A curated directory of 141 AI slide generation skills (including 26 manually reviewed) with live star counts and route-based comparisons to help users choose the right tool.

Stars

5

7-day growth

No data

Forks

0

Open issues

0

License

NOASSERTION

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It is the largest public catalog of this emerging skill category, offering objective head-to-head comparisons based on actual capabilities and delivery routes rather than star counts alone.

Who it is for

  • Developers building slide generation workflows
  • Presenters who need to choose a skill for their content
  • Technical writers and product managers evaluating documentation-to-slide tools
  • Enterprise teams needing editable PPTX outputs

Use cases

  • Selecting a slide skill for a specific content type (code, charts, formal reports)
  • Comparing HTML vs PPTX routes before committing to a toolchain
  • Using the gallery to visually preview output styles and then generate a deck in 60 seconds
  • Cross-referencing skill capabilities (export formats, animations, speaker notes) from a single page

Strengths

  • Comprehensive coverage of the landscape with live data refresh
  • Evidence-based comparison tables (capabilities, licenses, routes) drawn from each project's own documentation
  • Practical installation guide with concrete style IDs and three-step workflow
  • Includes a decision tree and a registry sorted by star tiers for quick scanning

Considerations

  • All capability claims are taken from each project's SKILL.md/README, not from actual test runs
  • About half of the listed projects (79 out of 141) are auto-discovered and lack manually verified installation commands
  • The gallery shows curated sample images from each project, not a same-content benchmark

README quick start

many-ppt-skills

值得知道的 AI 幻灯片 Skill 全在这一页,并排对比 —— 让你挑对一个,然后接着干活。

图库里看中哪张,照 60 秒做出同款 三步走,就能做出你自己的那一份。

简体中文 · English

收录 141 个 skill,其中 26 个人工读过 · 合计 271,212 star · HTML 路线 55 个 · PPTX 路线 49 个 · 双路线 13 个 · 数据刷新于 2026-07-29


Coding Agent 把 CSS 写好了,半年之内冒出一整个新品类:把文档变成不像机器做的幻灯片的 Skill。这一页收录了 141 个,其中四个 star 数都超过 2 万。

而所有关于它们的排名,都只是 star 数的重新排序。star 衡量的是作者会不会发推,不能告诉你 哪一个能处理好你的代码块,也不能告诉你财务总监能不能编辑第 12 页。

这个仓库就是用一页纸回答这件事:

  1. 全部收齐 —— 两条路线值得知道的 skill 都在,带实时数据。由 data/skills.json 自动生成,数字不会悄悄烂掉。
  2. 按真正决定选择的点来对比 —— 先回答路线问题,再看每个到底 适合干什么。都是你能自己核对的事实,不是我编的分数。
  3. 八条原则 —— 从这些项目源码里提炼,30 个团队各自独立收敛到的同一批做法, 这是这个领域目前最接近「证据」的东西。

挑一个、装上、继续干活。这就是全部意图。


60 秒做出同款

先看图库,看中一张图之后照这三步走。下面用一个真实例子从头走一遍。

第一步:从图注里抄下风格 ID。 每张图下面都有一行说明,长这样:

Soft Editorial · 4 · soft-editorial · screenshots/soft-editorial-4.png

等宽字体的 soft-editorial 就是风格 ID —— 抄它。它属于哪个 skill,看这组图上方的标题 (这里是 Frontend Slides)。

第二步:装这个 skill。 命令就印在那组图上面,直接复制。这个例子里是 plugin 方式, 两条命令都在 Claude Code 里面敲,不是终端

/plugin marketplace add https://github.com/zarazhangrui/frontend-slides
/plugin install frontend-slides@frontend-slides

一共有五种安装方式,含义不同(clone 是克隆进 ~/.claude/skills/ 并需要重开会话, python 要本机装依赖,npx 是建项目而不是装 skill)。对照表在 看中一张图,怎么做出来

第三步:把风格 ID 写进你的话里。 它不是命令行参数,就是提示词的一部分:

用 soft-editorial 这个模板,把 docs/roadmap.md 做成一份 12 页的 deck,
面向投资人,我会现场讲,所以每页字少一点。

就这样。点名风格 ID 等于跳过挑选环节 —— frontend-slides 默认会先生成 3 个预览让你选, 你直接点名就是告诉它别问了,照这个做。想看选项就别点名,直接说「帮我做一份关于 X 的 deck」。

不想自己翻这一页?下一节把这个仓库本身装成 skill,让 agent 替你选。


让 agent 直接帮你挑

这个仓库本身也是一个 skill。装上之后,你不用自己翻这一页 —— 直接说「我要做一份给投资人的 deck」,它会先问路线问题,再给出具体的 skill、安装命令和风格 ID。

# 作为 Claude Code 插件
/plugin marketplace add https://github.com/brycewang-stanford/many-ppt-skills
/plugin install many-ppt-skills@many-ppt-skills

# 或者直接克隆成个人 skill
git clone https://github.com/brycewang-stanford/many-ppt-skills ~/.claude/skills/many-ppt-skills

背后是一个命令行查询层,你也可以自己用:

python scripts/pick.py route                  # 路线问题 + 各路线数量
python scripts/pick.py list --route pptx      # 某条路线下的 skill
python scripts/pick.py show ppt-master        # 安装命

Description

Every AI slide-deck skill worth knowing, on one page — both the HTML and native-PPTX routes, compared on what actually decides the choice rather than on star count. Bilingual, auto-refreshed.

Related repositories

Similar projects matched by category, topics, and programming language.

0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

ponytail-improved

Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.

AI & Machine LearningAI Agents
545
0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models
577
yetone
Featured
yetone GitHub avatar

kill-ai-slop

Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.

AI & Machine LearningAI Agents
805