@getollie/cli 0.0.1

package/library/web_applications-education_learning/shang-han-lun-tcm-diagnostic-app.json

@@ -0,0 +1,68 @@
+{
+  "index": 1475,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Ensure that the code you generate is executable for demonstration. Study the original text of the Treatise on Cold Damage Disorders (Shang Han Lun), and help me develop a simple Traditional Chinese Medicine diagnostic app based on the Shang Han Lun.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the Traditional Chinese Medicine (TCM) diagnostic system accurately implemented?",
+      "description": "Review whether the code accurately implements the diagnostic patterns from Shang Han Lun, including the Six Stages (六经) diagnostic framework and proper syndrome differentiation. Score 0 if the core diagnostic logic is missing, 5 if basic patterns are implemented but incomplete, and 10 if comprehensive diagnostic pathways are included with accurate symptom-to-pattern mapping.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the symptom input and analysis system well-designed?",
+      "description": "Check whether the app includes a comprehensive symptom collection interface with proper categorization (e.g., pulse types, tongue diagnosis, temperature sensations, etc.). The system should use weighted algorithms to analyze symptom combinations. Deduct 5 points if critical symptoms from Shang Han Lun are missing, and 3 points if the symptom relationships don't reflect traditional diagnostic principles. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the herbal formula recommendation engine properly implemented?",
+      "description": "Evaluate whether the code correctly maps diagnosed patterns to the classical formulas from Shang Han Lun, with proper dosage calculations and contraindications. Must include at least 20 core formulas with their modifications. Deduct 5 points if formula compositions are inaccurate, and 3 points if the modification rules don't follow traditional principles. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the progression/transformation of disease patterns accurately modeled?",
+      "description": "Check whether the app models the dynamic nature of cold damage disorders according to Shang Han Lun, including the progression through different stages and transformations between syndromes. Score 0 if this core concept is missing, 5 if basic progression is implemented but lacks detail, and 10 if the system fully captures the complex transformations and transmissions described in the classic text.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as incomplete symptom input, contradictory symptoms, unusual symptom combinations, etc.) and provide appropriate guidance or clarifying questions. Code with strong robustness should gracefully handle edge cases in diagnosis, 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. Interactive tongue and pulse diagnosis tools 2. Historical case studies from the text 3. Visualization of the Six Stages progression 4. Personalized treatment timelines). 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 diagnostic methods 2. Function modules unrelated to Shang Han Lun diagnosis (e.g., unrelated modern medical tests) 3. Fancy effects that detract from clinical utility. Deduct 3 points for each redundancy found, and directly deduct 10 points if the core TCM diagnostic 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 diagnostic logic/view/data layers), test coverage for different diagnostic scenarios, and localization support for TCM terminology. 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 proper documentation for TCM concepts. 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 both modern design principles and traditional Chinese aesthetic sensibilities: 1) Harmonious color palette appropriate for a medical application 2) Proper layout with clear hierarchy of information 3) Professional typography with appropriate use of both modern and classical Chinese characters when needed. Deduct 3 points for cluttered diagnostic screens, 5 points for inappropriate color schemes for a medical app, and 5 points for poor information architecture. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the diagnostic interaction intuitive and educational?",
+      "description": "Judge whether the app guides users through the diagnostic process in an intuitive way: 1) Clear step-by-step progression through diagnostic questions 2) Educational explanations of TCM concepts 3) Appropriate visualizations of patterns and relationships from Shang Han Lun. Deduct 5 points for confusing diagnostic flows, 3 points for lack of explanations of TCM terminology, and 5 points for missing connections to the original text. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/side-by-side-translation-comparison-reading.json

@@ -0,0 +1,68 @@
+{
+  "index": 735,
+  "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. I want to implement a side-by-side translation comparison for reading!",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the side-by-side translation comparison layout fully implemented?",
+      "description": "Review whether the code accurately implements a dual-pane layout system through HTML/CSS/JavaScript, including responsive design for different screen sizes, synchronized scrolling between source and target text panels, and proper text alignment mechanisms. Score 0 if basic dual-pane structure is missing, 5 if only static layout is implemented without synchronization, and 10 if includes advanced features like paragraph-level alignment and mobile-responsive design.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the text input and processing functionality comprehensive?",
