Html

Organization

SourceWeft

html

Create and revise polished self-contained HTML reports, landing pages, infographics and local interactive visualizations with responsive layout and final-file QA. Use the separate html-slides skill for paginated browser presentations.

Overview

Publisher	SourceWeft
Repository	`SourceWeft`
Skill name	`html`
Stars	305
Forks	25
Bundled files	9
Links	Skill source Repository Homepage

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/SourceWeft/SourceWeft/tree/main/packages/builtin-skill-html
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.

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 .claude/skills/html

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html 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 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 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 pages

Create a complete offline index.html with semantic HTML, intentional typography, responsive layout and browser-local interactions. Use the existing artifact workflow and skill selection; no new product entry or mode selector.

Establish the audience, information hierarchy and expected interactions. Read references/page-design.md and references/quality.md.
Author a full UTF-8 document with an early charset declaration and viewport meta. Use normal document flow. Keep source, images and local scripts together in a sandbox project directory. Do not add Reveal, slide IDs, fixed presentation canvases or presentation font-size rules.
Confirm the provisioned SOURCEWEFT_HTML_RUNTIME and SOURCEWEFT_HTML_FONTS exist. Missing tooling, fonts or required model configuration must be reported; do not substitute runtime dependencies, system fonts or CDN assets.
Bundle the final document with node /skills/html/scripts/build.cjs /workspace/draft.html /workspace/index.html. Assets and selected fonts become part of the file. Use embedded font families from the provisioned catalog, or explicitly provision authorized custom fonts with their hashes and license information. Keep Canvas/SVG typography consistent with embedded fonts.
Run node /skills/html/scripts/qa.cjs /workspace/index.html /workspace/qa. Default viewports are 1440×900, 768×1024 and 390×844; inspect the whole page, including its tail. Interactive pages must supply a local interaction-checks.cjs module as the third argument. It exports an async function(page), asserts the requested behavior using the existing Playwright API, and returns true only after all checks pass. These are ordinary project tests, not a new platform protocol.
Before publishing, run review_html_visuals with task-specific criteria against every image path listed in the QA qa.json images array (in batches of at most 24). QA slices each viewport's full page into parts no taller than 2,000 px, so a long page has several images per viewport; review all of them. Never pass a hand-made full-page screenshot: a result naming an image with unsupported dimensions means rerunning QA to obtain slices, not skipping the review. Major visual defects, missing content, failed interactions, unavailable models and incomplete QA block delivery. Rebuild and recheck after any change.
Publish with artifactType=html, the actual final source file and the QA expectedContentDigest. An optional preview image can come from successful QA. Report only completed checks and the committed artifact/version.

Revisions

Load the artifact through prepare_sandbox_workspace, specifying its artifact ID and a sandbox destination. Retain the returned sourceArtifact.versionNo; pass an explicit artifactVersionId when the user selected a historical version. Modify the relevant sections or functionality, rebuild, rerun QA and publish with republishArtifactId plus the captured expectedVersionNo. Do not silently overwrite a concurrent revision.

Local execution

Use browser-local computation and state. The iframe has an opaque origin and cannot use the host's cookies or persistent storage. External services, login flows and multi-file website hosting need a separately agreed scope. The file must retain its content and interactions after this generating skill is disabled.

Bundled files

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

Frequently asked questions

What does the Html AI skill do?

Why use Html on TypingMind?

Because you install it once and use it with any model. Html 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 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SourceWeft/SourceWeft/tree/main/packages/builtin-skill-html. 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?

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?

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

Is the Html 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.

View all

Grilling

mattpocock

CommunityPopular

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Api Design

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Accessibility

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

HTML pages

Revisions

Local execution

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now