@getollie/cli 0.0.1

package/library/web_applications-education_learning/webpage-security-checklist-scl-to-word-converter.json

@@ -0,0 +1,68 @@
+{
+  "index": 1239,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the code you generate is executable for demonstration. Based on the security checklist SCL, create a webpage that includes all content and has the functionality to convert to Word.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the security checklist (SCL) content fully implemented in the webpage?",
+      "description": "Review whether the HTML structure properly organizes and presents all sections of the security checklist with appropriate headers, lists, and formatting. Score 0 if the checklist content is incomplete, 5 if basic content is present but poorly structured, and 10 if the full security checklist is comprehensively implemented with proper semantic HTML elements (like <section>, <h1>-<h6>, <ul>/<ol>, etc.).",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the Word conversion functionality properly implemented?",
+      "description": "Evaluate the implementation of the Word document export feature. Check if the code uses appropriate libraries (like docx.js, html-to-docx, or similar) with proper error handling. The exported Word document should maintain the structure, formatting, and completeness of the original checklist. Deduct 5 points if the export works but loses formatting, 3 points if it has compatibility issues with different browsers, and 3 points if it doesn't provide progress feedback during export operations. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the data structure of the security checklist properly organized?",
+      "description": "Assess how the security checklist data is structured in the code. Check if it uses appropriate data structures (arrays, objects) that facilitate filtering, sorting, and categorization of security items. The implementation should demonstrate separation of data and presentation concerns. Deduct 5 points if the data is hardcoded directly in the HTML rather than stored in JavaScript variables/objects, 3 points if the structure doesn't allow for easy modification or extension of the checklist. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are there search, filter, or navigation features to enhance usability of the security checklist?",
+      "description": "Check whether the webpage includes practical features to improve checklist usability such as search functionality, category filters, or quick navigation tools. Also verify if the implementation includes checklist item state management (marking items as complete/incomplete). Score 3 points for basic search implementation, 3 points for filtering capabilities, 2 points for navigation aids, and 2 points for checklist item state tracking. 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 browser compatibility issues, network interruptions during export, unexpected 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. Dark mode toggle 2. Automatic saving of checklist progress 3. Security score visualization 4. Export to multiple formats beyond Word). Add 2.5 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 export mechanisms doing the same thing) 2. Function modules unrelated to security checklist (e.g., unrelated analytics) 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 data/view/export functionality), code organization, and implementation patterns. 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 there's no error handling or input validation. 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 (especially for the export button), 3 points for visual after-images during interactions, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/wechat-login-medical-knowledge-viewer.json

@@ -0,0 +1,68 @@
+{
+  "index": 700,
+  "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. Write code for a WeChat login that allows users to view medical knowledge after logging in. Please write each file in detail.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the WeChat OAuth login flow properly implemented?",
+      "description": "Evaluate whether the code implements the complete WeChat OAuth 2.0 authentication flow, including redirecting to WeChat authorization page, handling callback with auth code, exchanging code for access token, and retrieving user information. Score 0 if the flow is incomplete, 5 if basic login works but lacks proper error handling, and 10 if it's fully implemented with proper state management and CSRF protection.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is secure session management implemented for authenticated users?",
+      "description": "Check whether the code securely manages user sessions after successful WeChat authentication. This includes generating secure session tokens, implementing proper cookie settings (httpOnly, secure, SameSite), session expiration handling, and protection against session fixation attacks. Deduct 5 points if session tokens are not securely generated, 3 points if cookies lack security attributes, and 3 points if there's no session expiration mechanism.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the medical knowledge content system properly implemented?",
+      "description": "Review whether the code includes a structured system for managing and displaying medical knowledge content. This should include content categorization, search functionality, and proper content rendering with medical terminology support. Deduct 5 points if content is hardcoded rather than dynamically loaded, 3 points if search functionality is missing, and 5 points if there's no proper categorization system.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there proper authentication and authorization for accessing medical content?",
