@getollie/cli 0.0.1

package/library/utility_tools-daily_office_tasks/html-speech-synthesis-multi-voice-tool.json

@@ -0,0 +1,68 @@
+{
+  "index": 941,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and expert responses. Make sure the generated code is executable for demonstration. Create a language synthesis tool using HTML that allows selection of multiple voices for speech synthesis!!! (No application files needed)",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Voice selection implementation",
+      "description": "Evaluate whether the code provides a comprehensive voice selection interface that allows users to select from all available system voices. Check if the voices are properly categorized by language and if there's a preview option. Score 0 if voice selection is missing, 5 if only basic voice listing is implemented, 10 if full voice selection with filtering and categorization is included.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Speech synthesis core functionality",
+      "description": "Review whether the code correctly implements the Web Speech API's SpeechSynthesis interface, including proper initialization, utterance creation, and event handling. Check if the synthesis can be started, paused, resumed, and stopped. Deduct 5 points if pitch/rate controls are missing, and 3 points if volume control is not implemented. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Text input and processing capabilities",
+      "description": "Assess the text input mechanism, checking if it supports multiple paragraphs, handles special characters, and includes options for text preprocessing (like normalization or phonetic adjustments). Check if the implementation allows users to save or load text. Deduct 3 points if there's no character count, 3 points if special characters cause issues, and 5 points if long text handling is problematic. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Voice parameter customization",
+      "description": "Evaluate the implementation of advanced voice parameter controls such as pitch, rate, volume and any additional SSML support. Check if parameters can be adjusted in real-time and if there are presets for common scenarios. Deduct 5 points if adjustments don't take effect immediately, and 5 points if the range of adjustments is too limited. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Code robustness",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as unavailable voices, browser compatibility issues, API 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": "Innovative features",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Real-time visualization of speech waveforms 2. Export options for synthesized speech 3. Voice effect filters). Add 3 points for each practical innovative feature implemented (maximum 10 points).",
+      "maxScore": 10
+    },
+    {
+      "id": 6,
+      "title": "Redundant features",
+      "description": "Strictly check three types of redundancy: 1. Redundant implementation of similar functions (e.g., multiple speech engines coexisting) 2. Function modules unrelated to speech synthesis (e.g., a built-in music player) 3. Fancy effects that affect performance (e.g., excessive animations). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Engineering quality",
+      "description": "Review modular design (such as separating UI/speech API/state management layers), proper error handling, and cross-browser compatibility. 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 browser compatibility issues are not addressed. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Interface vision",
+      "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": "Dynamic interaction",
+      "description": "Judge whether the dynamic effects conform to human perception characteristics: 1) Voice selection and playback response delay ≤ 100ms 2) Visual feedback during speech synthesis 3) Clear indication of active voice and synthesis state. Deduct 5 points for each operation without feedback, 3 points for laggy transitions between voices, and 5 points for unclear indication of the current synthesis state. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "medium"
+}

package/library/utility_tools-daily_office_tasks/html-webpage-comparison-analysis-html-documents.json

@@ -0,0 +1,68 @@
+{
+  "index": 1367,
+  "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. Could you help me write an HTML webpage that integrates comparison and analysis functions for HTML format documents?",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the HTML document comparison functionality fully implemented?",
+      "description": "Review whether the code accurately implements side-by-side or inline comparison of HTML documents, with clear visual differentiation between added, removed, and modified content. Score 0 if no comparison functionality exists, 5 if basic text comparison is implemented without HTML structure awareness, and 10 if the comparison handles both text content and HTML structure differences with proper visualization.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Does the analysis function provide comprehensive HTML document metrics?",
+      "description": "Evaluate whether the analysis includes key HTML metrics such as document structure analysis, tag usage statistics, accessibility compliance checking, and semantic markup evaluation. Deduct 3 points if only basic statistics (like element counts) are provided, 5 points if structural analysis is missing, and 7 points if the analysis lacks actionable insights. Full score requires both quantitative metrics and qualitative assessment capabilities.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the document parsing and processing mechanism robust?",
+      "description": "Check whether the code properly handles various HTML document inputs, including malformed HTML, different DOCTYPE declarations, and various encodings. The parser should normalize documents before comparison and handle edge cases like comments, CDATA sections, and script tags appropriately. Deduct 5 points if the parser breaks on malformed HTML, and 3 points if it doesn't properly normalize whitespace or handle special elements.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the interface provide intuitive visualization of comparison results?",
+      "description": "Assess whether the visualization clearly highlights differences using color coding, navigation controls for jumping between differences, and options for different view modes (e.g., side-by-side, unified view). The visualization should be comprehensible at a glance. Deduct 5 points if navigation between differences is absent, 3 points if the visual differentiation is unclear, and 2 points if there's only one view mode available.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as extremely large documents, network interruption during file upload, corrupt HTML files, 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. Export comparison results in different formats 2. Integration with version control systems 3. Visual DOM tree comparison 4. Automated suggestion for HTML improvements). 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 parsing engines) 2. Function modules unrelated to HTML comparison and analysis (e.g., a built-in image editor) 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 parsing/comparison/visualization logic), 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 scrolling or comparison transitions, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "easy"
+}

package/library/utility_tools-daily_office_tasks/html-xiaohongshu-image-text-overlay-generator.json

