@getollie/cli 0.0.1

package/library/web_applications-communication/wechat-multi-platform-personal-center.json

@@ -0,0 +1,68 @@
+{
+  "index": 853,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to ensure that the code you generate is executable for demonstration purposes. Specifically, implement a personal center page for WeChat multi-platform, and package and release it to different platforms.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the WeChat personal center UI implemented comprehensively?",
+      "description": "Review whether the code accurately implements all essential UI elements of a typical WeChat personal center (profile avatar, nickname, WeChat ID, moments section, wallet, settings, etc.). Check if the layout properly adapts to various screen sizes using responsive design techniques. Score 0 if core UI components are missing, 5 if basic components are present but lack polish, and 10 if the implementation is complete and faithful to WeChat's design language.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the multi-platform adaptation properly implemented?",
+      "description": "Evaluate the code's approach to multi-platform support (iOS, Android, Web, Desktop). Check for platform-specific conditional rendering, use of adaptive frameworks (like Flutter, React Native, or WeChat Mini Program framework), and appropriate handling of different device capabilities. Deduct 3 points if any major platform is not properly supported, 5 points if platform-specific features are ignored, and give 10 points only if the solution elegantly handles all target platforms.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the packaging and release pipeline properly configured?",
+      "description": "Check if the code includes the necessary configuration files for building and releasing to different platforms (such as Xcode project files, Android Gradle scripts, web build tools, or cross-platform configurations). Verify if CI/CD pipeline scripts are provided with platform-specific signing processes. Deduct 3 points for each missing platform build configuration, and 5 points if the release process lacks security considerations. Full score requires comprehensive release automation for all platforms.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are platform-specific optimizations and features implemented?",
+      "description": "Assess whether the implementation includes platform-specific optimizations and unique features (like iOS haptic feedback, Android material design components, desktop window management, etc.). Check if the code leverages native capabilities when appropriate while maintaining a consistent user experience. Score 0 if no platform-specific optimizations exist, 5 if basic adaptations are present, and 10 if sophisticated platform-specific features are thoughtfully implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as network failures, permission denials, different screen sizes, and device capabilities). Check for graceful error handling, fallback mechanisms, and proper state management. Code with strong robustness should effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Advanced theme customization beyond WeChat defaults 2. Intelligent notification grouping 3. Cross-device synchronization enhancements). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple profile editors) 2. Function modules unrelated to personal center (e.g., a full chat implementation) 3. Fancy effects that affect performance (e.g., unnecessary animations). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating UI/logic/network layers), unit test coverage, and build process automation. Assess code organization, naming conventions, and comments. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if the build process is not automated. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional design standards?",
+      "description": "Evaluate whether the design follows WeChat's established design language while maintaining platform-specific conventions: 1) Consistent color scheme matching WeChat's palette 2) Proper layout spacing following platform guidelines 3) Typography that adapts to platform standards. Deduct 3 points for each inconsistency with WeChat's design, 5 points for platform-inappropriate visual elements, and 5 points for accessibility issues. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics and platform expectations: 1) Responsive touch/click feedback 2) Smooth transitions between views 3) Appropriate loading states. Deduct 5 points for each operation without feedback, 3 points for janky animations or transitions, and 5 points for interactions that don't match platform conventions. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Communication",
+  "difficulty": "hard"
+}

package/library/web_applications-communication/wechat-official-account-graphic-message-draft.json

@@ -0,0 +1,68 @@
+{
+  "index": 943,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure that the code you generate is executable and can be demonstrated. Help me create runnable code for drafting a new graphic message for a WeChat Official Account.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the WeChat Official Account graphics message structure properly implemented?",
+      "description": "Review whether the code accurately implements the complete structure required for WeChat Official Account graphic messages, including title, author, cover image, digest, and content body. Verify if proper character limits are respected (title ≤64 characters, digest ≤120 characters). Score 0 if the basic structure is missing, 5 if only partial elements are implemented, and 10 if all required elements with proper validation are included.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the rich text editor implementation complete and functional?",