+      "description": "Check whether the implementation supports multiple text input methods (manual input, file upload, URL fetching), proper text parsing and segmentation (sentence/paragraph level), and format preservation. Evaluate if it handles various text formats (plain text, markdown, HTML). Deduct 5 points if file upload is not supported, 3 points if text segmentation is poorly implemented. Full score requires support for at least 3 input methods with proper error handling.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the translation integration and management system robust?",
+      "description": "Evaluate whether the system integrates with translation APIs (Google Translate, DeepL, etc.) or provides manual translation input capabilities. Check if it includes translation caching, batch processing for large texts, and translation quality indicators. Deduct 5 points if no API integration exists, 3 points if caching mechanism is missing. Requires proper API key management and fallback mechanisms for service failures.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are the reading assistance and navigation features complete?",
+      "description": "Check whether the code includes comprehensive reading aids such as text highlighting, bookmarking, progress tracking, search functionality across both languages, and export capabilities (PDF, text files). Evaluate if it provides reading statistics and customizable reading preferences. Deduct 5 points if search functionality is missing, 3 points if no progress tracking exists. Give 10 points if includes advanced features like reading speed analysis and custom note-taking.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as API failures, large text processing, network interruption, invalid file formats, encoding issues, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should gracefully handle edge cases like empty inputs, malformed text, and service timeouts, 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. Real-time dictionary lookup on hover 2. AI-powered reading comprehension questions 3. Voice narration for both languages 4. Collaborative annotation system 5. Reading analytics dashboard). 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 text processors coexisting) 2. Function modules unrelated to translation comparison (e.g., built-in games or social media integration) 3. Fancy effects that affect reading performance (e.g., distracting animations during text display). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core reading 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 translation logic/UI components/data management layers), proper state management, and build process automation. Deduct 5 points if global state pollution is found or component architecture is poorly structured; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if no proper dependency management or build process exists. The full score requires clean architecture with proper separation of concerns.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface vision meet professional reading application standards?",
+      "description": "Evaluate whether the design optimizes reading experience: 1) High contrast text with proper background colors for extended reading 2) Typography system with adjustable font sizes (minimum 14px, maximum 24px) and line heights (1.4-1.8x) 3) Proper spacing between translation panels (minimum 20px gap) 4) Reading-friendly color scheme without eye strain. Deduct 3 points for each readability issue, 5 points for poor contrast ratios, and 5 points for cramped text layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the reading interaction smooth and intuitive?",
+      "description": "Judge whether the reading interactions enhance user experience: 1) Smooth synchronized scrolling between panels with minimal lag (<50ms) 2) Quick text selection and highlighting responses 3) Intuitive navigation controls with keyboard shortcuts support 4) Seamless switching between different view modes. Deduct 5 points for each laggy interaction, 3 points for missing keyboard shortcuts, and 5 points for non-intuitive navigation patterns. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/spelling-flashcards-apple-cat-dog.json

@@ -0,0 +1,68 @@
+{
+  "index": 1751,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate, professional responses. Be sure to ensure that the code you generate is executable for demonstration. Please help me create code for spelling flashcards for the words \"apple,\" \"cat,\" and \"dog.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the basic flashcard functionality implemented?",
+      "description": "Check whether the code implements the core flashcard functionality for displaying the words 'apple', 'cat', and 'dog'. Verify that each word can be shown individually as a flashcard with clear visibility. Score 0 if functionality is missing, 5 if basic display is implemented, and 10 if the implementation includes proper card rotation/switching.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the spelling practice interaction implemented?",
+      "description": "Evaluate whether users can practice spelling the words through interaction. Check if there's input validation that compares user input against the correct spelling, with appropriate feedback for correct/incorrect answers. Score 0 if no spelling practice exists, 5 if basic input exists without validation, and 10 if complete validation with feedback is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is a complete flashcard navigation system implemented?",
