{"id":"0578f136-a4d7-4665-ac6e-b14d147cff98","shortId":"g5wCkn","kind":"skill","title":"windows-qa-engineer","tagline":"Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on \"test this Windows app\", \"QA the app\", \"run smoke test\", \"click the button\", \"fill the form\", \"check the UI\", \"Windows automation\", \"UFO QA\", \"verify the dialog\", or any Wind","description":"# Windows QA Engineer (UFO-powered)\n\nYou are an AI-QA operator on the SAME Windows 11 desktop as the SUT.\nAll automation uses UFO's real MCP tools (UICollector, HostUIExecutor, AppUIExecutor) -- no mocks.\n\n## Auto-Setup (when MCP tools are missing)\n\nIf UFO tools are NOT available as MCP tools, run setup before QA work:\n\n1. Run: `python \"<skill-dir>/scripts/skill_installer.py\" --project-dir \"<project-root>\"`\n2. Parse the JSON output — if `success` is true, tell user to restart Claude Code\n3. If failed, show the error and direct user to [references/setup.md](references/setup.md) for manual install\n\n## Mandatory Workflow\n\nFollow this sequence for every test run. Do not skip steps.\n\n### 1. Discover windows\n- Call `qa_refresh_and_list_windows()`\n- Identify the SUT window by title hint from the user\n\n### 2. Select window\n- Call `select_application_window(id, name)` (HostUIExecutor)\n- Call `capture_window_screenshot()` (UICollector) -- baseline screenshot\n\n### 3. Collect controls\n- Call `get_app_window_controls_info(field_list=[\"label\",\"control_text\",\"control_type\",\"automation_id\",\"control_rect\"])`\n- Anchor on `id` + `control_text` / `automation_id` -- never hardcode coordinates unless control tree fails\n\n### 4. Interact\n- Use `click_input(id, name)`, `set_edit_text(id, name, text)`, `keyboard_input(id, name, keys)`\n- Coordinate actions only as last resort (document why)\n- Re-collect controls after navigation or dialog open\n\n### 5. Assert\n- Read with `texts(id, name)` and compare against expected\n- Prefer `qa_wait_for_text_contains(id, name, expected, timeout_s=10)` over sleeps\n- Screenshot after each major checkpoint\n\n### 6. Report\n- Fill [assets/test-case.md](assets/test-case.md) template\n- Numbered execution log (step -> tool call -> result)\n- Final PASS/FAIL with exact failing assertion if applicable\n- Attach screenshot base64 strings from `capture_window_screenshot()`\n\n## Tool Reference\n\n| Tool | Server | Purpose |\n|------|--------|---------|\n| `qa_refresh_and_list_windows` | QA helper | Refresh + list all windows |\n| `select_application_window` | HostUIExecutor | Select SUT by id+name |\n| `get_app_window_controls_info` | UICollector | Get control tree |\n| `capture_window_screenshot` | UICollector | Screenshot selected window |\n| `click_input` | AppUIExecutor | Click control by id+name |\n| `set_edit_text` | AppUIExecutor | Type into control |\n| `keyboard_input` | AppUIExecutor | Send keystrokes |\n| `texts` | AppUIExecutor | Read control text |\n| `qa_wait_for_text_contains` | QA helper | Poll until text matches |\n| `qa_refresh_controls` | QA helper | Re-collect control tree |\n\n## Example: Login Smoke Test\n\nUser says: \"Test the login flow on MyApp\"\n\n```\n1. qa_refresh_and_list_windows() → find \"MyApp - Login\"\n2. select_application_window(id=\"3\", name=\"MyApp - Login\")\n3. capture_window_screenshot() → baseline\n4. get_app_window_controls_info(field_list=[\"label\",\"control_text\",\"control_type\",\"automation_id\",\"control_rect\"])\n   → find username (id=12), password (id=14), login button (id=16)\n5. set_edit_text(id=\"12\", name=\"Username\", text=\"testuser\")\n6. set_edit_text(id=\"14\", name=\"Password\", text=\"pass123\")\n7. click_input(id=\"16\", name=\"Login\")\n8. qa_wait_for_text_contains(id=\"20\", name=\"WelcomeLabel\", expected_substring=\"Welcome\", timeout_s=10)\n   → {\"ok\": true, \"text\": \"Welcome, testuser\"}\n9. capture_window_screenshot() → post-login\n10. Report: PASS\n```\n\n## Error Handling\n\n**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.\n\n**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).\n\n**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.