@getollie/cli 0.0.1

package/library/web_applications-education_learning/vocabulary-learning-app.json

@@ -0,0 +1,68 @@
+{
+  "index": 1248,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and expert responses. Make sure the generated code is executable when possible. Task description:\n\nI need you to develop a vocabulary learning app from scratch using React Native + FastAPI + SQLite, supporting features like offline learning, review, and difficult word categorization. Please develop strictly according to the following requirements.\n\n📌 Technical Requirements:\n\nFrontend: React Native (using Expo)\n\nBackend: FastAPI\n\nDatabase: SQLite (supporting offline storage)\n\nFrontend animations: Using react-native-reanimated\n\nData storage: Using AsyncStorage to store user progress, supporting offline learning\n\nState management: Using useContext or Redux Toolkit (as needed)\n\nBackend deployment: Render\n\n📌 Main App Functions:\n1️⃣ Course Management\n\nDisplay course list in HomeScreen, each course includes name, vocabulary count, a progress bar, 2 small circles or other elements to show the number of difficult words and words needing review\n-Have a \"create a new course\" button to help create new courses (displays a small screen with course name and save button)\nSupport course download, allowing users to learn offline\n\nSupport course deletion, but with confirmation prompts to avoid accidental deletion\n\nSupport course selection, all learning modes will load data based on the user's selected course\n\n2️⃣ Learning New Words (LearningScreen)\n\nAutomatically selects 5 new words each time you enter\n-When learning a new word, first displays a word card (wordscreen)\n\nUsers must answer correctly 5 times for each word before it enters the review library\n\nIf answered incorrectly, correct answer count doesn't accumulate\n\nIf users exit midway, progress is reset\n\nSupport 4 learning modes:\n\n4-choice quiz (select definition)\n\n4-choice quiz (select word)\n\n4-choice quiz (select correct pronunciation) (if the word has no pronunciation, this won't be offered)\n\nSpelling mode (10 characters are displayed below (including the word's characters), select the correct characters; there's a hint button that shows one character (for example, for the word \"不错\", if the user hasn't selected \"不\" yet, clicking hint will display \"不\", if the user has already selected \"不\" then it will show \"错\" and continue to the next question; there's also an \"I don't know\" button that directly shows the result (counted as incorrect))\n\n3️⃣ Quick Practice (QuickPracticeScreen)\n\nQuick practice & review share the same word library\n\nOptimize UI to prevent users from mistakenly thinking there are 5 answers\n-Upon entering, there's a 60-second countdown to 0, users do 4-choice quizzes (reference 4-choice quizzes in learning screen) (vocabulary comes from review), unlimited questions until 3 wrong answers or time reaches 0.\n\n4️⃣ Review Function (ReviewScreen)\n-Each time you enter, 25 words are selected for review (according to the learning algorithm), one question per word, wrong answers will trigger another question for the same word (can display questions for this word later), until all are completed.\n\nReview includes 4 question types:\n\n4-choice quiz (select definition)\n\n4-choice quiz (select word)\n\n4-choice quiz (select correct pronunciation)\n\nSpelling mode (10 characters are displayed below (including the word's characters), select the correct characters; there's a hint button that shows one character (for example, for the word \"不错\", if the user hasn't selected \"不\" yet, clicking hint will display \"不\", if the user has already selected \"不\" then it will show \"错\" and continue to the next question; there's also an \"I don't know\" button that directly shows the result (counted as incorrect))\n\n5️⃣ Difficult Word Review (DifficultWordsScreen)\n-Upon entering, 5 difficult words are selected, 5 questions per word, wrong answers add one more question for that word, until all are completed.\n\nDifficult word review includes 4 question types (same as review function)\n-For each word, must answer correctly three times to return to the review vocabulary library.\n\n6. Effective for all learning modes (except exceptions)\n\nWhen answered incorrectly, directly displays the word card for this word, with a \"next question\" button below (not applicable to quick learning)\n\nWhen answered incorrectly, shows the correct answer (correct answer turns green, wrong answer turns red)\n\nWhen answered correctly, uses bright green (enhanced visual feedback), then directly proceeds to the next question\n-In all modes, each question has a delete button at the top (directly removes this word from the course) and a difficult word flag (directly adds to difficult words)\n-Questions initially don't show pinyin, but after completion (whether right or wrong) pinyin is displayed (below the question)\nAudio support: If a word has audio, each question automatically plays audio (except for 4-choice quiz (select correct pronunciation)\n\n7. Word Explanation (WordScreen)\n-Displays word information here (vocabulary, pinyin, meaning, examples, a button to play word pronunciation)\n\n8. Courses (CourseScreen)\n-Accessed by clicking a course in course management\n-Has an \"add file\" button for uploading CSV files\n-Displays course vocabulary, difficult words and review words count, 200 words per page\n-Clicking a word here enters that word's card (WordScreen)\n-Each word can be individually deleted\n-Words categorized as difficult have a small indicator\n\n8. Learning Algorithm\n\nSRS Algorithm Core Logic\n\n1. Core Variables\n\nDifficulty coefficient (D): Initial value 0, range [0, 1].