Automates testing for Windows 11 desktop applications using UIA and Win32 automation via MCP tools.
- GitHub stars
- 173
- Files
- 10
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the windows-qa-engineer skill do?
windows-qa-engineer automates testing for Windows 11 desktop applications using UIA and Win32 automation via MCP tools.
Summary generated from the skill's SKILL.md.
About the windows-qa-engineer skill
Automating testing for Windows 11 desktop applications like WinForms, WPF, or UWP is the primary function of this skill. It is designed for QA engineers and developers who need to perform smoke tests, verify dialogs, or fill forms within an interactive Windows desktop session. The agent operates directly on the same desktop as the application under test, utilizing UFO UIA and Win32 automation tools rather than mocks.
To perform a test, the agent follows a strict sequence of discovering windows, selecting the target application, and collecting control information. It relies on specific tools such as UICollector for screenshots and control trees, HostUIExecutor for window selection, and AppUIExecutor for interacting with elements via clicks, text entry, or keystrokes. The process concludes by generating a report in a markdown template that includes a numbered execution log and base64 screenshots. This skill is strictly for Windows desktop environments and should not be used for web, mobile, or non-Windows platforms.
What an agent can do with it
- 1Verify UI elements and textDevelopers can use the agent to ensure that specific text appears in a label after a user action occurs.
- 2Automate form completionThe agent can be tasked with filling out various input fields within a Windows application window.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the windows-qa-engineer skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the windows-qa-engineer skill in Plugin
/plugin marketplace add CodeAlive-AI/ai-driven-development /plugin install ai-driven-development@ai-driven-development
Install the windows-qa-engineer skill in Claude Code
~/.claude/skills/windows-qa-engineer/SKILL.md
$ npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer ~/.claude/skills/windows-qa-engineerInstall the windows-qa-engineer skill in Claude Code (project)
.claude/skills/windows-qa-engineer/SKILL.md
$ npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer .claude/skills/windows-qa-engineerInstall the windows-qa-engineer skill in Codex
~/.agents/skills/windows-qa-engineer/SKILL.md
$ npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer ~/.agents/skills/windows-qa-engineerInstall the windows-qa-engineer skill in Gemini CLI
~/.gemini/skills/windows-qa-engineer/SKILL.md
$ npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer ~/.gemini/skills/windows-qa-engineerInstall the windows-qa-engineer skill in Claude.ai
npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer windows-qa-engineer && zip -r windows-qa-engineer.zip windows-qa-engineer # claude.ai → Customize → Skills → + → Create skill → Upload a skill → windows-qa-engineer.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablecodealive-ai/ai-driven-development/skills/windows-qa-engineer is public and reachablegithub.com/codealive-ai/ai-driven-development/tree/HEAD/skil ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/codealive-ai/ai-driven-development/commits ↗Pass
- No download-and-run or credential theft in scripts4 scripts read; no download-and-run, remote eval, base64 execution or credential uploadPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/codealive-ai/ai-driven-development/blob/HEAD/skil ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/codealive-ai/ai-driven-development/blob/HEAD/skil ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 109 linesgithub.com/codealive-ai/ai-driven-development/blob/HEAD/skil ↗Pass
SKILL.md
View on GitHubWindows QA Engineer (UFO-powered)
You are an AI-QA operator on the same interactive Windows desktop as the SUT. All automation uses UFO's real MCP tools (UICollector, HostUIExecutor, AppUIExecutor) -- no mocks.
The agent, UFO MCP process, and SUT must run in the same logged-in interactive Windows desktop session. SSH, WinRM, CI services, and Session 0 are headless even when they can start the SUT process; use an interactive console, RDP session, or a secured virtual desktop. Never expose RDP publicly merely to satisfy this requirement.
Auto-Setup (when MCP tools are missing)
If UFO tools are NOT available as MCP tools, run setup before QA work:
- Run:
python "<skill-dir>/scripts/skill_installer.py" --project-dir "<project-root>" - Parse the JSON output — if
successis true, restart the MCP client - If failed, show the error and direct user to references/setup.md for manual install
Mandatory Workflow
Follow this sequence for every test run. Do not skip steps.