+      "description": "Evaluate if the system properly restricts access to medical knowledge based on user authentication status. Check for middleware that verifies user sessions before serving protected content and redirects unauthenticated users to the login flow. Deduct 5 points if authentication checks are inconsistent across routes, 5 points if there are ways to bypass authentication, and 3 points if the login state persistence is not properly implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as WeChat API failures, network interruptions, invalid responses, timeouts) and provide friendly error prompts or recovery mechanisms. 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. Personalized content recommendations based on browsing history 2. Medical terminology tooltip explanations 3. Offline access capability for previously viewed content). 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 medical knowledge or authentication (e.g., unrelated social features) 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 auth logic/content management/frontend 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 modern design standards: 1) Harmonious color matching aligned with medical themes (professional blues/greens, not jarring 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 inappropriate color schemes for medical content, 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) Login process feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance for important medical information. Deduct 5 points for each operation without feedback, 3 points for visual after-images during content navigation, and 5 points for hard-to-find key medical content sections. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/wechat-mini-program-intelligent-lighting-design-form.json

@@ -0,0 +1,68 @@
+{
+  "index": 1351,
+  "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 demonstrable. Topic: Intelligent lighting design solution. Input: industry, room length and width, height. Help me design a form page implemented with native WeChat Mini Program.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the WeChat Mini Program form implementation complete and correct?",
+      "description": "Check whether the code correctly implements the basic form elements using native WeChat Mini Program components (input, picker, slider, etc.) for collecting industry type, room dimensions, and height. Verify that proper WXML structure, WXSS styling, and JS event handling are included. Score 0 if the core form elements are missing, 5 if basic implementation exists but lacks validation, and 10 if the form is complete with proper data binding and validation.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the lighting calculation logic implemented properly?",
+      "description": "Evaluate whether the code includes algorithms to calculate appropriate lighting solutions based on the input parameters (industry type, room dimensions, height). Check for industry-specific lighting standards implementation, lux level calculations, fixture quantity recommendations, and positioning suggestions. Deduct 5 points if the calculation lacks industry standards reference, and 3 points if it only provides basic calculations without optimization. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is there a visual representation of the lighting solution?",
+      "description": "Assess whether the code provides visual feedback of the lighting design through canvas, SVG, or other WeChat Mini Program compatible visualization methods. The visualization should accurately represent the room dimensions and proposed lighting fixtures placement. Deduct 5 points if there's no real-time preview, 3 points if the visualization is static and non-interactive. Give 10 points if the visualization is interactive and updates with input changes.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the WeChat Mini Program data management handled effectively?",
+      "description": "Check if the code implements proper data management including local storage for saving user inputs, cloud data integration if applicable, and proper state management between pages. Verify that the app can restore previous inputs when reopened. Deduct 5 points if there's no data persistence, 3 points if state management between components is inconsistent. 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 invalid inputs, out-of-range values, permission denials, network issues, 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. AR preview of lighting effects 2. Energy consumption calculation 3. Cost estimation based on fixture selection). 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 ways to input the same data) 2. Function modules unrelated to lighting design (e.g., unrelated social sharing features) 3. Fancy effects that affect performance (e.g., unnecessary animations that slow down the app). 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 layers), component reusability, and proper use of WeChat Mini Program best practices. Deduct 5 points if global state pollution is found or if the code doesn't follow the WeChat Mini Program development conventions; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there's no proper error handling and logging. 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 Mini Program design guidelines: 1) Harmonious color matching consistent with lighting industry aesthetics 2) Proper layout spacing following WeChat's component spacing principles 3) Professional typography system that ensures readability. Deduct 3 points for each crowded visual element, 5 points for inappropriate color schemes that harm readability, and 5 points for layouts that break on different screen sizes. 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 WeChat Mini Program interaction standards: 1) Form input feedback is immediate 2) Transitions between form sections are smooth 3) Loading states are properly indicated during calculations. Deduct 5 points for each operation without feedback, 3 points for lagging transitions when changing inputs, and 5 points for confusing navigation patterns. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/wechat-mini-program-novel-reader.json