\n\nInterval (I): Initial value 1 day.\n\nPerformance score (S): User rating, range [0, 5].\n\nEase factor (EF): Initial value 2.5, range [1.3, 2.5].\n\n2. Algorithm Formula\n\nEase factor (EF) update:\n\nEF_new = EF_old + (0.1 - (5 - S) * (0.08 + (5 - S) * 0.02))\n\nIf EF_new < 1.3, then EF_new = 1.3.\n\nIf EF_new > 2.5, then EF_new = 2.5.\n\nInterval (I) calculation:\n\nIf S ≥ 3:\n\nI_new = I_old * EF_new\n\nIf S < 3:\n\nI_new = I_old * 0.5\n\nDifficulty coefficient (D) update:\n\nD_new = D_old + (0.1 - (5 - S) * 0.02)\n\nIf D_new < 0, then D_new = 0.\n\nIf D_new > 1, then D_new = 1.\n\n3. Data Structure\n\nLearning unit table:\n\n{ \"id\": \"123\", \"content\": \"apple\", \"translation\": \"苹果\", \"audio\": \"apple.mp3\", \"image\": \"apple.jpg\", \"tags\": [\"fruit\", \"basic\"] }\n\nUser progress table:\n\n{ \"user_id\": \"456\", \"unit_id\": \"123\", \"last_reviewed\": \"2023-10-01\", \"next_review\": \"2023-10-08\", \"interval\": 7, \"score\": 3, \"difficulty\": 0.3, \"ease_factor\": 2.0 }\n\n4. Review Queue Generation\n\nDaily review queue:\n\nQuery all learning units where next_review ≤ current date.\n\nSort by priority:\n\nLearning units with lower ratings have priority.\n\nLearning units with shorter intervals have priority.\n\nNew learning queue:\n\nRecommend a certain number of new learning units for users daily (e.g., 5).\n\n5. Algorithm Implementation Steps\n\nFirst-time learning:\n\nInitialization:\n\nI = 1, D = 0, EF = 2.5 next_review = today + I\n\nUser practice:\n\nAfter users complete practice, input performance score S.\n\nUpdate algorithm:\n\nUpdate ease factor EF.\n\nUpdate interval I.\n\nUpdate difficulty coefficient D.\n\nUpdate next review time next_review.\n\nSave data:\n\nSave updated I_new, EF_new, D_new, next_review to user progress table.\n\n📌 Other Requirements:\n✅ Ensure UI is strictly user-friendly, beautiful (must research), interactive, with smooth animations (this part must be researched, very important)\n✅ Ensure changes are compatible with existing functions, not affecting user experience\n-Main color: dark blue, research appropriate colors (research color palette, etc.)",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the React Native + FastAPI + SQLite integration complete?",
+      "description": "Review whether the codebase fully integrates all three required technologies. Check if React Native frontend (using Expo) can communicate with FastAPI backend, if SQLite database is properly implemented with schema supporting all data requirements, and if offline functionality works through AsyncStorage. Score 0 if any major component is missing, 5 if basic integration exists but with significant gaps, and 10 if all technologies are seamlessly integrated with proper error handling between layers.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the course management system fully implemented?",
+      "description": "Evaluate whether the HomeScreen displays all required course elements (name, vocabulary count, progress bar, difficult words indicator, review indicator), and if the create/download/delete course functions work properly. Check if course selection affects all learning modes correctly. Deduct 3 points if visual indicators are missing, 3 points if any CRUD operation fails, and 4 points if course selection doesn't properly cascade to learning modes. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Are all learning modes implemented according to specifications?",
+      "description": "Check if all 4 learning modes (two 4-choice quizzes, pronunciation quiz, and spelling mode) are implemented with the specified logic (5 correct answers to enter review library, progress reset on exit). Verify the hint system in spelling mode functions as described. Deduct 2 points for each incorrectly implemented mode, 3 points if progress tracking is broken, and 3 points if the hint system doesn't work as specified. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the SRS learning algorithm correctly implemented?",
+      "description": "Analyze the implementation of the specified spaced repetition algorithm, checking if all core variables (difficulty coefficient, interval, performance score, ease factor) are properly calculated and stored. Verify that review queues are generated correctly based on the formula. Deduct 3 points if formula implementation is incorrect, 3 points if data persistence is faulty, and 4 points if the review queue generation logic doesn't prioritize as specified. 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 interruption, data inconsistency between offline and online modes, invalid user inputs, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should handle offline mode gracefully, implement proper error boundaries in React components, and include API fallbacks. Give 10 points if all edge cases are handled, 5 points if basic error handling exists, and 0 points if critical edge cases are ignored.",