@@ -0,0 +1,68 @@
+{
+  "index": 1823,
+  "question": "You are a code expert, please use your professional knowledge to generate accurate, professional responses. Make sure the generated code is executable whenever possible. Please help me create a tool using HTML that generates text overlays for Xiaohongshu (Little Red Book) images. The entire code should be saved in a single HTML file.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the HTML image overlay tool fully implemented?",
+      "description": "Review whether the code implements the core functionality of adding text overlays to images. Check if users can upload/select images, add text overlays with customization options, and save/export the final result. Score 0 if core functionality is missing, 5 if basic overlay is implemented but lacks customization, and 10 if all features are fully included with a Xiaohongshu-style aesthetic.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Are the text overlay customization options comprehensive?",
+      "description": "Evaluate the range of text customization options available. Should include font selection (minimum 5 popular fonts), text color picker with opacity control, font size adjustment, text alignment, rotation, and shadow/highlight effects commonly seen in Xiaohongshu posts. Deduct 2 points for each missing essential customization feature. Full score for implementing all features plus popular Xiaohongshu-specific text styles as presets.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the image handling functionality complete?",
+      "description": "Check if the tool allows for basic image operations: uploading from local storage, cropping/resizing to standard Xiaohongshu dimensions (3:4, 1:1, 4:3), basic filters similar to the platform, and brightness/contrast adjustments. Deduct 3 points if image upload is unreliable, 3 points if resizing/cropping is missing, and 4 points if no image enhancement features are available.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the export functionality properly implemented?",
+      "description": "Verify if the tool can export the final image with text overlays in common formats (PNG/JPEG), preserving quality and transparency where needed. Check for proper file naming options and if image dimensions match Xiaohongshu's recommended specifications. Deduct 5 points if export produces visual artifacts, 3 points if limited format options, and 5 points if no download functionality.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code handles common abnormal situations (such as unsupported file types, oversized images, text overflow, browser compatibility issues). Code should provide friendly error messages and recovery mechanisms. Check for proper event handling and memory management when processing large images. Give 10 points for comprehensive error handling, 5 points for average robustness, 0 points if exceptions crash the application.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Template library of popular Xiaohongshu text styles 2. Batch processing multiple images 3. AI-suggested text positioning 4. Social sharing 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 implementation of similar functions (e.g., multiple text editors coexisting) 2. Function modules unrelated to image text overlay (e.g., a built-in music player) 3. Fancy effects that affect performance (e.g., excessive animations that slow down the interface). 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 processing), code organization within the single HTML file (proper use of script sections, CSS organization), and efficient use of JavaScript libraries if included. Deduct 5 points if global namespace pollution is found; deduct 5 points if the code is difficult to maintain due to poor structure; deduct 5 points if the tool performs poorly on standard hardware. 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 and resembles Xiaohongshu's aesthetic: 1) Clean, feminine color palette with appropriate accent colors 2) Proper layout spacing with clear visual hierarchy 3) Professional typography that matches Xiaohongshu's style. Deduct 3 points for each misaligned element, 5 points for an inconsistent color scheme, and 5 points for poor typography choices. 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) Real-time preview of text overlays as users type 2) Smooth dragging and positioning of text elements 3) Responsive design that works on various screen sizes including mobile devices (where most Xiaohongshu users create content). Deduct 5 points for laggy text editing, 3 points for jerky drag-and-drop functionality, and 5 points if the tool is unusable on mobile devices. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "hard"
+}

package/library/utility_tools-daily_office_tasks/implement-simple-mind-map-tool.json