@@ -0,0 +1,68 @@
+{
+  "index": 431,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the code you provide is executable and can be demonstrated. I am a beginner in computer programming, but I want to create a WeChat Mini Program for reading novels. Based on my situation, please design a Mini Program for me with code that can run independently and normally. The novel content should be able to update in real time. Please design this for me.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the basic structure of the WeChat Mini Program correctly implemented?",
+      "description": "Review whether the code includes the essential files for a WeChat Mini Program (app.js, app.json, app.wxss, and page files with .js, .json, .wxml, and .wxss extensions). Check if the project structure follows Mini Program conventions and if the configuration in app.json is properly set up with necessary pages, window settings, and tabBar if applicable. Score 0 if the core structure is missing, 5 if basic structure exists but has configuration errors, and 10 if properly implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the novel reading functionality fully implemented?",
+      "description": "Evaluate whether the code implements core novel reading features: chapter navigation, content rendering, font size adjustment, background color themes, and reading progress tracking. Check if text rendering handles different character sets and formats properly. Deduct 3 points if chapter navigation is missing, 3 points if font/theme customization is absent, and 4 points if progress tracking is not implemented. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the real-time content update mechanism properly designed?",
+      "description": "Check if the code includes a robust mechanism for novel content updates: API integration for fetching new chapters, efficient caching strategy, and update notifications. Assess whether it handles network failures gracefully with retry logic. Deduct 4 points if there's no proper caching, 3 points if update notifications are missing, and 3 points if offline reading capability is not implemented. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the user interface designed for optimal reading experience?",
+      "description": "Review if the UI is optimized for reading with proper line spacing, paragraph breaks, comfortable margins, and eye-friendly color schemes. Check if the interface adapts to different screen sizes and orientations. Deduct 3 points for poor text formatting, 4 points for non-responsive design, and 3 points if there's no night mode for comfortable reading in low light. 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, API timeouts, malformed responses, etc.) and provide friendly error prompts or recovery mechanisms. Check if exception handling covers user operation errors and edge cases. Code with strong robustness should be able to effectively handle these issues, 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. Text-to-speech for audio reading 2. Social sharing with comments/annotations 3. Reading statistics and achievements system). 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 methods to store reading progress) 2. Function modules unrelated to novel reading (e.g., a built-in calculator) 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 (separation of UI components, data management, and business logic), naming conventions consistency, and comments clarity. Check if the code follows Mini Program best practices. Deduct 4 points if global state management is chaotic; deduct 3 points if the code duplication rate is high; deduct 3 points if comments are insufficient or misleading. 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 Mini Program design principles: 1) Consistent with WeChat's visual language 2) Proper layout spacing and component sizing 3) Professional typography with adequate contrast and readability. Deduct 3 points for inconsistent UI elements, 4 points for poor readability in text display, and 3 points for unintuitive navigation design. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the interactions meet Mini Program performance standards: 1) Page transitions ≤ 300ms 2) Content loading with appropriate feedback 3) Smooth scrolling without jank. Deduct 4 points for laggy page turns, 3 points for missing loading indicators, and 3 points for unresponsive UI during content fetching. Check if the Mini Program adopts proper techniques to optimize performance on low-end devices. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/wechat-mini-program-running-track-recorder.json

@@ -0,0 +1,68 @@
+{
+  "index": 1560,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to ensure the generated code is executable for demonstration. I want to create a WeChat mini program for recording running tracks, called \"Running Circle.\" The track color will be determined by the pace speed. It will use cloud development. Please provide me with the complete code for this mini program.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the core GPS tracking functionality fully implemented?",
