QGroundControl is a cross-platform ground control station for unmanned aircraft, allowing operators to control MAVLink-enabled drones and plan their missions. Drone users work with it to monitor flights, configure vehicles, tune parameters, stream video, and manage autonomous missions, while the catalogue contains skills and instructions for using the application.
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 skills add mavlink/qgroundcontrol --skill qt-ui-designgit clone --depth 1 https://github.com/mavlink/qgroundcontrolWrote 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/mavlink/qgroundcontrol/qt-ui-design)<a href="https://agentmods.dev/skills/mavlink/qgroundcontrol/qt-ui-design"><img src="https://agentmods.dev/badge/skills/mavlink/qgroundcontrol/qt-ui-design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Output Handling · line 209 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 5.1 | $0.00038 | $0.05683 |
| Opus 5 | $0.00019 | $0.02841 |
| Sonnet 5 | $0.00008 | $0.01137 |
| Haiku 4.5 | $0.00004 | $0.00568 |
Grade A, and why
qt-ui-design 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qt UI Design
Before producing UI output, confirm you know: target platform, screen geometry, design system, content priority, viewing distance, locale, and input methods. Run the seven items below as a check against the conversation and the project state; ask only the items that are genuinely missing. When the user cannot answer an item, choose a sensible Qt default and name it in your response so the user can correct it.
Small edits to an existing design — for example "move the OK button to the right", "change this label", "make this red" — do not trigger the checklist. Apply section 1 silently and verify section 2 (contrast, hit-target) where relevant.
0. Context check (before designing)
Use the seven items below to decide what is already known and what to ask. If the conversation or repository has already answered an item, do not re-ask.
- Target platform — Desktop, web browser, mobile, or specific hardware (MCU, Raspberry Pi, other embedded board)?
- If a specific board: ask whether a board-specific skill exists for it and load it if so.
- Screen shape — Rectangle (default), Square, or Circle?
- Resolution and DPI — Do you know the screen resolution and DPI? (Approximate is fine.)
- Design system — Check whether the project already uses a design system or Qt Quick Controls style. If so, follow it and reuse its tokens. If not, recommend a Qt Quick Controls style: Basic, Fusion, Imagine, Material, Universal, iOS, or FluentWinUI3 (the iOS and FluentWinUI3 styles require Qt 6.7 or later). Where the project follows a third-party design language (Material Design 3, Apple Human Interface Guidelines, Fluent 2), map its tokens to the corresponding Qt Quick Controls style rather than introducing a parallel token vocabulary.
- Content priority — What information is most important (primary), secondary, and tertiary on this screen?
- Viewing distance — How far will users be from the screen? (e.g. handheld ~30 cm, desk ~60 cm, panel ~1.5 m, wall ~3 m)
- Locale and input — What is the primary locale/language? Is RTL (Arabic, Hebrew, Farsi, Urdu) support required? What input methods must be supported (touch, keyboard, mouse/pointer, hardware buttons, voice)? If the target is an embedded or MCU device, also read section 4 in full before any design decisions — it overrides several desktop defaults.
What ships with it
2 files 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.
- 8d ago First seen · 334 lines · 38 tokens per session scan A e6f6df0ad1d7
qt-ui-design is a skill published in the GitHub repository mavlink/qgroundcontrol (4,902 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 5,683 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qcad
Use when editing DXF files with a professional open-source 2D CAD application — CAM output, part libraries, isometric projection. QCAD: open-source 2D CAD with DXF as native format, scriptable via ECMAScript.
qt-figma-token-extraction
Extract design tokens, text styles, and variables from a Figma design system and produce a design-tokens.json plus ready-to-use QML singletons. Use this skill whenever someone wants to pull their design system out of Figma — whether they say "export tokens from Figma", "get design tokens", "set up my design system"…
qt-ui-design
Design or audit UI for Qt/QML, Qt projects, web, or embedded MPU or MCU targets. Use when creating screens, layouts, navigation, or auditing UX.
qt-figma-component-generation
Extract component metadata from a Figma design system and generate production-ready QML controls. Use this skill whenever someone wants to turn Figma components into QML files — whether they say "generate components from Figma", "create QML controls based on a design system", "convert Figma components to QML", "build…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).