1. Discover windows
- Call
qa_refresh_and_list_windows() - Identify the SUT window by title hint from the user
2. Select window
- Call
select_application_window(id, name)(HostUIExecutor) - Call
capture_window_screenshot()(UICollector) -- baseline screenshot
3. Collect controls
- Call
qa_refresh_controls(field_list=["label","control_text","control_type","automation_id","control_rect"]) - Anchor on
id+control_text/automation_idwhen the returned tree is usable - If control collection returns an error or an empty tree for a large/legacy WinForms window, continue with screenshot inspection and coordinate actions; do not repeatedly force full UIA subtree scans
4. Interact
- Use
click_input(id, name),set_edit_text(id, name, text),keyboard_input(id, name, keys) - Coordinate actions only as last resort (document why)
- Re-collect controls after navigation or dialog open
5. Assert
- Read with
texts(id, name)and compare against expected - Prefer
qa_wait_for_text_contains(id, name, expected, timeout_s=10)over sleeps - Screenshot after each major checkpoint
6. Report
- Fill assets/test-case.md template
- Numbered execution log (step -> tool call -> result)
- Final PASS/FAIL with exact failing assertion if applicable
- Attach screenshot base64 strings from
capture_window_screenshot()
Tool Reference
| Tool | Server | Purpose |
|---|---|---|
qa_refresh_and_list_windows |
QA helper | Refresh + list all windows |
select_application_window |
HostUIExecutor | Select SUT by id+name |
get_app_window_controls_info |
UICollector | Raw control tree; use only when helper output is insufficient |
capture_window_screenshot |
UICollector | Screenshot selected window |
click_input |
AppUIExecutor | Click control by id+name |
set_edit_text |
AppUIExecutor | Type into control |
keyboard_input |
AppUIExecutor | Send keystrokes |
texts |
AppUIExecutor | Read control text |
qa_wait_for_text_contains |
QA helper | Poll until text matches |
qa_refresh_controls |
QA helper | Re-collect control tree with fail-soft parsing |
Example: Login Smoke Test
User says: "Test the login flow on MyApp"
1. qa_refresh_and_list_windows() → find "MyApp - Login"
2. select_application_window(id="3", name="MyApp - Login")
3. capture_window_screenshot() → baseline
4. qa_refresh_controls(field_list=["label","control_text","control_type","automation_id","control_rect"])
→ find username (id=12), password (id=14), login button (id=16)
5. set_edit_text(id="12", name="Username", text="testuser")
6. set_edit_text(id="14", name="Password", text="pass123")
7. click_input(id="16", name="Login")
8. qa_wait_for_text_contains(id="20", name="WelcomeLabel", expected_substring="Welcome", timeout_s=10)
→ {"ok": true, "text": "Welcome, testuser"}
9. capture_window_screenshot() → post-login
10. Report: PASS
Error Handling
No windows found: Re-check the SUT is running. Call qa_refresh_and_list_windows() again. If still empty, ask the user to confirm the app is open.
Empty control tree: The window may not have finished loading. Wait 2-3 seconds, then qa_refresh_controls(field_list=[...]). If still empty, try CONTROL_BACKEND=win32 (see setup.md). For large or legacy WinForms apps, avoid repeated full UIA subtree scans and use screenshot plus targeted coordinates.
Control not clickable / action fails: Re-collect controls (the tree may have changed after navigation). If the control lacks a usable id, fall back to coordinate-based action and document why.
MCP tools not found: Run auto-setup first (see Auto-Setup above). If auto-setup fails, direct the user to references/setup.md and run doctor.ps1.
Detailed Workflows
See references/qa-workflows.md for more examples, locator strategy, and common patterns.
Setup
See references/setup.md for UFO installation, MCP configuration, and diagnostics.
Files in this skill
10windows-qa-engineer skill questions
How do I install the windows-qa-engineer skill in Claude Code?
Run npx degit CodeAlive-AI/ai-driven-development/skills/windows-qa-engineer ~/.claude/skills/windows-qa-engineer. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the windows-qa-engineer skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What types of Windows applications can this skill test?
The skill is designed for testing Windows 11 desktop apps, specifically WinForms, WPF, and UWP applications.
Can I use this skill for web or mobile testing?
No, this skill is strictly for Windows desktop UI testing; use Playwright for web testing and other tools for mobile.
What should I do if the MCP tools are missing?
Run the auto-setup script by executing python "<skill-dir>/scripts/skill_installer.py" --project-dir "<project-root>" and restart the MCP client if successful.
How should the agent and the application be running?
The agent, UFO MCP process, and the application under test must all run within the same logged-in interactive Windows desktop session.