+      "description": "Evaluate whether the code accurately implements real-time GPS tracking with appropriate positioning accuracy settings. Check if it handles different GPS states (high/low accuracy, no signal) and contains power optimization strategies. Score 0 if GPS tracking isn't implemented, 5 if basic tracking works but lacks error handling, and 10 if it includes comprehensive tracking with proper error handling and optimization.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the pace-based track coloring system implemented correctly?",
+      "description": "Review whether the code includes algorithms to calculate pace (min/km) in real-time and applies appropriate color mapping based on pace thresholds. Check if color transitions are smooth and if the system handles edge cases like extremely slow/fast paces or GPS jumps. Deduct 5 points if pace calculation is inaccurate, 3 points if color mapping is simplistic or hard-coded, and 2 points if there's no visual feedback during running.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the WeChat cloud development integration complete?",
+      "description": "Assess whether the code properly utilizes WeChat cloud services for storing run data, user authentication, and sharing functionality. Check if it implements proper data synchronization between local storage and cloud databases. Deduct 5 points if cloud storage isn't implemented, 3 points if authentication is missing, and 3 points if there's no offline support with synchronization logic.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the run session lifecycle management properly implemented?",
+      "description": "Evaluate whether the code handles the complete lifecycle of a run session: preparation, start, pause/resume, completion, and summary. Check if it properly manages background/foreground transitions and includes mechanisms to prevent accidental data loss. Deduct 5 points if pause/resume functionality is missing, 3 points if background tracking isn't handled properly, and 2 points if run completion lacks proper validation or summary.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as GPS signal loss, battery optimization interference, accidental app closure, 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. AI-generated running insights 2. Social sharing with customizable post templates 3. Integration with music apps for run soundtrack 4. Gamification elements like achievements or challenges). 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 location tracking methods used simultaneously) 2. Function modules unrelated to running tracking (e.g., unnecessary social features) 3. Fancy effects that affect performance and battery life (e.g., constant 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 tracking logic/UI/cloud service layers), component reusability, and mini program best practices. Deduct 5 points if global state pollution is found or if the code doesn't follow WeChat mini program development standards; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there's no error logging or performance monitoring. 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 WeChat mini program 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) 4) Consistent with WeChat's design language. Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic map-UI integration. 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) Start/stop button feedback delay ≤ 100ms 2) Map updates at minimum 1Hz during activity 3) Smooth transition between different screens 4) Intuitive gestures for map manipulation. Deduct 5 points for each operation without feedback, 3 points for laggy map rendering during tracking, and 5 points for hard-to-reach controls during running. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/word-memorization-flashcards.json

@@ -0,0 +1,68 @@
+{
+  "index": 439,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Ensure that the generated code is executable for demonstration. The task is to: implement a program that can identify words in a file, sort them, provide translations and example sentences for each word, and then help me generate an interactive HTML page with flashcards to aid word memorization.\n\n1. The page should be aesthetically pleasing, concise and intuitive, with 3D-rotating word cards and a button below to randomly switch to the next word\n2. Interactive buttons should function properly with a reasonable layout without any overlapping elements\n3. All words must be included, generated completely at once, without omissions",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the word identification and extraction functionality implemented correctly?",
+      "description": "Evaluate whether the code can accurately extract all unique words from a text file, ignoring punctuation and case sensitivity. Check if it properly handles special cases like contractions, hyphenated words, and various encodings. Score 0 if word extraction is missing, 5 if basic extraction exists but with edge case issues, 10 if comprehensive with proper text processing techniques.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the word sorting functionality implemented properly?",
+      "description": "Check if words are sorted alphabetically or by other meaningful criteria (frequency, length, etc.). Verify that the sorting algorithm handles all edge cases like non-ASCII characters and is efficient for large word lists. Score 0 if sorting is missing, 5 if basic sorting exists but with issues, 10 if properly implemented with clear sorting logic.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Are translations and example sentences provided for each word?",