+      "description": "Check if the code implements a working rich text editor with essential formatting capabilities (bold, italic, paragraph styles, image insertion, links) matching WeChat's supported features. Verify if the editor properly sanitizes HTML to comply with WeChat's restrictions. Deduct 5 points if basic formatting is missing, and 3 points if the preview doesn't match actual WeChat rendering. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the image upload and processing functionality implemented correctly?",
+      "description": "Evaluate if the code handles image uploads with proper validation (file size ≤2MB, formats limited to jpg/png/gif), includes image compression/cropping tools, and manages the cover image aspect ratio (recommended 1.91:1). Check if image preview matches WeChat's display requirements. Deduct 5 points if image validation is missing, and 3 points if optimization tools are absent. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the code include WeChat API integration for publishing?",
+      "description": "Verify if the code includes proper integration with WeChat's official API for draft creation and publishing, including authentication handling and error management. Check if the implementation includes validation against WeChat's content policies and submission flow. Deduct 5 points if API integration is superficial without error handling, and 8 points if authentication flow is missing. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as network failures during uploads, API timeouts, invalid user inputs, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Template library with customizable styles 2. AI-assisted content suggestion 3. Mobile preview simulation 4. Scheduled publishing). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple image upload methods) 2. Function modules unrelated to WeChat graphic message creation (e.g., unnecessary social media sharing) 3. Fancy effects that affect performance (e.g., excessive animations). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating UI/business logic/API layers), unit test coverage, and build process automation. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if the build process is not automated. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional design standards?",
+      "description": "Evaluate whether the overall design follows WeChat's design principles: 1) Consistent color scheme with WeChat's brand guidelines 2) Proper layout spacing (element spacing follows the 8px multiple principle) 3) Professional font system (body font size ≥ 14px, line height over 1.5 times). Deduct 3 points for each crowded visual element, 5 points for inconsistent styling with WeChat, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance. Deduct 5 points for each operation without feedback, 3 points for visual after-images during content editing, and 5 points for hard-to-find key function buttons like 'Save' or 'Publish'. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Communication",
+  "difficulty": "hard"
+}

package/library/web_applications-communication/wechat-user-login-authorization-data-management.json

@@ -0,0 +1,68 @@
+{
+  "index": 1073,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Try to ensure that the generated code is executable. I've deleted all the previous code, and now I'm restating my requirements. Based on the previous code, please provide the complete code. On the personal homepage, first design a login button. When the login button is clicked, prompt for user information authorization. After the user authorizes, display \"Already logged in\" or \"Registration successful.\" At this point, after successful login, the page displays the user's nickname as \"WeChat User,\" and add this user's information to the user data table, mainly the user_id, which can be retrieved based on the user's login status on other pages.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the login button properly implemented?",
+      "description": "Check if the login button is visually distinct, properly positioned and has appropriate event handling. It should use standard CSS design patterns (hover/active states) and be accessible. Score 0 if the button is missing, 5 if it exists but lacks proper styling or interaction states, and 10 if fully implemented with all visual feedback states.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the user authorization flow correctly implemented?",
+      "description": "Verify if the code handles the OAuth flow properly, including authorization request, redirects, and token handling. Should include proper error handling for denied permissions. Deduct 5 points if security best practices are missing (e.g., CSRF protection), 3 points if scope permissions are too broad. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the post-login state management properly handled?",
+      "description": "Check if the page correctly updates to show 'Already logged in' or 'Registration successful' based on the user's status. Verify that the UI changes are persistent across page refreshes using proper storage mechanisms. Deduct 5 points if state is lost on refresh, 3 points if transitions between states are not smooth. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is user data storage and retrieval correctly implemented?",
+      "description": "Evaluate if the code correctly stores user_id and other required information to the user data table and if this data can be effectively retrieved on other pages. Check for proper data sanitization and validation. Deduct 5 points if data persistence is incomplete, 3 points if the cross-page data access mechanism is incomplete. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as authorization failures, network interruptions, session timeouts, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Animated transitions during login flow 2. Personalized welcome messages 3. Progressive user profile completion suggestions). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple authentication methods without clear purpose) 2. Function modules unrelated to user authentication (e.g., unnecessary analytics) 3. Fancy effects that affect performance (e.g., heavy animations during critical authentication steps). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating authentication logic/UI components/data handling), error handling coverage, and code organization. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if security best practices for authentication are not followed. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional design standards?",