+      "description": "Assess whether the code includes controls to navigate between flashcards (previous/next buttons, swipe functionality, or keyboard shortcuts). Check if the navigation system handles edge cases like reaching the first/last card. Deduct 5 points if navigation is partial or buggy, and 3 points if edge cases aren't handled properly.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there a progress tracking or scoring mechanism?",
+      "description": "Examine whether the code tracks user progress with the flashcards, such as recording correct/incorrect attempts, showing a progress bar, or implementing a scoring system. Score 0 if no tracking exists, 5 if basic tracking is implemented, and 10 if comprehensive statistics with visual representation are included.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as invalid inputs, browser compatibility issues, or unexpected user interaction patterns) 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. Audio pronunciation of words 2. Visual hints or images associated with words 3. Spaced repetition algorithm for word review). 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 display the same flashcard) 2. Function modules unrelated to flashcards (e.g., a built-in calculator) 3. Fancy effects that affect performance (e.g., excessive animations that slow down card transitions). 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 flashcard data/view/controller), code organization, 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) 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 card flips, 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/spring-wellness-guide-march-12-2025.json

@@ -0,0 +1,68 @@
+{
+  "index": 1782,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Spring Wellness Guide for March 12, 2025 🌿\nSeize the golden period to nourish your liver, support yang energy, and revitalize! 🌸\n\n## ✨ Today's Wellness Focus ✨\nIn March, liver fire easily flares up and temperature fluctuations increase risk of colds! Do these 5 things to maximize your health 👇\n\n## 🍵 Nutritional Guide: Eat the right colors to stay youthful!\n✅ Breakfast: Red date and goji berry millet porridge (warms the spleen and stomach)\n✅ Lunch: Stir-fried asparagus + Chinese toon egg scramble (high fiber, high protein)\n✅ Afternoon tea: Rose and chrysanthemum tea (soothes liver and relieves stress + antioxidant)\n⚠️ Avoid: Less sour, more sweet foods; reduce lamb hot pot which can cause internal heat!\n\n## 🌳 Special Arbor Day Activity\nBetween 3:00-5:00 PM when yang energy is strongest, visit a park for brisk walking/plant greenery, breathe in fresh wood energy to help liver qi flourish~\n\n## 💤 Sleep Rules\nSleep before 11 PM! Soak feet before bed (mugwort + fresh ginger slices), paired with Yongquan acupoint massage—excellent for expelling cold and aiding sleep!\n\n## 🌬️ Wind Prevention and Anti-allergy Measures\n🌼 Wear masks and windproof jackets when going out; allergy-prone individuals should keep loratadine handy\n💦 Drink 8 glasses of water (can add honey and dried tangerine peel to soothe the throat)\n\n## 🌞 Back-Sunning Technique\nChoose 10 AM or 3 PM sunlight, turn your back to the sun for 20 minutes—supplements calcium, eliminates dampness, and boosts immunity!\n\n## 💌 Wellness Tip:\nDon't rush to reduce layers in spring! Use the onion dressing method: base layer + cardigan + jacket to handle 10°C temperature differences~\n\n#SpringWellness #ArborDayHealthAction #90sGenerationWellnessDiary #LiverQiCirculation #AntiAllergyStrategies\n\n📌 Recommended today: Drink flower tea, sunbathe your back, plant greenery\n📌 Avoid today: Staying up late binge-watching, excessive exercise, fried foods",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the wellness guide content accurately structured and properly formatted?",
+      "description": "Evaluate whether the code properly structures the wellness guide with clear section headings, proper hierarchical organization, and consistent formatting. Check if HTML semantic elements (header, section, article) are used appropriately, and if styling provides clear visual hierarchy between main sections, subsections, and content items. Score 0 if structure is chaotic, 5 if basic structure exists but lacks semantic HTML, 10 if fully organized with proper HTML5 semantic elements.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Are interactive wellness tracking elements implemented?",
+      "description": "Check if the implementation includes interactive elements like checkboxes for daily wellness tasks, activity timers for the Arbor Day activities, or progress trackers for water consumption. Evaluate whether these elements store user progress (localStorage) and provide visual feedback when completed. Deduct 5 points if no interactive elements exist, 3 points if they exist but don't save user progress. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is there a time-sensitive content display mechanism?",
+      "description": "Assess whether the code implements date-aware content that recognizes the current date (relative to March 12, 2025) and adjusts recommendations accordingly. Check if there's a countdown to the special Arbor Day activity time window (3:00-5:00 PM) and notifications/reminders for optimal activities based on time of day. Deduct 5 points if no date awareness exists, 3 points if only basic date checking is implemented. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there personalization functionality for wellness recommendations?",
