QmlPreviewer logo

QmlPreviewer

Community
mengps
QmlPreviewer

Auto-detects the active QML file from editor context, runs qmlscene, and copies the rendered image to the clipboard by default. Invoke proactively when the agent needs to preview or visually verify a QML UI.

Overview

Publishermengps
RepositoryHuskarUI
Skill nameQmlPreviewer
Stars
591
Forks
75
Bundled files
1
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.

  • 1 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 QmlPreviewer 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/qmlpreviewer .claude/skills/QmlPreviewer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable QmlPreviewer 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 QmlPreviewer 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 QmlPreviewer 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.

QML Previewer

Use this skill whenever the agent needs to preview or visually verify a QML UI. Prefer the clipboard capture flow by default, and fall back to launching qmlscene directly when capture is unavailable or unsuitable.

When To Use

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

  1. The agent needs to preview the active QML file to understand the visual result.
  2. The agent needs to visually verify QML changes it just made or reviewed.
  3. The agent needs screenshot-based evidence to inspect layout, rendering, clipping, or missing assets.
  4. The agent needs to confirm whether a QML page loads successfully.
  5. Visual verification is needed even if the user did not explicitly ask for a preview.

Capabilities

  1. Auto Detection: Resolve the active QML file from editor context.
  2. Clipboard Preview: Run the capture script and copy the rendered result to the clipboard.
  3. Direct Launch: Fall back to qmlscene when clipboard capture is unavailable or unsuitable.
  4. Visual Verification: Report whether the page loads and whether obvious visual problems are present.
  5. Failure Reporting: Surface path issues, launch failures, and runtime errors.

Critical Rules

These rules are always enforced. Follow them in this order.

File Resolution

  • Prefer the active editor file when it is a .qml file.
  • If multiple files are open, use the focused editor tab.
  • If editor context is missing, search for the most relevant recently edited .qml file.
  • If auto-detection still fails, ask the user once for the QML file path.

Preview Execution

  • Use the clipboard capture flow by default.
  • Pass absolute paths only for both qmlscene.exe and the QML file.
  • Use the direct qmlscene launch only as a fallback when capture is unavailable or unsuitable.
  • Do not silently skip preview. If preview cannot run, explain why.

Reporting

  • Report whether the QML page loads successfully.
  • Report obvious layout or rendering issues such as clipping, blank content, missing assets, or unexpected sizing.
  • Include runtime or terminal errors when QML fails to launch.
  • Be explicit about which flow was used: clipboard capture or direct launch.

Execution Workflow

  1. Resolve the QML file path from editor context.
  2. Validate that the QML file path is absolute and exists.
  3. Resolve the absolute path to qmlscene.exe.
  4. Run the default clipboard capture flow:
powershell
& "<SKILL_DIR>\capture_qmlscene_to_clipboard.ps1" -QmlScenePath "<qmlscene.exe>" -QmlFilePath "<auto-detected absolute QML file path>"
  1. If clipboard capture is unavailable or unsuitable, launch the page directly:
powershell
& "<qmlscene.exe>" "<auto-detected absolute QML file path>" --maximized
  1. Inspect the clipboard image or live preview.
  2. Report load status, visible issues, and any runtime failures.

Fallback Workflow

Use this fallback order:

  1. If clipboard capture fails, verify both paths and retry only if the failure is clearly path-related.
  2. If capture remains unsuitable, launch the page directly with qmlscene.
  3. If auto-detection fails, ask once for the QML file path, then continue.
  4. If QML cannot load, capture terminal or runtime error output and include it in the report.

Response Policy

When using this skill in an answer:

  1. State which QML file was previewed.
  2. State which execution flow was used.
  3. Report whether the page loaded successfully.
  4. Summarize obvious visual findings.
  5. Include launch or runtime errors when present.
  6. State what blocked verification if preview could not be completed.

Quick Reference

powershell
# Default clipboard capture flow
& "<SKILL_DIR>\capture_qmlscene_to_clipboard.ps1" -QmlScenePath "<qmlscene.exe>" -QmlFilePath "<absolute QML file path>"

# Direct qmlscene fallback
& "<qmlscene.exe>" "<absolute QML file path>" --maximized

Current Skill Context

The skill currently depends on:

text
<SKILL_DIR>\SKILL.md
<SKILL_DIR>\capture_qmlscene_to_clipboard.ps1

The capture script currently supports:

  • Required -QmlScenePath
  • Required -QmlFilePath
  • Optional -StartupDelayMs
  • Optional -WindowPollTimeoutMs
  • Optional -WindowPollIntervalMs
  • Optional -KeepOpen

Detailed References

  • capture_qmlscene_to_clipboard.ps1 - default preview and clipboard capture entrypoint
  • qmlscene.exe - fallback runtime for direct QML preview

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 QmlPreviewer AI skill do?

Auto-detects the active QML file from editor context, runs qmlscene, and copies the rendered image to the clipboard by default. Invoke proactively when the agent needs to preview or visually verify a QML UI.

Why use QmlPreviewer on TypingMind?

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

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

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 QmlPreviewer?

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

Is the QmlPreviewer 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 👇