+      "description": "Evaluate whether the overall design follows modern design principles: 1) Harmonious color matching (no more than 3 primary colors) 2) Proper layout spacing (element spacing follows the 8px multiple principle) 3) Professional font system (body font size ≥ 14px, line height over 1.5 times). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance. Deduct 5 points for each operation without feedback, 3 points for visual after-images during fast sliding, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Communication",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/8th-grade-english-sentence-completion-interactive-html.json

@@ -0,0 +1,68 @@
+{
+  "index": 250,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the generated code is executable for demonstration. Based on the vocabulary in the document, create \"8th grade second semester\" level English multiple-choice sentence completion exercises with 4 options, and output them in interactive clickable HTML format for users to review and test themselves.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the HTML structure for interactive English exercises properly implemented?",
+      "description": "Evaluate whether the HTML structure includes proper semantic elements (form, fieldset, input[type=radio], etc.) for multiple-choice questions. Check if the questions are properly sectioned and if the code includes proper labeling for accessibility. Score 0 if basic HTML structure is missing, 5 if minimal structure is present but lacks proper semantic elements, and 10 if the structure is complete with proper semantic elements and accessibility considerations.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the content generation for 8th grade second semester English vocabulary appropriate?",
+      "description": "Check whether the generated multiple-choice questions accurately reflect 8th grade second semester English vocabulary level. Evaluate if sentence completion exercises are contextually appropriate and if the distractors (wrong options) are plausible but clearly incorrect. Deduct 5 points if vocabulary level is inappropriate, 3 points if context sentences are poorly constructed, and 2 points if distractors are too obvious or too difficult. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the interactive functionality for selecting and checking answers implemented?",
+      "description": "Verify if JavaScript code implements option selection, answer validation, and feedback mechanisms. Check for immediate feedback after selection and proper score tracking. Score 0 if no interactivity exists, 5 if basic selection functionality works but lacks proper feedback, and 10 if full interactivity with proper validation and meaningful feedback is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there an evaluation and tracking system for user performance?",
+      "description": "Assess whether the code tracks user performance (correct/wrong answers), calculates percentage scores, and provides performance summaries. Check if users can review their mistakes and see correct answers. Deduct 3 points if no tracking exists, 3 points if calculation errors are present, and 4 points if performance review features are missing. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as no selection made before submission, rapid multiple clicks, browser refresh, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should effectively handle edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the learning experience (e.g., 1. Spaced repetition review system 2. Visual progress tracking 3. Adaptive difficulty based on performance). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple scoring systems) 2. Function modules unrelated to language exercises (e.g., unnecessary animations) 3. Features that affect performance without educational value. Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating question data/UI components/scoring logic), reusability, and maintainability. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if the code is not organized in logical functions or components. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional educational design standards?",
+      "description": "Evaluate whether the overall design follows educational UX principles: 1) Appropriate color contrast for readability 2) Clear visual hierarchy with proper spacing between questions 3) Consistent typography with readable font sizes (at least 16px). Deduct 3 points for cluttered layout, 5 points for poor readability due to color/contrast issues, and 5 points for inconsistent visual presentation. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and intuitive for educational use?",
+      "description": "Judge whether the interaction design is appropriate for learning: 1) Clear indication of selected options 2) Immediate visual feedback on correct/incorrect answers 3) Intuitive navigation between questions. Deduct 5 points for confusing selection states, 3 points for delayed or unclear feedback, and 5 points for unintuitive navigation or progression. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/academic-research-platform-frontend.json

@@ -0,0 +1,68 @@
+{