+      "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. Gamification elements beyond requirements 2. Audio recording for pronunciation comparison 3. Visual learning aids like mnemonics 4. Social sharing of progress). 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 state management solutions coexisting) 2. Function modules unrelated to vocabulary learning (e.g., a built-in general calculator) 3. Fancy effects that affect performance (e.g., excessive animations that slow down the learning 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 (separation of UI components, business logic, and data layer), code reuse patterns for similar learning modes, proper TypeScript types, and build process automation. Deduct 5 points if global state is overused instead of component composition; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if proper CI/CD for both frontend and backend is missing. 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 the dark blue color scheme requirements and modern design principles: 1) Harmonious color palette with proper contrast ratios 2) Consistent spacing and alignment across screens 3) Professional typography system with proper hierarchy. Deduct 3 points for inconsistent UI elements, 5 points for poor color contrast affecting accessibility, and 5 points for chaotic layout causing cognitive overload. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the animation system smooth and enhancing user experience?",
+      "description": "Judge whether react-native-reanimated is properly implemented for smooth animations: 1) Transition animations between screens 2) Feedback animations for correct/incorrect answers 3) Progress indicators with fluid motion 4) Card flip or reveal animations for word learning. Deduct 3 points for janky animations that drop frames, 4 points for missing animations in key interactions, and 3 points if animations distract from rather than enhance learning. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "hard"
+}

package/library/web_applications-education_learning/vocabulary-learning-webpage.json

@@ -0,0 +1,68 @@
+{
+  "index": 1727,
+  "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. Please help me create an HTML program for a vocabulary learning webpage that has an attractive interface, high recognizability, and is easy to operate.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the vocabulary learning system's core functionality implemented?",
+      "description": "Review whether the code implements essential vocabulary learning features such as word display, definitions, examples, and some form of learning/testing mechanism. Score 0 if there's no vocabulary display functionality, 5 if only basic word display is implemented, and 10 if comprehensive vocabulary learning features (including word display, definitions, usage examples, and testing mechanisms) are included.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the vocabulary storage and retrieval mechanism designed effectively?",
+      "description": "Check how vocabulary data is stored and retrieved. Look for structured data organization (arrays/objects), potential for persistent storage (localStorage/IndexedDB), and efficient data loading mechanisms. Deduct 5 points if vocabulary is hardcoded with no data structure, 3 points if there's no mechanism to add new words. Award full 10 points for a well-structured data model with persistence capabilities.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Does the page implement any learning optimization techniques?",
+      "description": "Evaluate whether the implementation includes educational techniques like spaced repetition, flashcards, progress tracking, or personalized learning paths. Deduct 5 points if no learning optimization is implemented, 3 points if only basic review functionality exists. Give full 10 points for sophisticated learning algorithms that adapt to user progress.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the user interaction for vocabulary practice well designed?",
+      "description": "Assess the implementation of interactive practice features like quizzes, matching exercises, fill-in-the-blanks, or pronunciation practice. Evaluate if the code provides immediate feedback on user inputs and tracks progress. Score 0 if no practice features exist, 5 for basic quizzing, and 10 for multiple engaging practice modes with feedback systems.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as empty vocabulary lists, invalid user inputs, browser compatibility 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 vocabulary learning experience (e.g., 1. Audio pronunciation 2. Visual mnemonics 3. Gamification elements 4. Social sharing capabilities). 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 test the same vocabulary) 2. Function modules unrelated to vocabulary learning (e.g., a built-in calculator) 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 learning 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/UI/logic layers), code organization, and maintainability. Deduct 5 points if global variables are overused or if there's no separation of concerns; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there's no consideration for scalability or future enhancements. 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) 4) Clear visual hierarchy for learning content. Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance for vocabulary learning flow. Deduct 5 points for each operation without feedback, 3 points for disruptive animations during learning sessions, and 5 points for hard-to-find key learning functions. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/vocabulary-memorization-pep-8th-grade-english.json

@@ -0,0 +1,68 @@
+{
+  "index": 972,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure to ensure the generated code is executable for display purposes. Create a vocabulary memorization software for People's Education Press 8th grade (second semester) English textbook.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the vocabulary database implementation complete?",