+      "description": "Assess whether the code includes mechanisms to fetch translations and contextual example sentences (either through an API, embedded database, or other sources). Verify that translations are relevant and example sentences demonstrate proper word usage. Score 0 if missing, 5 if only translations exist without examples, 10 if both are comprehensively implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the 3D-rotating flashcard visualization implemented effectively?",
+      "description": "Evaluate whether the code properly implements 3D-rotating animations for the flashcards using CSS 3D transforms or JavaScript libraries. Check if the rotation reveals the word, translation, and example sentence in an intuitive manner. Score 0 if rotation is missing, 5 if basic rotation exists but appears janky or incomplete, 10 if smooth, natural rotation with proper perspective is achieved.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as empty files, extremely large word lists, network issues when fetching translations, invalid input formats, 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 learning experience (e.g., 1. Word pronunciation audio 2. Difficulty categorization for spaced repetition 3. Progress tracking system 4. Visual word associations/mnemonics). 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 sorting methods without purpose) 2. Function modules unrelated to vocabulary learning (e.g., built-in games not tied to word memorization) 3. Fancy effects that affect performance (e.g., complex animations that slow page loading). 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 data processing/UI rendering/user interaction logic), code 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 lacks comments or documentation. 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) Card flip/rotation animations complete within 500-800ms 2) Random word selection responds within 100ms 3) Clear visual cues for interactive elements. Deduct 5 points for each operation without feedback, 3 points for jerky animations, and 5 points if the random word selection button is not prominently displayed or easily accessible. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/zhejiang-high-school-chemistry-quiz-software.json

@@ -0,0 +1,68 @@
+{
+  "index": 1525,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the code you generate is executable for demonstration purposes. Please help create a quiz training software for the Chemistry Academic Level Qualification Examination (Academic Assessment) for first-year high school students in Zhejiang Province, focusing on multiple-choice questions.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the core quiz functionality implemented effectively?",
+      "description": "Review whether the code accurately implements the multiple-choice question system for Chemistry, including question presentation, answer selection, and result evaluation. Check if questions are correctly structured with chemistry-specific content (e.g., chemical formulas, reactions, principles). Score 0 if core functionality is missing, 5 if basic quiz features exist but lack chemistry specificity, and 10 if the system fully accommodates chemistry content with proper formatting.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the question database comprehensive and relevant to the Chemistry Academic Level Qualification Examination?",
+      "description": "Evaluate whether the implemented question database covers key topics from the Zhejiang Province first-year high school chemistry curriculum (e.g., atomic structure, periodic table, chemical bonds, basic reactions). Check for question variety and difficulty levels that match academic assessment standards. Deduct 5 points if topics are too generic, 5 points if content doesn't align with curriculum requirements, and 3 points if question variety is insufficient. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Does the application include performance analysis and learning progress tracking?",
+      "description": "Check for implementation of statistical analysis of student performance, including tracking correct/incorrect answers, time spent, difficulty assessment, and identifying knowledge gaps. Evaluate whether the system provides detailed feedback with explanations for wrong answers and suggests areas for improvement. Deduct 5 points if only basic scoring exists without analysis, and 3 points if feedback lacks educational value. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there an adaptive learning mechanism implemented?",
+      "description": "Assess whether the application adapts question difficulty based on user performance, implements spaced repetition for previously missed questions, and personalizes the learning path. Check if the algorithm effectively identifies and prioritizes weak areas. Deduct 5 points if questions appear randomly without adaptation, 3 points if the system lacks personalization features, and 3 points if there's no mechanism to reinforce difficult concepts. 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 invalid inputs, submission errors, data loading failures, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should effectively handle edge cases like disconnections during quiz submission or corrupted question data. Give 10 points if exception handling is comprehensive, 5 points if basic error handling exists, and 0 points if exceptions are unmanaged.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance learning (e.g., 1. Interactive molecular visualization for chemistry concepts 2. Voice-enabled question reading for accessibility 3. Chemistry formula editor/validator 4. AR-based molecular structure visualization). 