+  "index": 1661,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate, professional responses. Make sure the generated code is executable for demonstration purposes. Create a front-end for the \"Review Writer\" website project using React framework, with a design style that is cutting-edge and tech-oriented while maintaining an academic aesthetic. The website navigation includes: Home, Data Analysis, Journal Recommendations, Resource Search, Literature Management, Research Proposals, Writing Assistant, and Security & Version Management.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the React component architecture properly implemented?",
+      "description": "Evaluate if the code uses a clean component hierarchy with proper separation of concerns (presentational vs. container components). Check for context API or Redux for state management. Code should implement React hooks appropriately and avoid anti-patterns. Reusable components should be modular with well-defined props. Score 0 if React is not properly implemented, 5 if basic components exist but lack proper structure, 10 if the architecture follows best practices with clean component composition.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the navigation system fully functional with proper routing?",
+      "description": "Examine if all required navigation items (Home, Data Analysis, Journal Recommendations, Resource Search, Literature Management, Research Proposals, Writing Assistant, and Security & Version Management) are implemented. Check if React Router is properly configured with appropriate routes, including nested routing where applicable. Verify navigation state persistence across refreshes, browser history support, and URL parameter handling. Score 3 if basic navigation exists, 7 if most items are implemented with routing, 10 if comprehensive navigation with proper state management is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Does the UI reflect the cutting-edge tech-oriented style with academic aesthetic?",
+      "description": "Assess whether the design balances modern tech aesthetics (clean lines, appropriate white space, subtle animations) with academic elements (structured layout, legible typography, scholarly color scheme). Check for consistency in UI components across all pages. The design should have visual hierarchy with clear content organization. Score 3 if the basic style is present but inconsistent, 7 if design is cohesive but lacks refinement, 10 if the UI demonstrates sophisticated design principles with perfect balance between tech and academic aesthetics.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are all specified website sections meaningfully implemented?",
+      "description": "Evaluate whether each section (Data Analysis, Journal Recommendations, Resource Search, etc.) has appropriate functionality beyond mere placeholders. Data Analysis should have data visualization components, Journal Recommendations should have filtering capabilities, Resource Search needs proper search functionality, Literature Management requires document organization features, Research Proposals section should have document creation tools, Writing Assistant needs text editing capabilities, and Security & Version Management should include version control UI. Deduct 1 point per section without meaningful implementation. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as API failures, form validation errors, loading states, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should include error boundaries, form validation, loading states, and graceful degradation. Give 10 points for comprehensive error handling, 5 points if only basic validation exists, and 0 points if no error handling is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. AI-powered writing suggestions 2. Citation format auto-detection 3. Interactive research timeline visualization 4. Real-time collaboration tools). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple search mechanisms with overlapping functionality) 2. Function modules unrelated to academic writing/research (e.g., social media feeds) 3. Fancy effects that affect performance (e.g., excessive animations or unnecessarily complex visualizations). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating UI components/business logic/API layer), component reusability, and build process configuration. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if the build process is not properly configured. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional design standards?",
+      "description": "Evaluate whether the overall design follows modern design principles: 1) Harmonious color matching (no more than 3 primary colors plus accents) 2) Proper layout spacing (element spacing follows the 8px multiple principle) 3) Professional font system (body font size ≥ 14px, line height over 1.5 times, appropriate font for academic content). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance for academic workflow. Deduct 5 points for each operation without feedback, 3 points for visual after-images during navigation transitions, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/ai-teaching-assistant-educational-platform.json

@@ -0,0 +1,68 @@
+{
+  "index": 1337,
+  "question": "You are a coding expert. Please use your professional knowledge to generate accurate and professional responses. Make sure to ensure that the code you generate is executable for demonstration purposes. Help me write the project content for an AI teaching assistant educational platform.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is a comprehensive AI teaching assistant system architecture designed?",
+      "description": "Review whether the architecture clearly defines the core components of an educational platform (user management, content delivery, AI assistant integration, database design). Score 0 if there's no clear architecture, 5 if basic components are outlined but connections are unclear, and 10 if a complete, well-integrated system architecture with clear data flows is provided.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the AI interaction model properly implemented?",
