agentleFS
YiShu5YiShu5/claude-skills/skills/HTMLPPT.skill/SKILL.md

HTMLPPT.skill

Skill131 starsChanged 54 days agoMITView on GitHub

Build or extend a runnable multi-slide HTML presentation from an existing Hero visual system or frontend project. Use for HTML slide decks and presentation-style pages; use HTMLHero.skill when the first-screen Hero is the missing foundation.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user wants multiple presentation pages, a slide deck, or a presentation-style HTML experience.

    line 12
  2. Very specific:

    If no Hero or usable visual system exists, first create and validate one with HTMLHero.skill, then extend it.

    line 13
  3. Distinctive:

    Read references/validation.md, then build, preview, inspect every slide at the target ratio, and fix issues before delivery.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

HTMLPPT.skill

Turn an established Hero or frontend project into a coherent, runnable HTML slide deck. Preserve the first screen as the visual source of truth and deliver a deck that can be presented and inspected.

Route

  • Use when the user wants multiple presentation pages, a slide deck, or a presentation-style HTML experience.
  • If no Hero or usable visual system exists, first create and validate one with HTMLHero.skill, then extend it.
  • A true .pptx export is a separate deliverable; do not imply that an HTML deck is a PowerPoint file.

Workflow

  1. Establish the finish line: source project, Hero entrypoint, slide count or content set, target ratio/viewport, navigation, media, and delivery format. Inspect only relevant files, AGENTS.md, package.json, lockfile, entrypoints, and assets.
  2. Resolve a compact deck contract. Read references/deck-contract.md when page data, navigation, or delivery decisions need to be made. Missing final copy becomes a labeled placeholder; do not invent claims or metrics.
  3. Apply constraints in this order: user request, existing Hero/design system, project conventions, then skill defaults. Proceed on reversible assumptions when the user has requested implementation. Ask only for a material ambiguity or an external/irreversible action, unless the user explicitly requested an alignment gate.
  4. Implement in the existing stack. Reuse the Hero’s tokens, components, typography, media treatment, and motion language; add shared components only when they reduce real repetition. Keep slide content concise enough to present and keep unrelated dirty work intact.
  5. Provide presentation behavior appropriate to the request: semantic slide sections, visible focus, keyboard navigation and hash/deep links when navigation is requested, responsive fallback, and reduced-motion behavior. Do not add decorative animation that competes with the content.
  6. Read references/validation.md, then build, preview, inspect every slide at the target ratio, and fix issues before delivery.

Completion and delivery

A task is complete when every requested slide renders, the Hero-derived visual system remains coherent, the requested navigation works, and build/preview plus target-viewport inspection have passed or have concrete blockers documented. Continue through fixes instead of stopping after a first draft for routine review.

Report changed files, actual commands and results, preview URL or entrypoint, slide/interaction checks, assumptions and fallbacks, and any known blocker. Create a zip or convert to .pptx only when requested, and clearly label the artifact type.

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.