TypingMindTypingMindThe best frontend for AI
Html Slides logo

Html Slides

Organization
SourceWeft
html-slides

Create and revise offline HTML presentations with Reveal, polished themes, layouts, fragment animation and visual effects. Use for browser-native slides and shareable interactive presentations. PowerPoint files remain the ppt-deck skill's responsibility.

Overview

PublisherSourceWeft
RepositorySourceWeft
Skill namehtml-slides
Stars
305
Forks
25
Bundled files
112
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 112 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SourceWeft on GitHub. Read the source before you install it.

Installation

Install the Html Slides AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SourceWeft/SourceWeft/tree/main/packages/builtin-skill-html-slides
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SourceWeft/SourceWeft.git /tmp/SourceWeft
mkdir -p .claude/skills
cp -r /tmp/SourceWeft/packages/builtin-skill-html-slides .claude/skills/html-slides
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html Slides in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Html Slides on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Html Slides is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HTML presentations

Produce one complete, offline index.html through the existing artifact workflow. The file contains its player, assets, scripts and embedded fonts. Use the selected skill normally; do not introduce a studio, new command or product mode selector.

  1. Plan the story and page roles. Default to 1280×720 / 16:9, support 4:3 on request, 1–40 pages. Body text must be at least 24px in the unscaled design. Reorganize or split dense content.
  2. Read references/design.md and the relevant files from runtime/layouts/ and runtime/themes/. runtime/catalog.json enumerates all 36 themes, 31 layouts, 27 animations and 20 FX; use only real entries. Read effects guidance when needed.
  3. Prepare files in the provider sandbox using existing tools. Confirm SOURCEWEFT_HTML_RUNTIME, SOURCEWEFT_HTML_FONTS and the pinned Node/Python/browser tools exist. A missing runtime is a deployment error: report it; never install a different version, switch fonts or use a CDN to continue.
  4. Create a starter when helpful: node /skills/html-slides/scripts/build.cjs /workspace/draft.html --layout=two-column --starter. Edit its real content with the sandbox tools; add flat section pages with stable data-slide-id. Keep custom assets inside the project directory.
  5. Build: node /skills/html-slides/scripts/build.cjs /workspace/draft.html /workspace/index.html --theme=minimal-white --ratio=16:9. This embeds resources and fonts. The theme and ratio are generation details, not product UI modes.
  6. Run final-file QA: node /skills/html-slides/scripts/qa.cjs /workspace/index.html /workspace/qa. It checks offline loading, actual glyph coverage, page layout, deterministic captures and lifecycle cleanup. Fix reported problems and rebuild. Do not treat a screenshot's existence as QA success.
  7. Use review_html_visuals on every image listed in /workspace/qa/qa.json, in batches of at most 24. Criteria must include readability, hierarchy, balance, content completeness and the intended visual effect. Major/critical issues, missing vision configuration, exceptions or incomplete results block delivery. Review all batches; do not extrapolate one page's pass to the deck.
  8. Publish the exact final file using publish_artifact with artifactType=html, the final expectedContentDigest, and every public image attachment from /workspace/qa/attachments.json. The presentation metadata names these thumbnails; omitting them is an error. Use the first image as optional previewImage for the artifact card. Report the committed artifact/version, page count and actual QA result.

Revisions

Use prepare_sandbox_workspace with {artifactId, sandboxPath:'/workspace/current.html'}. For an explicitly requested history version, also provide artifactVersionId. Keep the returned sourceArtifact.versionNo as the editing baseline; do not guess it or reread a newer number just before publishing.

Resolve “change page 3” by the order of sections in the version you loaded, then edit that section's stable ID. Preserve other page IDs, the presentation metadata and its required image names. Rebuild from the modified full HTML, rerun all required QA, and publish with republishArtifactId and the captured expectedVersionNo. A conflict requires reloading and reconciling edits. The complete HTML is a valid revision source; do not invent a private project file.

Delivery boundaries

All styling, animations, effects and controls live in the file. Reveal is the sole player. The included adapter implements presentation/v1 for optional host controls; a plain iframe and the downloaded file must work without a host handshake. Preview/share read the finished artifact and never load this skill at viewing time.

Source HTML, QA screenshots and process notes may stay in the sandbox or Files for follow-up. Publish the real file; never claim the workspace path itself is a delivered artifact. Do not claim visual checks that were not run.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 52 more files.

Frequently asked questions

What does the Html Slides AI skill do?

Create and revise offline HTML presentations with Reveal, polished themes, layouts, fragment animation and visual effects. Use for browser-native slides and shareable interactive presentations. PowerPoint files remain the ppt-deck skill's responsibility.

Why use Html Slides on TypingMind?

Because you install it once and use it with any model. Html Slides is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Html Slides in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SourceWeft/SourceWeft/tree/main/packages/builtin-skill-html-slides. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Html Slides?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Html Slides?

As many as you like. As long as a model supports skills, you can use Html Slides with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Html Slides AI skill free?

It is published on GitHub by SourceWeft. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Pptx Author

NousResearch
OrganizationPopular

Build PowerPoint decks headless with python-pptx.

53.5K
250.4K
Instructions
View
NousResearch logo

Pokemon Player

NousResearch
OrganizationPopular

Play Pokemon via headless emulator + RAM reads.

53.5K
250.4K
Instructions
View
anthropics logo

Docx

anthropics
OrganizationPopular

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

21.8K
184K
59 files
View
openclaw logo

Openclaw Docker E2e Authoring

openclaw
OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

82.2K
391K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