+      "description": "Evaluate the implementation of the AI teaching assistant's core functionality, including natural language processing capabilities, response generation algorithms, and contextual understanding. Look for prompt engineering techniques, model selection justification, and handling of educational context. Deduct 5 points if the AI model lacks educational domain adaptation, and 3 points if there's no context retention between interactions. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the educational content management system fully functional?",
+      "description": "Check whether the platform includes a comprehensive content management system with curriculum organization, lesson planning, assessment creation, and learning path customization. Score 0 if content management is missing, 5 if basic management exists but lacks educational metadata/taxonomies, and 10 if there is a complete system with content versioning, learning objective mapping, and adapting content based on student progress.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are student progress tracking and analytics features implemented?",
+      "description": "Evaluate the implementation of learning analytics, student performance tracking, and personalized feedback mechanisms. Score 10 points if the system includes comprehensive dashboards for educators, learning pattern detection algorithms, and personalized intervention suggestions. Deduct 5 points if analytics are limited to basic metrics without actionable insights, and 3 points if visualization components are missing or inadequate.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as invalid user inputs, network interruptions, AI service failures, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the educational experience (e.g., 1. Real-time speech-to-text for lecture transcription 2. AI-generated visual concept maps 3. Personalized learning style adaptation). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar educational functions (e.g., multiple assessment systems) 2. Function modules unrelated to education (e.g., excessive gamification elements) 3. Fancy effects that affect platform performance (e.g., unnecessary animations that distract from learning). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core educational functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating educational content/AI service/user interface layers), unit test coverage, and build process automation. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if the build process is not automated. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional educational design standards?",
+      "description": "Evaluate whether the overall design follows modern educational UX principles: 1) Accessible color scheme (WCAG AA compliance) 2) Consistent information hierarchy (clear visual distinction between primary/secondary content) 3) Professional typography system (readable fonts with proper contrast). Deduct 3 points for cluttered learning interfaces, 5 points for cognitive overload-inducing layouts, and 5 points for non-intuitive navigation patterns. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the platform interaction designed for effective learning?",
+      "description": "Judge whether the interaction design supports educational goals: 1) Clear feedback on learning activities within 1-2 seconds 2) Scaffolded interfaces that adapt to learner proficiency 3) Distraction-minimizing focus states during core learning activities. Deduct 5 points for cognitive friction in primary learning paths, 3 points for inconsistent interaction patterns across modules, and 5 points for excessive UI friction in assessment components. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/andrej-karpathy-minimalist-note-taking-method.json

@@ -0,0 +1,68 @@
+{
+  "index": 438,
+  "question": "You are a Code Expert\n\n## Andrej Karpathy's Minimalist Note-taking Method\n### How to Manage All Non-Project Notes Using a Single File\n\n**Design Style:**\n- **Visual Style:** Soft Technology\n- **Emotional Tone:** Warm and Friendly\n- **Target Audience:** Young Demographics\n- **Brand Personality:** Futuristic Tech Feel\n\n**Visual Elements and Layout:**\n- **Rounded Card Layout:** Use large rounded corner cards as information containers, colored in mint green, light gray, and champagne gold accents to create a friendly, approachable feel.\n- **Soft Color System:** Primarily using mint green, light gray, champagne gold and other soft tones, avoiding strong visual stimulation.\n- **Minimalist White Space Design:** Ample white space enhances readability and reduces visual fatigue.\n- **Subtle Shadow Depth:** Subtle shadow effects give the interface a slight three-dimensional feel without overemphasis.\n- **Functional Aestheticism:** Design serves function, with no superfluous decorative elements.\n- **Grid-based Layout:** Cards arranged on a clear grid system to maintain overall sense of order.\n- **Gradient Accents:** Soft gradients used as backgrounds in parts of the interface, such as transitions from mint green to light gray, enhancing the modern feel.\n\n**Typography Style:**\n- **Data Highlighting:** Key numerical information uses extra-large font size and bold treatment, e.g., \"12,002\", \"20x\".\n- **Clear Hierarchical Typography:** Titles, explanatory text, data, and annotations distinguished by clear font size hierarchy (Headings 80-160px, Subheadings 48-80px, Body Text 32-48px, Supporting Information 24-32px).\n- **Simple Sans-serif Fonts:** All text uses modern, clean sans-serif fonts for improved readability.\n- **Consistent Text Alignment:** Maintaining unified left alignment or center alignment within cards.\n- **Color-coded Important Terms:** Using high-contrast colors like blue to mark important terms such as \"tweets\" and \"threads\".