+      "description": "Evaluate whether the code allows users to input personal health information (allergies, health conditions, age) and adjusts recommendations accordingly. Check for preference settings that remember dietary restrictions, wellness goals, or climate adaptations. Deduct 5 points if no personalization exists, 3 points if only basic preference settings without recommendation adjustment. 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 browser compatibility issues, offline usage, timezone differences affecting recommendations, incorrect user inputs) 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. Animation showing optimal sunbathing position 2. Interactive meridian point map for acupressure guidance 3. Seasonal ingredient availability 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 date checking mechanisms) 2. Function modules unrelated to wellness guidance (e.g., a built-in game) 3. Fancy effects that affect performance (e.g., excessive animations that slow 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/view/controller 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 traditional Chinese medicine aesthetics and modern design principles: 1) Harmonious color matching (natural greens/browns with seasonal accent 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 for wellness activities timing. 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 wellness tracking functions. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/star-trail-app-wechat-mini-program.json

@@ -0,0 +1,68 @@
+{
+  "index": 844,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Design and Implementation of \"Star Trail\" App Based on WeChat Mini Program\n\nYou are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the generated code is executable whenever possible. This concerns the design and implementation of the \"Star Trail\" app based on WeChat Mini Program.\n\nThe app allows users to set habit goals (such as early rising, reading, exercising, etc.), check in daily to record completion status, generates habit formation progress charts, provides habit-related knowledge and tips, includes reminder functionality, and supports social sharing and friend interaction encouragement. Complete code required.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Habit Goal Setting Functionality",
+      "description": "Evaluate whether the code implements comprehensive habit goal setting features including habit categories, frequency settings (daily/weekly/custom), start date, end date, reminder time, and personalized icons/colors for different habits.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Check-in and Progress Tracking System",
+      "description": "Review the implementation of the daily check-in mechanism, streak counting, and progress visualization. Check if the code handles edge cases like timezone differences, backdated check-ins, or missed days properly.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Data Visualization Components",
+      "description": "Examine the implementation of progress charts and statistics visualization. Check for different chart types (line charts, heat maps, radar charts), time range selectors, and interactive elements in the visualization.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Notification and Reminder System",
+      "description": "Assess the implementation of the reminder functionality, including scheduled notifications, customizable reminder messages, snooze options, and compliance with WeChat Mini Program notification constraints.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Code Robustness",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as network interruptions, permission denials, data inconsistencies) and provide friendly error prompts or recovery mechanisms.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Innovative Features",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. AI-powered habit recommendations 2. Gamification elements like badges/achievements 3. Intelligent streak recovery options 4. Habit correlation analysis).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Feature Redundancy",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementations of similar functions (e.g., multiple notification systems) 2. Function modules unrelated to habit tracking 3. Fancy effects that affect performance in low-end devices.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Engineering Quality",
+      "description": "Review modular design (separation of UI components, business logic, and data layer), component reusability, unit test coverage, and Mini Program best practices implementation.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Interface Design Quality",
+      "description": "Evaluate whether the overall design follows modern mobile design principles: 1) Harmonious color matching suitable for a habit tracking app 2) Proper layout spacing optimized for various screen sizes 3) Professional typography system with clear visual hierarchy 4) Accessibility considerations for diverse users.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Interaction Fluidity and User Experience",
+      "description": "Judge whether the dynamic effects conform to WeChat Mini Program best practices: 1) Responsive touch feedback 2) Smooth transitions between pages 3) Intuitive navigation patterns 4) Social sharing implementation quality 5) Friend interaction mechanisms.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/streamlit-ocr-math-solver-app.json

