HuskarUI logo

HuskarUI

Community
mengps
HuskarUI

Queries HuskarUI metadata with Python and guides HuskarUI-first QML/C++ code. Invoke when choosing components, checking examples, or generating HuskarUI UI.

Overview

Publishermengps
RepositoryHuskarUI
Skill nameHuskarUI
Stars
591
Forks
75
Bundled files
2
LicenseMIT
Links
  • 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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the HuskarUI 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.
  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/mengps/HuskarUI.git /tmp/HuskarUI
mkdir -p .claude/skills
cp -r /tmp/HuskarUI/agent/skills/huskarui .claude/skills/HuskarUI
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable HuskarUI 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 HuskarUI 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 HuskarUI 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.

HuskarUI

Use this skill when the agent needs HuskarUI component knowledge or must generate HuskarUI-first UI. Treat Python query results as the primary source of truth. Use source files only for verification. The skill always works from query_metainfo.py and guide.metainfo.json in <SKILL_DIR>.

When To Use

Invoke this skill proactively when any of the following is true:

  1. The agent needs to identify which HuskarUI component matches a requested control, pattern, or interaction.
  2. The agent needs examples, documentation, or usage guidance for a HuskarUI component.
  3. The user asks for HuskarUI-first QML code such as a page, dialog, toolbar, form, navigation area, or card.
  4. The agent needs to decide whether a visible control should use HuskarUI or native QtQuick.
  5. The agent needs to search the HuskarUI component set before proposing an implementation.

Capabilities

  1. List: Return component titles for discovery.
  2. Lookup: Return documentation and embedded examples for an exact component name.
  3. Search: Return candidate components for a keyword or UI role.
  4. Component Mapping: Map generic UI requests to HuskarUI components before code generation.
  5. HuskarUI-first Guidance: Choose HuskarUI controls over native QtQuick when a suitable component exists.

Critical Rules

These rules always apply. Follow them in this order.

Metadata

  • Always use Python first. Query metadata before answering from memory.
  • Never read the full guide.metainfo.json directly. Use query_metainfo.py.
  • Use exact lookup for known component names. Do not guess APIs or examples.
  • Use keyword search for generic UI needs. Search by role such as button, dialog, avatar, table, navigation.

Component Selection

  • Prefer HuskarUI for visible controls. Buttons, inputs, avatars, dialogs, tables, navigation, and common widgets should map to HuskarUI first.
  • Use native QtQuick only when HuskarUI has no suitable component or when the need is clearly low-level layout, animation, or primitives.
  • Do not mix HuskarUI and native controls for the same role without a clear reason.
  • Say explicitly when no HuskarUI component fits before falling back to native QtQuick.

Code Generation

  • Base generated code on metadata results, not assumptions.
  • Use Python-returned examples as the primary usage reference.
  • For generic UI requests, map each requested role to a HuskarUI component before writing code.
  • Prefer composition from existing HuskarUI components over custom controls.

Query Workflow

  1. Work from <SKILL_DIR> and use query_metainfo.py with guide.metainfo.json.
  2. Select the query mode that matches the request:
    • list when you need discovery or want to browse the component set.
    • <ComponentName> --exact when the component name is already known.
    • <keyword> when the request describes a generic UI role or interaction.
  3. Run the Python query before answering from memory.
  4. Use the returned title, documentation, and examples as the primary basis for the answer.
  5. For UI generation, map the requested UI roles to HuskarUI components first.
  6. Compose the code from those components.
  7. If the results are empty or insufficient, say that explicitly and fall back to the minimum native QtQuick needed.

Verification Workflow

Use source verification only when at least one of these is true:

  1. The Python output is ambiguous.
  2. The examples do not cover the requested usage.
  3. The user asks for implementation-level behavior.
  4. The metadata appears stale or incomplete.

When verification is needed:

  1. Identify the target component through Python first.
  2. Read only the source file or section that is needed to verify the specific point in question.
  3. Confirm the exact behavior, API detail, or implementation constraint being discussed.
  4. Answer from the verified implementation.
  5. State explicitly that source verification was required.

Coding Guidelines

QML

  • Import order: QtQuick -> QtQuick.* -> HuskarUI.Basic.
  • Use QtQuick.Templates as T when inheriting from templates.
  • Names: Components in PascalCase; properties, functions, and ids in camelCase.
  • Private members: Prefix with double underscore.
  • Indentation: 4 spaces.
  • Structure: id, properties, implicit size, visual properties, child objects.
  • Prefer let and const over var.
  • Use strict equality with === and !==.
  • Avoid binding loops.
  • Use Loader for conditional heavy subtrees when appropriate.

Response Policy

When answering with this skill:

  1. Start from Python query results, not from memory.
  2. Name the HuskarUI component or candidate components that best match the request.
  3. Summarize the most relevant documentation and examples returned by the query.
  4. When implementation is requested, generate HuskarUI-first code based on those results.
  5. State explicitly when the answer depends on source verification.
  6. State explicitly when no suitable HuskarUI component was found and native QtQuick is used as the fallback.

Quick Reference

powershell
# List all components
python <SKILL_DIR>/query_metainfo.py <SKILL_DIR>/guide.metainfo.json list

# Exact lookup
python <SKILL_DIR>/query_metainfo.py <SKILL_DIR>/guide.metainfo.json HusAvatar --exact

# Search by keyword or UI role
python <SKILL_DIR>/query_metainfo.py <SKILL_DIR>/guide.metainfo.json button
python <SKILL_DIR>/query_metainfo.py <SKILL_DIR>/guide.metainfo.json navigation
python <SKILL_DIR>/query_metainfo.py <SKILL_DIR>/guide.metainfo.json table

Skill Inputs

The skill always works from these files in <SKILL_DIR>:

text
<SKILL_DIR>/query_metainfo.py
<SKILL_DIR>/guide.metainfo.json

The Python helper supports:

  • Listing all component titles.
  • Exact component lookup by title.
  • Keyword search across component titles and documentation.
  • Returning documentation and embedded QML examples.

Detailed References

  • query_metainfo.py - metadata query entrypoint
  • guide.metainfo.json - metadata database, accessed through Python only
  • Repository source files - selective verification only when Python output is ambiguous or insufficient

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 HuskarUI AI skill do?

Queries HuskarUI metadata with Python and guides HuskarUI-first QML/C++ code. Invoke when choosing components, checking examples, or generating HuskarUI UI.

Why use HuskarUI on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mengps/HuskarUI/tree/master/agent/skills/huskarui. 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 HuskarUI?

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 HuskarUI?

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

Is the HuskarUI AI skill free?

Yes. It is published on GitHub by mengps under the MIT 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

Set up your own AI workspace now

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