\n- **Breathing Space:** Ample spacing between text blocks creates \"breathing\" room.\n- **Special Brand Name Treatment:** Product names like \"alohi\", \"deel.\" use special fonts or styles to strengthen brand recognition.\n\n**Visual Element Style:**\n- **Subtle Icon System:** Using simple linear or filled icons, appropriately sized without overwhelming the content.\n- **Progress Visualization:** Semi-transparent circular charts + subtle gradient fills intuitively display progress, such as annual completion percentage.\n- **Color-coded Information:** Different cards use different colors for quick distinction between functional modules.\n- **Brand Identity Integration:** Product logos naturally integrated into the interface, such as \"alohi's\" circular logo.\n- **Profile Picture Elements:** Appropriate use of circular avatars adds humanizing qualities, such as on customer recommendation cards.\n- **Geometric Decorations:** Simple geometric shapes used as background decorations, such as semi-transparent circles.\n- **Component Consistency:** Buttons, labels, tabs and other elements maintain a unified style, enhancing systematic feel.\n\n**Design Principle Guidance:**\n- **Visual Hierarchy:** Headings (80-160px) > Subheadings (48-80px) > Body Text (32-48px) > Supporting Information (24-32px).\n- **Color Scheme:** Using mint green, light gray, and champagne gold as the three main color tones, ensuring contrast meets WCAG 2.1 standards.\n- **White Space Art:** Strategic use of negative space creates elegant visual balance.\n- **Font Selection:** Recommended use of two complementary modern, clean sans-serif fonts, ensuring both readability and aesthetics.\n\nFrontend implementation required",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is Karpathy's single-file note-taking methodology accurately implemented?",
+      "description": "Review whether the code correctly implements the core concept of managing all non-project notes in a single file structure. Check if features include: unified note entry/editing, hierarchical tag system, search functionality, and note linking mechanisms. Score 0 if the single-file concept is not implemented, 5 if only basic note management exists, and 10 if the complete minimalist methodology with advanced search and organization is fully realized.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Does the visual design strictly follow the 'Soft Technology' aesthetic requirements?",
+      "description": "Evaluate whether the interface adheres to the specified design system: mint green/light gray/champagne gold color palette, rounded card layouts with subtle shadows, and gradient accents. Check color contrast ratios meet WCAG 2.1 standards. Deduct 3 points for each color deviation from the specified palette, 5 points if rounded corners are not consistently applied, and 3 points if gradient implementations are jarring or excessive. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the typography hierarchy system properly implemented according to specifications?",
+      "description": "Verify that font sizing follows the exact hierarchy: Headings (80-160px), Subheadings (48-80px), Body Text (32-48px), Supporting Information (24-32px). Check for consistent sans-serif font usage, appropriate line spacing (≥1.5x), and proper text alignment. Deduct 5 points if the hierarchy is not maintained, 3 points for inconsistent font choices, and 2 points for inadequate text spacing. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are the visual elements and layout components accurately executed?",
+      "description": "Assess implementation of: grid-based card layout, subtle shadow depth effects, minimalist white space design, progress visualization elements, and icon system consistency. Check if geometric decorations and brand identity elements are properly integrated. Deduct 3 points for each missing visual component, 5 points if the grid system is not properly implemented, and 3 points if white space ratios are inadequate. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust and handles edge cases effectively?",
+      "description": "Evaluate whether the code can handle common abnormal situations such as: large note files, special characters in content, browser compatibility issues, data corruption recovery, and performance degradation with extensive notes. Code with strong robustness should effectively handle these edge cases, giving 10 points. If robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there innovative features that enhance the note-taking experience?",
+      "description": "Check whether the code includes valuable enhancements such as: 1. Smart auto-tagging based on content analysis 2. Real-time collaboration features 3. Export functionality with formatting preservation 4. Keyboard shortcut customization 5. Dark/light theme toggle matching the soft technology aesthetic. Add 2-3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features that violate the minimalist principle?",
+      "description": "Strictly check for three types of redundancy: 1. Redundant UI components that clutter the interface 2. Features unrelated to note-taking (e.g., built-in games, social media integration) 3. Excessive animations or effects that contradict the 'soft technology' aesthetic. Deduct 3 points for each redundancy found, and directly deduct 10 points if core minimalist principles are violated by feature bloat.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code demonstrate professional engineering quality?",
+      "description": "Review modular architecture (separation of data layer/view layer/utility functions), code organization, component reusability, and performance optimization. Deduct 5 points if global state is poorly managed or no design patterns are used; deduct 5 points if code duplication exceeds 25%; deduct 3 points if no build optimization is implemented. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface design meet the specified professional visual standards?",