@@ -0,0 +1,68 @@
+{
+  "index": 257,
+  "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. You are a team of software programming masters working together on this project.\n\nUsing the Streamlit framework, build a user-friendly OCR application that can recognize various mathematical content symbols and formulas, including geometric patterns, and then have AI solve the mathematical problems through a web UI program.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the OCR functionality for mathematical content properly implemented?",
+      "description": "Evaluate whether the code implements OCR capabilities specifically optimized for mathematical notation (including operators, fractions, exponents, integrals, etc.). Check if it uses appropriate libraries like Tesseract with math-specific training data or specialized math OCR solutions like Mathpix. Score 0 if no OCR is implemented, 5 if basic text OCR is implemented without math optimization, and 10 if it handles complex mathematical notations effectively.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Does the application recognize and process geometric patterns?",
+      "description": "Review whether the code includes computer vision capabilities to identify geometric shapes (circles, triangles, rectangles, etc.) and convert them to mathematical representations. Check if it implements contour detection, shape recognition algorithms, and geometric property extraction. Score 0 if geometric pattern recognition is absent, 5 if only basic shapes are detected without proper mathematical interpretation, and 10 if it can identify complex geometric configurations with proper mathematical analysis.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the AI problem-solving component effectively implemented?",
+      "description": "Assess whether the code connects to an appropriate AI model (like OpenAI API, local mathematical solver, etc.) and properly structures the recognized mathematical problems for solving. Check if the system can handle various types of math problems (algebraic equations, calculus, geometry). Deduct 5 points if the AI component only works for limited problem types, and 3 points if it doesn't provide step-by-step solutions. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the Streamlit UI functionality complete and user-friendly?",
+      "description": "Evaluate whether the Streamlit interface implements all necessary components: image upload, OCR result display, problem formulation confirmation, solution display, and error handling. Check if the UI flow is logical and intuitive. Deduct 5 points if critical components are missing, and 3 points if the UI flow is confusing or requires unnecessary steps. 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 unclear images, unrecognizable mathematical symbols, invalid inputs, network interruptions, 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. Real-time formula rendering as LaTeX 2. Image preprocessing options to improve OCR accuracy 3. History of solved problems with export functionality). 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 preprocessing steps that don't improve OCR accuracy 2. Function modules unrelated to mathematical OCR or problem-solving 3. Excessive UI components that complicate the user experience. 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 OCR/AI solving/view layers), error handling, logging, 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 configuration isn't properly externalized. 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) Processing feedback indicates activity during OCR and AI solving 2) Transition animations for state changes are controlled between 300-500ms 3) Clear visual focus guidance between steps. Deduct 5 points for each operation without feedback, 3 points for jarring transitions between application states, and 5 points for confusing workflow progression. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/student-id-verification-webpage.json

@@ -0,0 +1,68 @@
+{
+  "index": 1820,
+  "question": "You are a code expert. Please use your specialized knowledge to generate accurate and professional responses. Ensure that the code you generate is executable for demonstration. This is downloaded student information, and now students need to verify the information. To ensure information security, please output a web page code with functionality that requires students to enter their student ID to view their own information.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the student ID verification system properly implemented?",
+      "description": "Check if the code implements a secure verification mechanism that only allows students to access their own information after entering a valid student ID. Score 0 if there's no verification logic, 5 if basic verification exists but has security flaws, and 10 if the verification is robust with proper validation patterns and error handling.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the student information data structure well-designed?",
+      "description": "Evaluate whether the code includes a proper data structure for storing student information (e.g., array of objects, Map, or database connection). Check if it includes essential fields like name, ID, major, etc. Deduct 3 points if missing critical fields, 3 points if using inefficient data structures, and 5 points if no clear structure is defined. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the information display system implemented correctly?",