\n\n**MCP tools not found**: Run auto-setup first (see [Auto-Setup](#auto-setup-when-mcp-tools-are-missing) above). If auto-setup fails, direct the user to [references/setup.md](references/setup.md) and run `doctor.ps1`.\n\n## Detailed Workflows\n\nSee [references/qa-workflows.md](references/qa-workflows.md) for more examples, locator strategy, and common patterns.\n\n## Setup\n\nSee [references/setup.md](references/setup.md) for UFO installation, MCP configuration, and diagnostics.","tags":["windows","engineer","driven","development","codealive-ai","agent-safety","agent-skills","ai-coding","ai-driven-development","ai-safety","antigravity","bash"],"capabilities":["skill","source-codealive-ai","skill-windows-qa-engineer","topic-agent-safety","topic-agent-skills","topic-ai-coding","topic-ai-driven-development","topic-ai-safety","topic-antigravity","topic-bash","topic-claude-code","topic-codex-cli","topic-cursor","topic-developer-tools","topic-gemini-cli"],"categories":["ai-driven-development"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/CodeAlive-AI/ai-driven-development/windows-qa-engineer","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add CodeAlive-AI/ai-driven-development","source_repo":"https://github.com/CodeAlive-AI/ai-driven-development","install_from":"skills.sh"}},"qualityScore":"0.483","qualityRationale":"deterministic score 0.48 from registry signals: · indexed on github topic:agent-skills · 67 github stars · SKILL.md body (4,446 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:57:08.001Z","embedding":null,"createdAt":"2026-05-04T06:56:24.242Z","updatedAt":"2026-05-18T18:57:08.001Z","lastSeenAt":"2026-05-18T18:57:08.001Z","tsv":"'-3':571 '/scripts/skill_installer.py':109 '1':106,156,419 '10':283,512,525 '11':9,66 '12':462,475 '14':465,485 '16':469,494 '2':113,175,428,570 '20':504 '3':128,192,433,437 '4':226,442 '5':261,470 '6':291,480 '7':490 '8':497 '9':518 'action':245,591,617 'ai':59 'ai-qa':58 'anchor':212 'app':11,23,26,197,346,444,556 'applic':180,311,337,430 'appuiexecutor':81,363,372,378,382 'ask':550 'assert':262,309 'assets/test-case.md':294,295 'attach':312 'auto':85,627,632,635,645 'auto-setup':84,626,631,644 'auto-setup-when-mcp-tools-are-miss':634 'autom':16,40,72,208,217,455 'avail':97 'back':612 'backend':584 'base':616 'base64':314 'baselin':190,441 'button':32,467 'call':159,178,185,195,302,540 'captur':186,317,354,438,519 'chang':601 'check':36,535 'checkpoint':290 'claud':126 'click':30,229,361,364,491 'clickabl':590 'code':127 'collect':193,254,404,595 'common':668 'compar':269 'configur':678 'confirm':554 'contain':277,390,502 'control':194,199,204,206,210,215,223,255,348,352,365,375,384,399,405,446,451,453,457,560,576,583,588,596,606 'coordin':221,244,615 'coordinate-bas':614 'desktop':10,67 'detail':657 'diagnost':680 'dialog':45,259 'dir':112 'direct':135,648 'discov':157 'doctor.ps1':656 'document':250,619 'edit':234,370,472,482 'empti':549,559,581 'engin':4,51 'error':133,528 'everi':149 'exact':307 'exampl':407,664 'execut':298 'expect':271,280,507 'fail':130,225,308,592,647 'fall':611 'field':201,448,577 'fill':33,293 'final':304 'find':425,459 'finish':567 'first':629 'flow':416 'follow':145 'form':35 'found':532,624 'get':196,345,351,443 'handl':529 'hardcod':220 'helper':331,392,401 'hint':171 'hostuiexecutor':80,184,339 'id':182,209,214,218,231,236,241,266,278,343,367,432,456,461,464,468,474,484,493,503,610 'identifi':165 'info':200,349,447 'input':230,240,362,377,492 'instal':142,676 'interact':227 'json':116 'key':243 'keyboard':239,376 'keystrok':380 'label':203,450 'lack':607 'last':248 'list':163,202,328,333,423,449,544,578 'load':568 'locat':665 'log':299 'login':408,415,427,436,466,496,524 'major':289 'mandatori':143 'manual':141 'match':396 'may':564,599 'mcp':17,77,88,99,621,638,677 'miss':91,641 'mock':83 'myapp':418,426,435 'name':183,232,237,242,267,279,344,368,434,476,486,495,505 'navig':257,603 'never':219 'number':297 'ok':513 'open':260,558 'oper':61 'output':117 'pars':114 'pass':527 'pass/fail':305 'pass123':489 'password':463,487 'pattern':669 'poll':393 'post':523 'post-login':522 'power':54 'prefer':272 'project':111 'project-dir':110 'purpos':324 'python':108 