+      "description": "Evaluate adherence to the design specification: 1) Exact color palette implementation (mint green, light gray, champagne gold) 2) Proper spacing following 8px grid principles 3) Consistent rounded corner radius across all cards 4) Appropriate contrast ratios for accessibility. Deduct 3 points for each spacing inconsistency, 5 points for color palette deviations, and 5 points for poor visual hierarchy. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Are the interactions smooth and aligned with the 'warm and friendly' user experience?",
+      "description": "Judge whether dynamic effects create the intended emotional response: 1) Hover states with subtle transitions (200-300ms) 2) Click feedback that feels responsive (≤100ms) 3) Smooth card animations when adding/editing notes 4) Intuitive navigation flow that supports the single-file methodology. Deduct 5 points for each interaction without proper feedback, 3 points for jarring transitions, and 5 points if key functions lack discoverability. Full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/android-novel-reader-app-json-url.json

@@ -0,0 +1,68 @@
+{
+  "index": 937,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and expert responses. Be sure to make the generated code executable for demonstration purposes. Design a mobile app for the Android system that functions as a novel reader, retrieving book content in JSON format from specific URLs.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the core novel reading functionality fully implemented?",
+      "description": "Review whether the code accurately implements the book content retrieval mechanism from JSON APIs, including parsing, caching, and displaying formatted text content. Check for proper handling of different chapter navigation, bookmarks, and reading progress tracking. Score 0 if core reading functionality is missing, 5 if basic reading is implemented but lacks navigation features, and 10 if all essential reader functions are included.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the JSON data handling correctly implemented?",
+      "description": "Evaluate the JSON parsing mechanism, including error handling for malformed data, empty responses, or unexpected content structure. Check for proper model classes representing book and chapter data. Verify that JSON parsing is performed off the main thread to prevent UI freezes. Deduct 5 points if no error handling exists, 3 points if parsing blocks the UI thread, and 2 points if model classes are poorly designed. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the network communication layer properly designed?",
+      "description": "Check whether the app implements proper HTTP client (Retrofit/Volley/OkHttp), handles network timeouts, implements retry mechanisms, and displays appropriate loading/error states. Verify implementation of network state monitoring and offline mode. Deduct 5 points if no network error handling exists, 3 points if no caching strategy is implemented, and 3 points if offline mode is missing. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the Android-specific architecture and lifecycle management implemented correctly?",
+      "description": "Assess whether the code follows Android architectural patterns (MVVM/MVP/MVI), handles configuration changes properly, manages Activity/Fragment lifecycles, and implements proper state preservation. Check for implementation of ViewModels, LiveData/StateFlow, and proper navigation components. Deduct 5 points for not following architecture patterns, 3 points for lifecycle leaks, and 3 points for improper state management. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as network errors, out-of-memory issues, device rotation, background process killing, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the reading experience (e.g., 1. Text-to-speech integration 2. Customizable reading themes/fonts 3. Reading statistics and analytics 4. Social sharing capabilities 5. Annotation and highlighting). Add 2 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Are there any redundant features?",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple text parsing engines) 2. Function modules unrelated to novel reading (e.g., built-in games) 3. Fancy effects that affect performance (e.g., excessive animations during page turns). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating UI/business logic/data access layers), unit test coverage, and build process automation. Examine proper dependency injection usage, static analysis tools integration, and code documentation. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 3 points if the code duplication rate is too high (over 30%); deduct 2 points if build variants (debug/release) are not properly configured. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface design meet modern Android UI standards?",
+      "description": "Evaluate whether the UI follows Material Design principles: 1) Proper implementation of components (RecyclerView, ConstraintLayout, etc.) 2) Support for both light/dark themes 3) Responsive layouts for different screen sizes 4) Proper touch target sizes (min 48dp) 5) Accessibility compliance. Deduct 2 points for each UI guideline violation, 3 points for non-responsive layouts, and 3 points for accessibility issues. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and battery-efficient?",
+      "description": "Judge whether the app performs well on mobile devices: 1) Smooth scrolling without frame drops 2) Efficient battery usage (no continuous background processes) 3) Fast app startup time (under 2 seconds) 4) Proper handling of system resources. Deduct 3 points for janky scrolling, 3 points for excessive battery drain, 2 points for slow startup, and 2 points for memory leaks. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}