qt-commander: Skill for Claude Code

.claude/skills/qt-commander-ui/SKILL.md

qt-commander-ui is a skill for Claude Code from tiefeiyu/qt-commander. It costs 85 tokens per session (872 once invoked), scanned A, original, MIT.

A tool for controlling a running Qt desktop application's interface, such as buttons, fields, and menus. It can inspect the interface and capture screenshots while checking the result.

In plain words
What is it for?
Use it to connect to a running Qt app, find interface elements, click or type into them, confirm the visible state, and save screenshot evidence.
Why use it?
It removes the need to perform interface checks manually when testing a real Qt application. It is not intended for checking backend logs or starting and stopping programs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is tiefeiyu/qt-commander's own configuration. It tells Claude Code how to work on qt-commander itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qt-commander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tiefeiyu/qt-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tiefeiyu/qt-commander/master/.claude/skills/qt-commander-ui/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tiefeiyu/qt-commander

Made for: Claude Code.

Wrote 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.

agentmods badge for qt-commander-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiefeiyu/qt-commander/qt-commander-ui/github.svg)](https://agentmods.dev/skills/tiefeiyu/qt-commander/qt-commander-ui)
Your own site
<a href="https://agentmods.dev/skills/tiefeiyu/qt-commander/qt-commander-ui"><img src="https://agentmods.dev/badge/skills/tiefeiyu/qt-commander/qt-commander-ui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qt-commander-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/tiefeiyu/qt-commander/qt-commander-ui"><img src="https://agentmods.dev/badge/skills/tiefeiyu/qt-commander/qt-commander-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.00872
Opus 5 $0.00043 $0.00436
Sonnet 5 $0.00017 $0.00174
Haiku 4.5 $0.00009 $0.00087

Measured 12d ago against content hash f74415df391a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qt-commander-ui 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 12d 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.

.claude/skills/qt-commander-ui/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qt-commander-ui

Drive a running Qt application's UI to complete verification loops. All operations go through the qt-commander MCP tools (configured at user level, available in every project).

When to Use

  • Verification tasks that need to click buttons, type text, verify UI state, or capture screenshot evidence
  • Not for: pure backend/log verification or process start/stop management (use the project's own verify/run/kill-style skills)

Preflight

  1. Build the library (first time or after source changes):
    • qt_detect_msvc_and_qt to discover the environment → confirm build parameters with the user (never auto-pick)
    • qt_build (parameters must match the target process; see references/build-params.md)
  2. Start the target app and wait for its main window before attaching (during startup the GUI is busy; injection and operations tend to time out with 2004)
  3. qt_attach <pid> (find the pid with qt_list_processes) → confirm connected via qt_list_sessions

Standard Workflow

  1. qt_snapshot(max_depth=1, detail=extended) → read the snapshot resource (qt-commander://sessions/...) to inspect the UI tree
  2. qt_find_element to locate the target (custom QML components: prefer qml_id — the QML id from source, shown on snapshot nodes — then object_name/properties; type_inherits does NOT match QML type names)
  3. Ids are stable until the next qt_snapshotqt_find_element and qt_get_snapshot never invalidate them; hold onto ids across steps
  4. Need full-tree context after a find? Call qt_get_snapshot (read-only view) — it never renumbers ids, so the ids you already hold stay valid. Only an explicit qt_snapshot renumbers.
  5. Capture a qt_screenshot after operations as evidence

Operating Discipline (mandatory)

  1. Mouse clicks always go through the real input pipeline: qt_mouse_click_region (element center) or qt_mouse_click_at (exact coordinates) — routed through Qt's real event dispatch + hit testing, identical to a human click (QML MouseArea, focus changes, etc. all work). No QWidget/QML distinction.
  2. qt_mouse_click (direct delivery to the widget) is a debug fallback only; not for routine use.
  3. qt_keyboard_input is already real input; always use a fresh id — a stale id errors out (Element not found: id=N) instead of silently typing.
  4. 2004 timeout ≠ failure: the request may still execute (at-least-once). Do not blindly retry side-effect operations (click/type/setProperty); snapshot first to verify state.
  5. Prefer real input; avoid qt_set_property/qt_call_method (destructive, bypasses the real interaction path).
  6. Before rebuilding the library, qt_detach(purge=True) (the DLL is locked by the target process, failing the build).
  7. 2007 = definitively not executed, safe to retry (unlike 2004; see references/error-codes.md).

Read the full file on GitHub · 51 lines

Files

What ships with it

3 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.

Changes

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.

  1. 12d ago First seen · 51 lines · 85 tokens per session scan A f74415df391a

Subscribe to this mod's changes

qt-commander-ui is a skill published in the GitHub repository tiefeiyu/qt-commander (2 stars, last pushed 16d ago), licensed MIT. It adds 85 tokens to every session and 872 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

e2e-testing

AI-powered E2E testing for any app — Flutter, React Native, iOS, Android, Electron, Tauri, KMP, .NET MAUI. Connects via MCP to running apps so the agent can take screenshots, tap elements, enter text, scroll, inspect UI trees, and verify state with natural language. Use when the user wants to test an app's UI…

ai-dashboad/flutter-skill · 107 tokens

flutter-skill

Automate and test Flutter applications — launch apps, inspect widgets, tap elements, enter text, scroll, swipe, take screenshots, validate state, and debug via Dart VM Service Protocol. Use when the user wants to run Flutter app tests, automate Flutter UI interactions, inspect widget trees, debug a running Flutter…

ai-dashboad/flutter-skill · 73 tokens

Appium Mobile Testing

Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.

PramodDutta/qaskills · 32 tokens

E2E Testing Patterns

Comprehensive end-to-end testing methodologies and best practices covering architecture, test design, data management, flakiness prevention, and cross-browser strategies.

PramodDutta/qaskills · 35 tokens

axe-core Accessibility Automation

Automated accessibility testing with axe-core integrated into CI pipelines, including custom rule configuration, issue prioritization, and remediation guidance.

PramodDutta/qaskills · 30 tokens

CI/CD Pipeline Config

CI/CD pipeline configuration skill for test automation, covering GitHub Actions, Jenkins, GitLab CI, test parallelization, reporting, and artifact management.

PramodDutta/qaskills · 35 tokens