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 operating in parallel) 2. Function modules unrelated to chemistry learning (e.g., games not tied to educational content) 3. Fancy effects that affect performance (e.g., unnecessary animations slowing question loading). 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/logic layers), unit test coverage, and build process automation. Check if chemistry-specific content rendering (formulas, equations) is properly abstracted. 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 modern educational software principles: 1) Harmonious color matching appropriate for extended study sessions (no more than 3 primary colors) 2) Proper layout spacing with clear question/answer distinction 3) Professional font system with proper rendering of chemistry notations and formulas (subscripts, superscripts, special symbols). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for poorly rendered chemical formulas. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the interface interactions support effective learning: 1) Question navigation response time ≤ 100ms 2) Clear visual feedback for answer selection 3) Smooth transitions between questions without disrupting concentration. Deduct 5 points for each operation without feedback, 3 points for laggy transitions between questions, and 5 points for confusing navigation that could disrupt the learning flow. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-entertainment/anime-website-creation.json

@@ -0,0 +1,68 @@
+{
+  "index": 1753,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure that the code you produce is executable for display. Help me create an anime website.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the basic website structure properly implemented?",
+      "description": "Review whether the HTML5 structure includes semantic tags (header, nav, main, section, footer), proper DOCTYPE declaration, and responsive meta tags. Check if the CSS follows a logical organization (reset/normalize, variables, components, layouts). Score 0 if the structure is chaotic, 5 if basic elements are present but poorly organized, and 10 if the structure is clean, semantic, and follows best practices.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the anime catalog and browsing functionality implemented?",
+      "description": "Evaluate the implementation of the anime catalog with filtering, sorting, and search capabilities. Check if the catalog displays essential information (title, cover image, rating, genres, release year) and provides pagination or infinite scrolling. Deduct 5 points if search functionality is missing, 3 points if filtering is limited, and 2 points if sorting options are inadequate. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the anime detail page and media player properly designed?",
+      "description": "Assess the detail page for comprehensive anime information (synopsis, episodes, characters, related anime) and a functional video player with essential controls (play/pause, volume, fullscreen, quality options). Score 0 if the detail page or player is missing, 5 if they exist but lack essential features, and 10 if both are fully featured and well-integrated.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there a user system with personalization features?",
+      "description": "Check for user authentication (signup/login), profile management, and personalization features such as watchlists, favorites, and watch history. Evaluate if the system includes recommendation algorithms based on user preferences. Deduct 5 points if authentication is insecure, 3 points if personalization features are missing, and 2 points if recommendations are not implemented. 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 failed API requests, missing images, slow network connections, etc.) and provide friendly error prompts or recovery mechanisms. Check for input validation, error handling for API calls, and fallback content. 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. Dark/light theme toggle 2. Seasonal anime calendar visualization 3. Character relationship graphs 4. Episode screenshot previews 5. Voice actor profiles with other works). 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 carousel components with different code) 2. Function modules unrelated to anime website (e.g., news ticker unrelated to anime) 3. Fancy effects that affect performance (e.g., excessive parallax effects or 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 component-based architecture, separation of concerns), state management implementation, code reusability, and build process. Deduct 5 points if global state is managed poorly; deduct 3 points if components are tightly coupled; deduct 2 points if the code duplication rate is high (over 30%). Check for proper use of async/await or Promises for API calls. 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 modern anime website aesthetics: 1) Cohesive color scheme aligned with anime themes 2) Proper card layouts with consistent spacing (8px grid system) 3) Typography hierarchy with readable fonts (min 14px for body text) 4) Appropriate use of imagery and thumbnails. Deduct 3 points for cluttered layouts, 4 points for poor visual hierarchy, and 3 points for inconsistent styling across pages. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects enhance user experience: 1) Page transitions under 300ms 2) Loading states for async operations 3) Hover/click animations that provide feedback 4) Smooth scrolling behavior 5) Mobile touch gestures support. Deduct 3 points for jarring transitions between pages, 3 points for missing loading indicators, 2 points for unresponsive UI elements, and 2 points for poor mobile interaction design. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Web Visuals",
+  "difficulty": "hard"
+}