@@ -0,0 +1,68 @@
+{
+  "index": 679,
+  "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 when possible. Implement a simple mind map tool that supports creating nodes, connecting nodes, dragging to adjust node positions, editing node content, and folding/expanding child nodes. Users should be able to change node colors, add icons, and export the mind map as PNG images. The mind map data should be able to be saved and restored.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the node creation and connection system fully implemented?",
+      "description": "Review whether the code implements a complete node system including creation, connection, and hierarchy management. Node objects should have clear parent-child relationships and support tree traversal. Check if nodes can be properly positioned in a hierarchical structure, and if connections between parent-child nodes automatically update when nodes are moved. Score 0 if nodes cannot be created, 5 if basic node creation exists but connections are static, and 10 if the system fully supports dynamic node relationships with visual connections that update automatically.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the drag-and-drop functionality for node positioning implemented correctly?",
+      "description": "Evaluate the drag-and-drop implementation for smoothness and accuracy. The code should handle mousedown/touchstart, mousemove/touchmove, and mouseup/touchend events properly, include collision prevention between nodes, and maintain parent-child relationships during movement. Score should account for: position calculations that handle offsets correctly (3 points), smooth rendering during drag operations (3 points), and proper event cleanup to prevent memory leaks (4 points). Deduct 5 points if dragging a parent node doesn't also move its children appropriately.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is node content editing and styling functionality complete?",
+      "description": "Check whether users can edit node text content in-place (not just through a separate dialog), change text formatting (at minimum: bold, italic, or font size), and modify node colors. The implementation should handle focus management properly when editing. Score 0 if editing is not supported, 5 if only basic text editing is available, and 10 if the implementation includes text formatting options, color customization with a proper color picker, and maintains editing state properly across user interactions.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Are node folding/expanding and icon addition features implemented?",
+      "description": "Evaluate the implementation of node folding/expanding functionality and icon addition. The code should visually indicate which nodes can be collapsed, animate the collapse/expand transition, and maintain the mind map's overall layout after these operations. For icons, review whether users can select from multiple icon options, position icons within nodes, and whether the implementation handles the display of both text and icons elegantly. Deduct 5 points if folding animation is jarring or if the layout breaks after folding/expanding operations.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as invalid user inputs, unexpected JSON data structures when loading saved mind maps, browser resize events affecting layout, 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. Automatic layout algorithms for node positioning 2. Keyboard shortcuts for common operations 3. Mind map templates or themes). 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 perform the same node operations) 2. Function modules unrelated to mind mapping (e.g., an unnecessary settings panel with non-mind map related options) 3. Fancy effects that affect performance (e.g., excessive animations that slow down the rendering). 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 model/view/controller layers), event handling patterns, and code organization. Deduct 5 points if global state pollution is found or design patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there's no clear separation between mind map logic and rendering. 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 export functionality and data persistence implemented correctly?",
+      "description": "Judge whether the mind map can be properly exported as a PNG image and if the mind map data can be saved and restored. The PNG export should capture the entire mind map with proper resolution, while the save/restore functionality should persist all node properties, positions, connections, and styling. Deduct 5 points if the PNG export crops the mind map incorrectly or has poor resolution, 5 points if the save/restore functionality doesn't maintain all node properties, and 5 points if there's no error handling for failed export or save operations. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "medium"
+}

package/library/utility_tools-daily_office_tasks/intelligent-screenshot-annotation-tool.json

@@ -0,0 +1,68 @@
+{
+  "index": 694,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to ensure that the code you generate is executable for demonstration purposes. Develop an intelligent screenshot annotation tool that supports adding arrows/mosaic/text annotations after capturing a region, implementing undo/redo functionality for annotation history, saving preset annotation styles, and supporting export to PNG and copying to clipboard.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the screenshot capture function properly implemented?",
+      "description": "Review whether the code correctly implements screen region selection with visual guidance (crosshair cursor, marquee selection box). Check if the captured area is accurately represented in the annotation canvas. Verify if the tool handles multiple monitors and different screen resolutions correctly. Score 0 if screen capture is not implemented, 5 if basic region capture works but has limitations, and 10 if the implementation is robust across different environments.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Are all required annotation tools (arrows/mosaic/text) implemented and functional?",
+      "description": "Examine if the code provides complete implementations for arrows (with customizable direction, thickness, color), mosaic effects (with adjustable blur/pixelation levels), and text annotations (with font selection, size, color, and positioning). Each tool should have proper mouse interaction patterns. Deduct 3 points for each missing tool. Deduct 2 points for tools with limited customization options. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the undo/redo functionality properly implemented with comprehensive history tracking?",
+      "description": "Assess whether the code maintains a complete operation history stack that tracks all annotation actions separately. Verify that undo/redo works correctly for complex sequences of operations and after switching between annotation tools. Check if the implementation handles composite operations properly. Score 0 if history management is missing, 5 if basic undo/redo works for simple cases, and 10 if the implementation is robust for all scenarios.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Does the tool support saving and applying preset annotation styles?",
+      "description": "Evaluate whether users can save custom styles (color combinations, line thickness, text fonts, mosaic patterns) as presets and apply them with a single click. Check if presets persist between sessions and if the preset management UI is intuitive. Deduct 5 points if presets are not persistent, 3 points if preset UI is confusing, and 2 points if style application is inconsistent across annotation types. 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 selections, large images, memory limitations, operating system restrictions, 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. Smart object detection for auto-annotation 2. Voice commands for annotation 3. Automatic annotation suggestions based on content 4. Multi-layer annotation support). 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 annotation functions (e.g., multiple text insertion methods) 2. Function modules unrelated to screenshot annotation (e.g., a built-in image editor for other purposes) 3. Fancy effects that affect performance (e.g., unnecessary animations). Deduct 3 points for each redundancy found, and directly deduct 10 points if the core functions are interfered with by redundant code.",
+      "maxScore": 10
+    },
+    {
+      "id": 7,
+      "title": "Does the code have engineering quality?",
+      "description": "Review modular design (such as separating UI/annotation logic/storage 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 toolbar organization (grouped by function, with clear icons). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for chaotic tool arrangement. 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) Immediate visual feedback during annotation drawing 2) Smooth transitions between annotation states 3) Clear visual indicators for selection and focus. Deduct 5 points for laggy annotation rendering, 3 points for jerky tool switching transitions, and 5 points for unclear selection state indicators. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "medium"
+}