+      "description": "Verify that after successful ID verification, the system properly displays only the relevant student's information. Check if the display is organized, complete, and doesn't leak other students' data. Deduct 5 points if all student data is exposed in client-side code, 5 points if information display is incomplete, and 3 points if the display mechanism has glitches. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are security measures implemented to protect student data?",
+      "description": "Assess whether appropriate security measures are in place, such as input sanitization, prevention of client-side data exposure, protection against XSS attacks, and CSRF protection. Deduct 3 points for each missing essential security feature. Give 10 points only if comprehensive security measures are implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as invalid student IDs, empty input, special characters, 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. Two-factor authentication 2. Session timeout for security 3. Progressive information disclosure 4. Information edit functionality with validation). 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 verification methods coexisting) 2. Function modules unrelated to student information verification (e.g., a built-in calculator) 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 data/view/controller layers), code organization, 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 there are no 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) 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 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": "easy"
+}

package/library/web_applications-education_learning/student-preview-assignment-with-answer-check.json

@@ -0,0 +1,68 @@
+{
+  "index": 1432,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to ensure that the generated code is executable for demonstration. Based on the above content, please help me create a directly runnable web page for a preview assignment where students can check their answers after completion and generate a compilation of their incorrect answers.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the core preview assignment system implementation complete?",
+      "description": "Review whether the code implements a functional preview assignment system with question display, answer input, and validation mechanisms. Score 0 if these core components are missing, 5 if basic functionality exists with limitations, and 10 if the system has comprehensive question types (multiple choice, text input, matching, etc.) with proper validation logic for each type.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the answer checking functionality properly implemented?",
+      "description": "Evaluate the answer validation system - check if it properly compares student responses against correct answers with appropriate tolerance for text-based answers (case sensitivity, whitespace handling, etc.). Deduct 5 points if the validation is too strict or too lenient, 3 points if it lacks feedback on why an answer is incorrect. Give 10 points for sophisticated validation with partial credit capabilities.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the incorrect answers compilation feature implemented effectively?",
+      "description": "Assess whether the system correctly identifies, stores, and compiles incorrect answers in an organized manner. Check if it shows the student's answer alongside the correct answer with appropriate explanations. Deduct 5 points if only basic compilation exists without categorization, 3 points if it lacks visual distinction between correct/incorrect portions of answers. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is there a complete user progress tracking system?",
+      "description": "Check if the code includes functionality to track user progress through the assignment, including completion status, score calculation, and session persistence (local storage). Deduct 5 points if there's no way to save progress, 3 points if analytics on student performance patterns are missing. Full score of 10 points requires comprehensive progress tracking with visualization of performance metrics.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as unexpected input formats, browser compatibility issues, storage limitations) 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. Adaptive difficulty based on performance 2. Interactive hints system 3. Visual progress indicators that motivate completion). 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 answer validation methods) 2. Function modules unrelated to the assignment system (e.g., unnecessary animations) 3. Fancy effects that affect performance (e.g., heavy graphics that slow loading times). 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/data layers), script organization, and maintenance considerations. Deduct 5 points if global variable 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 question-answer layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and intuitive?",
+      "description": "Judge whether the interface interactions conform to user expectations: 1) Clear feedback when submitting answers ≤ 100ms 2) Smooth transitions between questions 300-500ms 3) Intuitive navigation between sections. Deduct 5 points for each operation without feedback, 3 points for confusing navigation, and 5 points for hard-to-find essential functions (like submit or review). The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}