Custom Theme

Q: Why use Custom Theme on TypingMind?

Because you install it once and use it with any model. Custom Theme 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.

Q: How do I install Custom Theme in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xuzhougeng/wisp-science/tree/main/skills/custom-theme. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Custom Theme?

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.

Q: How many AI models can I use with Custom Theme?

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

Q: Is the Custom Theme AI skill free?

Yes. It is published on GitHub by xuzhougeng under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

CommunityPopular

xuzhougeng

custom-theme

Author a Wisp custom theme CSS file that uses documented tokens and import constraints. Use when the user wants a custom look, hide the paragraph lead bar, restyle chat Markdown, override colors, or import a stylesheet under Settings → Appearance.

Overview

Publisher	xuzhougeng
Repository	`wisp-science`
Skill name	`custom-theme`
Stars	1K
Forks	104
Bundled files	Instructions only
License	AGPL-3.0
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by xuzhougeng on GitHub. Read the source before you install it.

Installation

Install the Custom Theme 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/xuzhougeng/wisp-science/tree/main/skills/custom-theme
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/xuzhougeng/wisp-science.git /tmp/wisp-science
mkdir -p .claude/skills
cp -r /tmp/wisp-science/skills/custom-theme .claude/skills/custom-theme

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

Use it in TypingMind

Enable Custom Theme 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 Custom Theme 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 Custom Theme 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.

Custom Wisp theme CSS

Wisp injects one user stylesheet after the built-in theme. Prefer CSS variables on :root. Do not invent Settings toggles for one-off look changes.

Workflow

Ask what should change (lead bar, table size, accent, chat density, fonts).
Write a .css file in the project, usually theme.css.
Apply it:
- Desktop: configure with action=set and values.custom_css set to the full stylesheet text. Empty string clears it.
- Or tell the user to import the file under Settings → Appearance.
Confirm the change is visible. If a rule did nothing, the selector is wrong; do not add !important unless a built-in rule requires it.

Constraints

The host sanitizes CSS before inject. These are stripped:

@import and @namespace
every url(...)
javascript:, expression(, behavior:, -moz-binding
</style and <script
NULs; payload longer than 64 KB is truncated

Do not rely on remote fonts, images, or other stylesheets. Name an installed font with configure ui_font_family / code_font_family instead.

Scope light/dark overrides with :root[data-theme="light"] and :root[data-theme="dark"]. System theme follows the OS, so also cover :root[data-theme="system"] when the user cares about both.

Tokens

Override these on :root. Leave unused tokens alone.

Token	Default role
`--bg-app`, `--bg-elev`, `--bg-sunken`, `--bg-input`, `--bg-panel`	Surfaces
`--text`, `--text-muted`, `--text-faint`	Ink
`--border`, `--border-strong`	Hairlines
`--clay`, `--clay-strong`, `--clay-soft`, `--on-clay`	Accent (teal)
`--ui-font-size`, `--code-font-size`	Set by Appearance sliders; do not hard-code px on chat body
`--md-table-font-size`	Markdown tables; default `calc(var(--ui-font-size, 14px) - 1px)`
`--md-lead-bar-width`, `--md-lead-bar-pad`	Bold-at-start emphasis bar; `3px` / `0.55em`
`--font-user-ui`, `--font-user-mono`	Optional family names; empty restores the stack
`--radius`, `--radius-sm`, `--radius-xs`	Corners

Palette attributes (data-light-palette, data-dark-palette) already map onto the semantic tokens. Prefer --clay / --bg-app over palette internals (--lp-*, --dp-*) unless the user asked to restyle one palette only.

Common requests

Hide the lead bar (the vertical mark before a paragraph that starts with bold):

css
:root {
  --md-lead-bar-width: 0;
  --md-lead-bar-pad: 0;
}

Keep tables aligned with UI size, or pin a size:

css
:root { --md-table-font-size: calc(var(--ui-font-size, 14px) - 1px); }

css
:root { --md-table-font-size: 14px; }

Quiet chat chrome:

css
.msg.assistant .role { display: none; }
.msg.assistant .body.md { letter-spacing: 0; }

Do not restyle window controls, settings forms, or tool-approval cards unless the user asked. Keep contrast readable on both themes.

Apply via configure

json
{
  "action": "set",
  "values": {
    "custom_css": ":root { --md-lead-bar-width: 0; --md-lead-bar-pad: 0; }\n"
  }
}

After writing theme.css, read it and pass the exact file contents. Do not summarize or wrap the CSS in Markdown fences inside custom_css.

Frequently asked questions

What does the Custom Theme AI skill do?

Why use Custom Theme on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xuzhougeng/wisp-science/tree/main/skills/custom-theme. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Custom Theme?

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 Custom Theme?

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

Is the Custom Theme AI skill free?

Yes. It is published on GitHub by xuzhougeng under the AGPL-3.0 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

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Custom Wisp theme CSS

Workflow

Constraints

Tokens

Common requests

Apply via configure

Frequently asked questions

Related AI Skills

Set up your own AI workspace now