+      "description": "Check if the code includes a comprehensive vocabulary database for the 8th grade PEP textbook (second semester). The database should include words, meanings, example sentences, and unit classifications. Score 0 if there's no structured database, 5 if only words and meanings are included, and 10 if the database is complete with words, phonetics, definitions, example sentences, and unit organization.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Does the memorization system implement effective learning mechanisms?",
+      "description": "Evaluate if the code implements scientifically-backed memorization techniques such as spaced repetition, recall testing, or the Leitner system. Check if the system tracks user learning progress and adapts difficulty accordingly. Deduct 5 points if there's no algorithm for spaced repetition, and 3 points if there's no mechanism to prioritize difficult words. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is there a comprehensive assessment and progress tracking system?",
+      "description": "Review if the code includes various test modes (multiple choice, spelling, matching, etc.) and maintains learning statistics. Check if it provides performance metrics like accuracy rates, mastery levels, and learning curves. Deduct 5 points if assessment lacks variety, and 5 points if there's no progress visualization. Give 10 points for a complete system with diverse test types and detailed analytics.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the software provide effective vocabulary organization by units/themes?",
+      "description": "Check if vocabulary is properly organized according to PEP 8th grade textbook units, allowing students to focus on specific sections. The system should allow filtering by unit, difficulty level, and mastery status. Deduct 3 points if unit organization is missing, 3 points if there's no difficulty classification, and 4 points if there's no custom list feature. 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 incorrect inputs, data loading failures, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the learning experience (e.g., 1. Visual mnemonics for vocabulary 2. Game-based learning modules 3. Voice recognition for pronunciation practice). 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 learning methods (e.g., multiple flashcard systems with overlapping functionality) 2. Function modules unrelated to vocabulary learning (e.g., a built-in general calculator) 3. Fancy effects that affect performance (e.g., excessive animations that slow down word 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 data/learning logic/view 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 educational software design principles: 1) Age-appropriate color scheme for 8th graders 2) Proper layout spacing and information hierarchy 3) Professional font system with good readability (body font size ≥ 14px, line height over 1.5 times). Deduct 3 points for each crowded visual element, 5 points for distracting color combinations, 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 developmentally appropriate?",
+      "description": "Judge whether the dynamic effects conform to adolescent learning characteristics: 1) Clear feedback for right/wrong answers within 100ms 2) Appropriate animation duration between 300-500ms 3) Intuitive navigation suitable for 13-14 year old users. Deduct 5 points for each operation without feedback, 3 points for distracting transitions, and 5 points if key learning functions are difficult to locate. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/vocabulary-practice-app-chinese-8th-grade.json

@@ -0,0 +1,68 @@
+{
+  "index": 1411,
+  "question": "You are a coding expert. Please use your professional knowledge to generate accurate and expert responses. Be sure that any code you produce is executable and displayable. How do I create an app for practicing new vocabulary words from the \"Reading and Writing\" section at the end of each lesson in the 8th grade second semester Chinese Language Arts textbook (non-provincial edition)?",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the vocabulary management system fully implemented?",
+      "description": "Review whether the code accurately implements a database/storage system for vocabulary words, with proper categorization by textbook lessons. Check if it includes CRUD operations (Create, Read, Update, Delete) for words, definitions, and example sentences. Score 0 if core vocabulary storage is not implemented, 5 if basic storage exists without lesson organization, and 10 if complete vocabulary management with lesson-based organization is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Are the learning modes comprehensive and pedagogically sound?",
+      "description": "Evaluate whether multiple learning modes are implemented (e.g., flashcards, multiple choice, fill-in-the-blank, matching exercises). Check if the implementation follows spaced repetition principles and adapts to the student's performance. Deduct 3 points if spaced repetition is missing, 3 points if there are fewer than 3 practice modes, and 2 points if performance tracking is absent. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the lesson-based organization properly structured?",
