[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-422fa200-4965-44c0-b885-eb659b953978":3,"$f03XL4BFvxxaUde14UecmRluFNCHofopWPmjubL9h-EQ":43},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":34},"422fa200-4965-44c0-b885-eb659b953978","awt-e2e-testing","AI驱动端到端Web测试——AI编码工具的眼睛和双手。声明式YAML场景，Playwright执行，视觉匹配（OpenCV + OCR），平台自动检测（Flutter\u002FReact\u002FVue），学习数据库。安装：npx skills add ksgisang\u002Fawt-skill --skill awt -g","cat_coding_review","mod_coding","sickn33,coding","---\nname: awt-e2e-testing\ndescription: \"AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter\u002FReact\u002FVue), learning DB. Install: npx skills add ksgisang\u002Fawt-skill --skill awt -g\"\nrisk: unknown\nsource: \"https:\u002F\u002Fgithub.com\u002Fksgisang\u002Fawt-skill\"\n---\n\n# AWT — AI-Powered E2E Testing (Beta)\n\n> `npx skills add ksgisang\u002Fawt-skill --skill awt -g`\n\nAWT gives AI coding tools the ability to see and interact with web applications through a real browser. Your AI designs YAML test scenarios; AWT executes them with Playwright.\n\n## When to Use\n- You need AI-assisted end-to-end testing through a real browser with declarative YAML scenarios.\n- The test flow depends on visual matching, OCR, or platform auto-detection instead of stable DOM selectors.\n- You want an E2E toolchain that can both execute tests and explain failures for AI coding workflows.\n\n## What works now\n- YAML scenarios → Playwright with human-like interaction\n- Visual matching: OpenCV template + OCR (no CSS selectors needed)\n- Platform auto-detection: Flutter, React, Next.js, Vue, Angular, Svelte\n- Structured failure diagnosis with investigation checklists\n- Learning DB: failure→fix patterns in SQLite\n- 5 AI providers: Claude, OpenAI, Gemini, DeepSeek, Ollama\n- Skill Mode: no extra AI API key needed\n\n## Links\n- Main repo: https:\u002F\u002Fgithub.com\u002Fksgisang\u002FAI-Watch-Tester\n- Skill repo: https:\u002F\u002Fgithub.com\u002Fksgisang\u002Fawt-skill\n- Cloud demo: https:\u002F\u002Fai-watch-tester.vercel.app\n\nBuilt with the help of AI coding tools — and designed to help AI coding tools test better.\n\nActively developed by a solo developer at AILoopLab. Feedback welcome!\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,172,818,"2026-05-16 13:04:56",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"编程开发","coding","mdi-code-braces","代码生成、调试、审查，提升开发效率",2,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"代码审查","review","mdi-magnify-scan","代码质量分析、安全审查",4,145,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"f180fa76-c5d3-4893-9187-068b3e37c32c","1.0.0","awt-e2e-testing.zip",1160,"uploads\u002Fskills\u002F422fa200-4965-44c0-b885-eb659b953978\u002Fawt-e2e-testing.zip","daf78537154487bb29f6d7c72e87e6dbec3830ae1794fdc715d72cf401f775f1","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":2050}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]