Static Sites

OrganizationPopular

bionic-gpt

static-sites

Create or modify Bionic's generated marketing site, documentation, blog, course pages, and static assets. Use for content, layouts, summaries, Tailwind, or ssg_whiz changes under crates/bionic-gpt.

Overview

Publisher	bionic-gpt
Repository	`bionic-gpt`
Skill name	`static-sites`
Stars	2.4K
Forks	247
Bundled files	4
License	Apache-2.0
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.
4 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by bionic-gpt on GitHub. Read the source before you install it.

Installation

Install the Static Sites 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/bionic-gpt/bionic-gpt/tree/main/.agents/skills/static-sites
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/bionic-gpt/bionic-gpt.git /tmp/bionic-gpt
mkdir -p .claude/skills
cp -r /tmp/bionic-gpt/.agents/skills/static-sites .claude/skills/static-sites

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

Use it in TypingMind

Enable Static Sites 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 Static Sites 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 Static Sites 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.

Static Sites

The current static site is crates/bionic-gpt

Content and Rendering

Marketing pages are under crates/bionic-gpt/content/pages.
Blog content is under crates/bionic-gpt/content/blog and is registered through src/blog_summary.rs.
Documentation is under content/docs and is registered through src/docs_summary.rs.
Course content is under content/architect-course and is registered through src/architect_course_summary.rs.
Shared layouts and site configuration are under crates/bionic-gpt/src.
crates/bionic-gpt/build.rs generates course page source where required before ssg_whiz renders the site.

Preserve the existing ssg_whiz summary and layout conventions. Keep visible images, Open Graph images, metadata, canonical links, navigation, and footer behavior distinct where the code supports those concepts.

Marketing Visual System

Marketing typography is defined in crates/bionic-gpt/input.css. HTML heading levels provide the standard type hierarchy: h1 is the page or hero heading, h2 is a section heading, and h3 is a feature, card, or subsection heading. The site inherits Tailwind's --default-font-family, currently its system sans stack. Eyebrow text uses the semantic .site-eyebrow class.

The homepage use-case river has named art-direction treatments for its intro and feature headings: .use-case-river__heading--intro and .use-case-river__heading--copy. These styles live alongside the global heading rules in the marketing stylesheet.

Shared CSS owns recurring typography. DaisyUI provides themed controls such as buttons and semantic colors such as base-content and primary. Component Tailwind classes describe composition and geometry, including grids, flex layouts, spacing, alignment, and image sizing.

Blog Articles

For a new blog article, read references/new-blog-article.md before editing. It defines the content, summary metadata, hero-image, and Open Graph workflow.

Use the bundled Open Graph helper to create the social-preview image from the article hero:

bash
cargo run --quiet --manifest-path .agents/skills/static-sites/scripts/prepare-open-graph/Cargo.toml -- <hero-image> <article-folder>/open-graph.jpg

The helper creates an exact 1200x630 JPEG and adapts quality until the file is below the site's 490,000-byte limit.

Assets and Commands

Static application assets are maintained in crates/web-assets; its Tailwind input is crates/web-assets/input.css, and its TypeScript entry is crates/web-assets/index.ts. The site-specific Tailwind input is in crates/bionic-gpt/input.css.

crates/web-assets/build.rs uses cache-busters to generate typed references for files in dist/ and images/; application code should use those generated references rather than hard-coded hashed asset paths.

Verified development recipes are:

bash
just ws
just wts

The ws recipe watches crates/bionic-gpt/content and src; wts watches the site's Tailwind input. Inspect Justfile before using other recipes.

Verification

bash
(cd crates/bionic-gpt && DO_NOT_RUN_SERVER=1 cargo run -p bionic-gpt)
cargo build -p bionic-gpt

Run the site generator from crates/bionic-gpt so its dist/ output lands in the site crate's ignored build directory, not the workspace root. Inspect the generated HTML for metadata, links, and asset paths. Run git diff --check.

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 Static Sites AI skill do?

Create or modify Bionic's generated marketing site, documentation, blog, course pages, and static assets. Use for content, layouts, summaries, Tailwind, or ssg_whiz changes under crates/bionic-gpt.

Why use Static Sites on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bionic-gpt/bionic-gpt/tree/main/.agents/skills/static-sites. 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 Static Sites?

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 Static Sites?

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

Is the Static Sites AI skill free?

Yes. It is published on GitHub by bionic-gpt under the Apache-2.0 license. 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

Control Ui E2e

openclaw

OrganizationPopular

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Discrawl

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Static Sites

Content and Rendering

Marketing Visual System

Blog Articles

Assets and Commands

Verification

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now