+      "description": "Assess whether the app correctly organizes vocabulary by lessons according to the textbook structure. Check if it allows navigation between lessons, tracking completion rates, and provides lesson-specific statistics. Deduct 5 points if lessons cannot be individually selected, 3 points if progress tracking per lesson is missing, and 2 points if there's no visual indication of lesson completion status. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the progress tracking and performance analysis feature implemented?",
+      "description": "Check if the code includes comprehensive progress tracking, performance analysis, and visualization of learning outcomes. Score should reflect implementation of learning curves, mistake frequency analysis, and time-based performance metrics. Deduct 4 points if visualization is missing, 3 points if historical performance comparison is absent, and 3 points if there's no weak-point identification system. 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 input, network interruption, data corruption, 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. Audio pronunciation of vocabulary 2. Handwriting recognition for character practice 3. Contextual usage examples from real texts 4. Gamification elements that motivate continued learning). 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 learning activities 2. Function modules unrelated to vocabulary learning 3. Fancy effects that affect performance or distract from learning. Deduct 3 points for each redundancy found, and directly deduct 10 points if the core learning 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/logic/UI layers), 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 there's no clear separation between UI and business logic. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface design meet educational application standards?",
+      "description": "Evaluate whether the design follows educational UX principles: 1) Age-appropriate visual elements for 8th graders 2) Distraction-free learning environment 3) Clear instructional cues 4) Proper text size and readability (min 16px font size). Deduct 3 points for each distracting visual element, 5 points for poor readability, and 5 points for inappropriate or confusing navigation. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the learning interaction intuitive and responsive?",
+      "description": "Judge whether the interaction design supports effective learning: 1) Immediate feedback on answers within 500ms 2) Clear indication of correct/incorrect responses 3) Intuitive input methods appropriate for Chinese character entry 4) Smooth transitions between learning activities. Deduct 3 points for delayed feedback, 3 points for confusing response indicators, and 4 points for cumbersome character input methods. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/vue-3-offline-deepseek-application.json

@@ -0,0 +1,68 @@
+{
+  "index": 395,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to provide executable code examples whenever possible. How can Vue 3 code be used to implement a local application of DeepSeek that doesn't require an internet connection?",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the Vue 3 application structure properly implemented?",
+      "description": "Check if the code includes proper Vue 3 setup with Composition API, properly structured components, and correct use of Vue 3 features (ref, reactive, computed, watch, etc.). Deduct 3 points if using Options API without justification, 5 points if Vue 2 patterns are mixed in, and 5 points if component architecture is monolithic. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the offline capability implemented correctly?",
+      "description": "Evaluate whether the code implements Service Workers for offline cache, properly manages offline assets, and uses IndexedDB or localStorage for data persistence. Check if the application works completely offline after initial load. Deduct 5 points if Service Worker is missing, 3 points if offline state handling is incomplete, and 5 points if there are network dependencies not properly cached. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the local DeepSeek model integration properly implemented?",
+      "description": "Review whether the code correctly integrates a local DeepSeek model using WebAssembly, TensorFlow.js, or ONNX Runtime. Check if model loading, initialization, and inference are handled efficiently. Deduct 5 points if model initialization fails, 5 points if memory management is poor, and 3 points if the model size is not optimized for web use. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the application state management implemented effectively?",
+      "description": "Assess whether the code uses appropriate state management (Pinia, Vuex, or built-in Composition API) for handling the application state, model parameters, inference results, and user interactions. Deduct 3 points for global state pollution, 5 points for missing reactivity in critical paths, and 5 points for state inconsistencies. 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 model loading failures, out-of-memory errors, browser compatibility 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. Progressive model loading 2. Export/import of conversation history 3. Customizable model parameters 4. Voice input/output integration). 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 implementations of similar functions 2. Function modules unrelated to DeepSeek's core functionality 3. Fancy effects that affect performance and model inference speed. 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/model inference/data management layers), unit test coverage, and build process optimization. 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 optimized for offline use. 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 model inference, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}

