0.00023 | $0.00229 |
Grade A, and why
wan-pptx-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wan PPT Generator（图片PPT 生成技能）
使用qwen-doc-turbo，通过直接 API 调用生成 AI 驱动的 PPT 幻灯片图片，背后调度wan2.7-image模型。
Quick Start
1. 配置环境变量 DASHSCOPE_API_KEY
2. 了解能力 → 阅读下文核心能力介绍
3. 准备输入 → 文件路径或文本内容二选一
4. 运行脚本 → scripts/pptx_generator.py
核心能力：
- ✅ 文档转 PPT：直接传入文件，自动解析并生成幻灯片
- ✅ 文本转 PPT：根据文字内容或主题描述生成演示文稿
- ✅ 风格化生成：支持指定视觉风格与叙事风格
- ✅ AI 图片渲染：每页幻灯片由 Wan2.7-Image 模型生成高质量配图
🎉 限时优惠：当前通过 qwen-doc-turbo 调用 Wan2.7-Image 图片生成限时免费，仅计算文本 Token 费用，欢迎体验！
环境变量配置
使用前需设置 DashScope API Key：
获取 API Key：
- 访问阿里云百炼控制台：https://bailian.console.aliyun.com/
- 登录后在 API Key 管理页面创建或获取您的 API Key
运行脚本前，请先检查 DASHSCOPE_API_KEY 是否已在环境配置
风格选择引导
如果用户已经明确说了风格，跳过此菜单直接生成。
当用户没有指定风格，或者说"帮我选一个"、"你来决定"、"有什么风格"时， 主动展示风格菜单供用户选择，格式如下：
🎨 请选择您喜欢的 PPT 风格：
🎌 日漫 / 动漫风
哆啦A梦 / 宫崎骏 / 鸟山明 / 龙珠 / 火影忍者 / 海贼王 / 鬼灭之刃 死神 / 灌篮高手 / 一拳超人 / 美少女战士 / 樱桃小丸子 / 银魂 圣斗士 / 阿童木 / 蜡笔小新 / JOJO的奇妙冒险 / 罗小黑 / 3渲2
🦸 欧美漫画风
漫威 / DC / 蝙蝠侠 / X战警 / 罪恶之城 / 地狱男爵 / 美式漫画
🇨🇳 中国风 / 国漫
新中式国潮 / 水墨风 / 敦煌风 / 工笔画 / 浮世绘 / 剪纸风 三毛流浪记 / 老夫子 / 朱德庸 / 镖人 / 风云雄霸天下
🎮 游戏 / 像素风
原神 / 塞尔达 / 我的世界(Minecraft) / 赛博朋克 / 街机 / 像素风 低面建模 / 积木风 / 2.5D / 3D
✏️ 插画 / 设计风
MBE插画 / 扁平化 / 波普艺术 / 孟菲斯 / 包豪斯 / 苹果设计 材质设计 / 新拟物 / 黏土拟物 / 手绘 / 草图 / 文具手帐
🖼️ 艺术 / 绘画风
油画 / 水彩 / 版画 / 木刻 / 彩绘玻璃 / 超写实 / 超现实 梵高 / 莫奈 / 达芬奇 / 蒙德里安 / 立体主义 / 欧普艺术
🌈 潮流 / 特效风
蒸汽波 / 蒸汽朋克 / 赛璐璐 / 酸性设计 / 故障美学 / 科技未来 哥特风 / 重工业 / 定格动画
📸 复古 / 生活风
胶片复古 / 做旧风 / 怀旧风 / 北欧风 / 奶油风 / 和风侘寂 韦斯安德森 / 宜家 / 维多利亚 / 新艺术 / 大字报 / 杂志排版
🎤 演讲 / 商务风
TED风
直接回复风格名称即可，或者"日漫里选一个最适合的"，如果您无法选择，我将自行为您选择最合适的风格制作PPT。
Workflow：PPT 生成流程
- 判断输入类型 - 根据用户提供的是文件还是文本，选择对应输入方式
- 调用生成脚本 - 调用
scripts/pptx_generator.py，传入内容、查询指令和输出目录 - 生成脚本会实时保存结果：
- 收到大纲 → 保存为
content.md - 收到每页图片 URL → 逐页下载保存为
1.jpg、2.jpg... - 收到 PPTX 下载链接 → 下载保存为
presentation_{timestamp}.pptx
- 收到大纲 → 保存为
- 展示结果 - 在用户交互界面中显示页面图片预览
- 提示保存 - 告知用户图片链接有效期为 24 小时，建议指定目录长期保存
Command Line Arguments（命令行参数）
| 参数 | 简写 | 必填 | 说明 |
|---|---|---|---|
| --content | -c | 否* | PPT 文本内容 |
| --file | -f | 否* | 输入文件路径（支持 pdf、docx、txt、md 等） |
| --query | -q | 是 | 风格与需求描述，如"用哆啦A梦视觉风格和 TED 叙事风格生成 PPT" |
| --mode | -m | 否 | 生成模式，默认为 creative |
| --output-dir | -o | 否 | 输出目录，指定后自动保存大纲、页面图片和 PPTX 文件 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 164 lines · 231 tokens per session scan A 9c75d7f4005c
wan-pptx-generator is a skill published in the GitHub repository Wan-Video/Wan-skills (76 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 231 tokens to every session and 2,286 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.