agentleFS
moewu325-huemoewu325-hue/html-ppt/SKILL.md

html-ppt

Skill2 starsChanged 22 days agoMITView on GitHub

Use when creating or editing HTML browser presentations, standalone slides, React decks, or data narrative presentations. 浏览器PPT、HTML幻灯片、数据可视化演示。

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the chosen mode and quality checks.

    line 25
  2. Distinctive:

    Default standalone is offline only while all resources are embedded/local.

    line 27
  3. Distinctive:

    Test keyboard, wheel, touch/buttons, first/last controls and all slides at 1920×1080, 1366×768, 1024×768 and 375×812.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HTML PPT | 浏览器演示文稿

Create a browser presentation from the user's content, style, page count and interaction needs. Preserve supplied facts and choices. Treat an already complete brief as authorization to build; ask only for missing decisions that materially affect the result. Do not invent data or add mandatory approval rounds. 依据已有内容、风格、页数与交互生成演示;材料充分就直接实施,只追问影响实现的缺项。

Choose the mode | 模式路由

RequestReadDeliver
Simple deck, normally ≤8 slides, no complex animationStandalone guideCopy/adapt HTML template; one zero-dependency HTML
>8 slides, complex motion or explicit React requirementReact/Vite guideVite + React + Tailwind + Motion project, lockfile, build/preview
Chart/image-heavy report, pitch or explicit data narrativeData narrative, then appropriate implementation guide≤8 simple slides: enhanced HTML; >8/complex motion/React: React project

Data narrative is a content/layout mode: retain eight layout skeletons, chart insights and image roles. Do not force it into the five default slide types or force React merely to vary layouts. Preserve user aesthetic choices; CSS variables are configurable, not a required theme.

Explicit .pptx requests go to an available presentation-authoring tool/skill; use python-pptx only if installed and suitable. python-docx creates Word documents, not PowerPoint. If unavailable, explain the format limitation rather than renaming HTML to .pptx. Existing complete designs can skip animation design.

Build and verify | 实施与核验

  1. Read the chosen mode and quality checks. Keep content density and font limits, splitting or reflowing when needed without losing facts.
  2. For standalone output copy the actual asset, update slidesData and theme. Use python scripts/build_demo.py output.html for the reproducible offline example. Text fields are plain text; preserve escaping. Embed JSON safely (< as \u003c) when generating data inside script tags.
  3. Default standalone is offline only while all resources are embedded/local. CDN charts, placeholder services, remote fonts and external images need network; disclose and list replacements. Avoid adding remote assets to an offline brief.
  4. Test keyboard, wheel, touch/buttons, first/last controls and all slides at 1920×1080, 1366×768, 1024×768 and 375×812. Check clipping, text ≥11px, console errors, image loading and reduced motion. Test the actual generated artifact, not a separate mockup.
  5. Report output path, run/open instructions, placeholder list and validation actually performed. For React run build and preview; do not claim an unexecuted check passed.

Maintainers: README, release procedure, provenance.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.