package/library/web_applications-education_learning/vue-3-pdf-analysis-page.json

@@ -0,0 +1,68 @@
+{
+  "index": 886,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Take care to ensure the generated code is executable for demonstration. Please analyze the structure and content of PDF files, and implement a page using Vue 3 Composition API. Provide complete content.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the PDF file structure analysis implementation complete?",
+      "description": "Review whether the code accurately implements PDF structure parsing, including detecting PDF versions, extracting document structure, handling object streams, and processing cross-reference tables. Score 0 if no parsing logic is implemented, 5 if only basic header/trailer extraction is present, and 10 if complete PDF object hierarchy parsing is implemented.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the PDF content extraction functionality implemented?",
+      "description": "Check whether the implementation can extract text content, images, vector graphics, and forms from PDF files. Evaluate support for different encodings (ASCII, UTF-16), font handling, and content streams interpretation. Deduct 3 points if text extraction is limited, 3 points if image extraction is missing, and 4 points if vector graphics rendering is incomplete. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the Vue 3 Composition API correctly utilized?",
+      "description": "Evaluate whether the code properly implements Vue 3 Composition API patterns (setup(), ref(), reactive(), computed(), watch(), lifecycle hooks). Check for proper separation of concerns, composition functions, and dependency injection. Deduct 5 points for using Options API instead of Composition API, 3 points for mixing patterns inconsistently, and 3 points for not leveraging reactive primitives effectively. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the implementation include PDF rendering and display functionality?",
+      "description": "Assess whether the code provides visualization of PDF content, including page navigation, zoom functionality, and text selection. Check for canvas-based rendering or DOM-based representation. Deduct 3 points if page navigation is missing, 3 points if zoom functionality is not implemented, 2 points if text selection is not supported, and 2 points if the rendering is not performant with larger documents. 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 malformed PDFs, unsupported features, large files, network interruptions during loading, 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. PDF annotation capability 2. Text-to-speech for PDF content 3. Dark mode for PDF viewing 4. PDF content search with highlighting). 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 PDF parsing libraries used simultaneously) 2. Function modules unrelated to PDF handling (e.g., excessive animations unrelated to document viewing) 3. Fancy effects that affect performance (e.g., unnecessary 3D transforms for page turns). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating PDF parsing/rendering/UI components), 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 principles: 1) Harmonious color matching (no more than 3 primary colors) 2) Proper layout spacing (element spacing follows the 8px multiple principle) 3) Professional font system (body font size ≥ 14px, line height over 1.5 times). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance. Deduct 5 points for each operation without feedback, 3 points for visual after-images during fast sliding, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/vue-3-sql-query-beautify-results.json

@@ -0,0 +1,68 @@
+{
+  "index": 909,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and specialized responses. Make sure the generated code is executable for demonstration purposes. I'm using a Vue 3 project where users edit SQL queries and the query results are rendered on the page. SQL Beautify can enhance the appearance. Please help me implement this functionality.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the SQL editor implementation complete?",
+      "description": "Review whether the code implements a fully functional SQL editor using Vue 3, with features like syntax highlighting, auto-completion, and line numbering. Check if it uses appropriate libraries (like CodeMirror, Monaco Editor, or Ace Editor) and if proper event bindings are established. Score 0 if there's no editor implementation, 5 if basic editing is supported but advanced features are missing, 10 if the editor is complete with all expected features.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is SQL beautification properly implemented?",
+      "description": "Evaluate the SQL beautification functionality. It should format queries with consistent indentation, proper keyword capitalization, and aligned clauses. Check if it handles complex queries with subqueries, CTEs, and various SQL dialects. Deduct 5 points if beautification only works for basic queries, 3 points if it doesn't preserve comments or special syntax. Give full points only if the beautification is configurable and preserves all SQL semantics.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the SQL execution and results rendering complete?",
