Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mengps/pyhuskarui/qmlpreviewernpx skills add mengps/PyHuskarUI --skill qmlpreviewergit clone --depth 1 https://github.com/mengps/PyHuskarUIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mengps/pyhuskarui/qmlpreviewer)<a href="https://agentmods.dev/skills/mengps/pyhuskarui/qmlpreviewer"><img src="https://agentmods.dev/badge/skills/mengps/pyhuskarui/qmlpreviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.01090 |
| Opus 5 | $0.00025 | $0.00545 |
| Sonnet 5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
QmlPreviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to QmlPreviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- The agent needs to preview the active QML file to understand the visual result.
- The agent needs to visually verify QML changes it just made or reviewed.
- The agent needs screenshot-based evidence to inspect layout, rendering, clipping, or missing assets.
- The agent needs to confirm whether a QML page loads successfully.
- Visual verification is needed even if the user did not explicitly ask for a preview.
Capabilities
- Auto Detection: Resolve the active QML file from editor context.
- Clipboard Preview: Run the capture script and copy the rendered result to the clipboard.
- Direct Launch: Fall back to
qmlscenewhen clipboard capture is unavailable or unsuitable. - Visual Verification: Report whether the page loads and whether obvious visual problems are present.
- 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
.qmlfile. - If multiple files are open, use the focused editor tab.
- If editor context is missing, search for the most relevant recently edited
.qmlfile. - 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.exeand the QML file. - Use the direct
qmlscenelaunch 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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 125 lines · 50 tokens per session scan A e3ee15ff0022
QmlPreviewer is a skill published in the GitHub repository mengps/PyHuskarUI (115 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,090 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to QmlPreviewer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
HuskarUI
Queries HuskarUI metadata with Python and guides HuskarUI-first QML/C++ code. Invoke when choosing components, checking examples, or generating HuskarUI UI.
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.
antd
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
b123d-drawing
../../../src/build123dmcp/skills/b123d-drawing/SKILL.md.
design-interaction
Design the interaction + feedback + error flows for a user-facing surface (CLI, API, or web). On-demand — run when the ux-engineer is consulted on an interaction contract.