'qa':3,24,42,50,60,104,160,273,325,330,386,391,397,400,420,498,541,574 're':253,403,534,594 're-check':533 're-collect':252,402,593 'read':263,383 'real':76 'rect':211,458 'refer':321 'references/qa-workflows.md':660,661 'references/setup.md':138,139,652,653,672,673 'refresh':161,326,332,398,421,542,575 'report':292,526 'resort':249 'restart':125 'result':303 'run':27,101,107,151,539,625,655 'say':412 'screenshot':188,191,286,313,319,356,358,440,521 'second':572 'see':586,630,659,671 'select':176,179,336,340,359,429 'send':379 'sequenc':147 'server':323 'set':233,369,471,481 'setup':86,102,628,633,636,646,670 'setup.md':587 'show':131 'skill' 'skill-windows-qa-engineer' 'skip':154 'sleep':285 'smoke':28,409 'source-codealive-ai' 'step':155,300 'still':548,580 'strategi':666 'string':315 'substr':508 'success':119 'sut':70,167,341,537 'tell':122 'templat':296 'test':7,20,29,150,410,413 'testus':479,517 'text':205,216,235,238,265,276,371,381,385,389,395,452,473,478,483,488,501,515 'timeout':281,510 'titl':170 'tool':78,89,94,100,301,320,322,622,639 'topic-agent-safety' 'topic-agent-skills' 'topic-ai-coding' 'topic-ai-driven-development' 'topic-ai-safety' 'topic-antigravity' 'topic-bash' 'topic-claude-code' 'topic-codex-cli' 'topic-cursor' 'topic-developer-tools' 'topic-gemini-cli' 'tree':224,353,406,561,598 'tri':582 'trigger':18 'true':121,514 'type':207,373,454 'ufo':14,41,53,74,93,675 'ufo-pow':52 'ui':38 'uia/win32':15 'uicollector':79,189,350,357 'unless':222 'usabl':609 'use':5,73,228 'user':123,136,174,411,552,650 'usernam':460,477 'verifi':43 'via':13 'wait':274,387,499,569 'welcom':509,516 'welcomelabel':506 'win32':585 'wind':48 'window':2,8,22,39,49,65,158,164,168,177,181,187,198,318,329,335,338,347,355,360,424,431,439,445,520,531,545,563 'windows-qa-engin':1 'winforms/wpf/uwp':12 'work':105 'workflow':144,658","prices":[{"id":"5e7c605a-9786-4d36-8a33-29b2a3c59cf7","listingId":"0578f136-a4d7-4665-ac6e-b14d147cff98","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"CodeAlive-AI","category":"ai-driven-development","install_from":"skills.sh"},"createdAt":"2026-05-04T06:56:24.242Z"}],"sources":[{"listingId":"0578f136-a4d7-4665-ac6e-b14d147cff98","source":"github","sourceId":"CodeAlive-AI/ai-driven-development/windows-qa-engineer","sourceUrl":"https://github.com/CodeAlive-AI/ai-driven-development/tree/main/skills/windows-qa-engineer","isPrimary":false,"firstSeenAt":"2026-05-04T06:56:24.242Z","lastSeenAt":"2026-05-18T18:57:08.001Z"}],"details":{"listingId":"0578f136-a4d7-4665-ac6e-b14d147cff98","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"CodeAlive-AI","slug":"windows-qa-engineer","github":{"repo":"CodeAlive-AI/ai-driven-development","stars":67,"topics":["agent-safety","agent-skills","ai-coding","ai-driven-development","ai-safety","antigravity","bash","claude-code","codex-cli","cursor","developer-tools","gemini-cli","hooks","mcp","multi-agent","opencode","plugins","prompt-engineering","skills","subagents"],"license":"mit","html_url":"https://github.com/CodeAlive-AI/ai-driven-development","pushed_at":"2026-05-12T20:04:46Z","description":"Practices, protocols, and skills for AI-driven software development. 18 skills + 1 Bash safety hook for Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI, Antigravity, and any agent supporting the Agent Skills standard.","skill_md_sha":"2f972cdfa6dbb03dca5ea33d5554759cf01b9eea","skill_md_path":"skills/windows-qa-engineer/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/CodeAlive-AI/ai-driven-development/tree/main/skills/windows-qa-engineer"},"layout":"multi","source":"github","category":"ai-driven-development","frontmatter":{"name":"windows-qa-engineer","description":"Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on \"test this Windows app\", \"QA the app\", \"run smoke test\", \"click the button\", \"fill the form\", \"check the UI\", \"Windows automation\", \"UFO QA\", \"verify the dialog\", or any Windows desktop UI testing task. Not for web/browser testing (use Playwright), mobile testing, or non-Windows platforms."},"skills_sh_url":"https://skills.sh/CodeAlive-AI/ai-driven-development/windows-qa-engineer"},"updatedAt":"2026-05-18T18:57:08.001Z"}}