+      "description": "Check if the code handles SQL query execution through appropriate API calls and displays results in a well-structured table or visualization. Verify if it includes loading states, proper error handling, and can handle different result types (empty sets, large datasets, various data types). Score 3 if only basic query results are shown, 7 if pagination or sorting is included, 10 if the implementation includes advanced features like filtering and column customization.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the integration with Vue 3 reactive system properly done?",
+      "description": "Assess whether the code properly leverages Vue 3's composition API, reactive references, computed properties, and watch functions. Check for proper component organization, state management, and lifecycle hooks usage. Deduct 3 points for each anti-pattern (like direct DOM manipulation), 5 points if reactivity is broken in key features, and 5 points if the component structure is poorly organized. 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 SQL syntax, API request failures, long-running queries, 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. Query history with local storage 2. Visual query builder alongside text editor 3. Query execution plan 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 SQL parsing libraries) 2. Function modules unrelated to SQL editing/execution (e.g., unrelated charts or widgets) 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 SQL processing logic/UI components/API services), 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 principles: 1) Harmonious color matching (no more than 3 primary colors) 2) Proper layout spacing (element spacing follows the 8px multiple principle) 3) Professional font system (body font size ≥ 14px, line height over 1.5 times). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic text-image layout. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the dynamic interaction smooth and seamless?",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Click feedback delay ≤ 100ms 2) Transition animation duration controlled between 300-500ms 3) Clear visual focus guidance. Deduct 5 points for each operation without feedback, 3 points for visual after-images during fast sliding, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "easy"
+}

package/library/web_applications-education_learning/vue-blockly-project-generation.json

@@ -0,0 +1,68 @@
+{
+  "index": 1032,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the generated code is executable for demonstration purposes. Generate a Vue project using Blockly.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the Vue integration with Blockly fully implemented?",
+      "description": "Review whether the code correctly imports and initializes Blockly within a Vue component, properly renders the Blockly workspace, handles Vue lifecycle hooks (mounted, beforeDestroy), and manages the Blockly instance. Score 0 if Blockly isn't properly integrated with Vue, 5 if basic integration exists but with flaws, and 10 if the integration is seamless with proper component architecture.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Are custom Blockly blocks created and properly integrated with Vue data flow?",
+      "description": "Check if custom blocks are defined that generate Vue-compatible code, if the code includes block definitions with proper Vue syntax output, and if there's bidirectional data binding between Blockly workspace and Vue components. Deduct 5 points if custom blocks don't generate valid Vue code, 3 points if the data flow is unidirectional only. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is there a mechanism to convert Blockly code to Vue components/templates?",
+      "description": "Evaluate whether the project includes a code generator that translates Blockly blocks into valid Vue syntax (components, methods, computed properties, etc.) and whether the generated Vue code can be dynamically loaded/executed. Score 0 if no generation mechanism exists, 5 if basic code generation exists but with limitations, and 10 if there is a complete, error-handling code generation pipeline.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the project include a preview/live execution environment?",
+      "description": "Assess if the implementation allows users to visually preview the Vue components created through Blockly in real-time, and whether state changes in the preview environment are reflected back to the Blockly workspace. Deduct 5 points if the preview is static only, 3 points if there's significant rendering delay (>500ms). 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 block configurations, syntax errors in generated code, component mounting failures, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Drag-and-drop between Blockly and actual Vue components 2. Export to Vue CLI project 3. Visual component theme editor 4. Block-level version control). 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 code generators) 2. Function modules unrelated to Vue/Blockly integration (e.g., a built-in file explorer) 3. Fancy effects that affect performance (e.g., excessive animations in the Blockly workspace). 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 Blockly configuration/Vue component generation/UI 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 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 between Blockly workspace and Vue output. Deduct 5 points for each operation without feedback, 3 points for visual after-images during block drag operations, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Web Applications-Education/Learning",
+  "difficulty": "medium"
+}