package/library/utility_tools-daily_office_tasks/medication-reminders-mini-program-elderly.json

@@ -0,0 +1,68 @@
+{
+  "index": 1610,
+  "question": "You are a coding expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the code you produce is executable and ready for demonstration. Please help me write a complete mini-program for medication reminders for elderly people that I can directly copy and paste for use.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the medication reminder core functionality fully implemented?",
+      "description": "Evaluate whether the code implements essential medication reminder features: scheduling reminders, setting medication details (name, dosage, frequency), notification system, and acknowledgment of taken medication. Score 0 if core functionality is missing, 5 if basic reminders are implemented without flexibility, and 10 if the system includes multiple scheduling options (daily, weekly, specific times) with medication details management.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the elderly user interface properly designed for accessibility?",
+      "description": "Check if the UI follows elderly-friendly design principles: large text (at least 16px), high contrast colors (contrast ratio ≥ 7:1), simplified navigation, clear buttons (minimum 44x44px touch targets), and minimal steps to complete tasks. Deduct 3 points for each accessibility guideline violated. Award full points only if the interface demonstrates specific considerations for elderly users including font scaling options.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Does the application include caregiver integration features?",
+      "description": "Assess whether the code implements caregiver monitoring capabilities: missed medication alerts, medication adherence tracking, remote monitoring dashboard, and emergency contact integration. Deduct 3 points if remote monitoring is missing, 3 points if adherence tracking is absent, and 4 points if emergency contact functionality is not implemented. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is data persistence and offline functionality properly implemented?",
+      "description": "Evaluate if the code properly handles data storage (local storage or database implementation), synchronization mechanisms, and offline functionality. Check for proper data validation, backup mechanisms, and recovery procedures. Deduct 5 points if medication data isn't persistent after app restart, and 5 points if the app requires constant internet connection to function. Full score for complete offline capability with data integrity protection.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as incorrect inputs, network interruption, system notifications being blocked, 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. Medication identification using camera 2. Voice-based reminders and commands 3. Adaptive reminder timing based on user habits 4. Gamification elements for medication adherence). 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 notification systems coexisting) 2. Function modules unrelated to medication reminders (e.g., a built-in games section) 3. Fancy effects that affect performance (e.g., unnecessary animations that might confuse elderly users). 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/UI/notification 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 ≥ 16px for elderly users, 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 elderly users' perception characteristics: 1) Clear feedback for every action 2) Transition animation duration controlled between 400-700ms (slightly longer for elderly users) 3) Obvious visual and possibly auditory cues for important actions. Deduct 5 points for each operation without feedback, 3 points for confusing transitions, and 5 points for hard-to-find key function buttons. The full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "hard"
+}

package/library/utility_tools-daily_office_tasks/meeting-schedule-qq-music-reminder-system.json

@@ -0,0 +1,68 @@
+{
+  "index": 448,
+  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Make sure the generated code is executable whenever possible. Help me write a simple software code for a meeting schedule recording reminder system that allows users to input schedule arrangements and dates. When the reminder button is clicked, on the corresponding date, the interface will automatically open QQ Music to play \"Today Is a Good Day.\" When the stop button is clicked, QQ Music will exit and the music will stop playing.",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the meeting schedule input and storage system fully implemented?",
+      "description": "Review whether the code accurately implements schedule input functionality through HTML forms/JavaScript, including date picker, time selector, and schedule description fields. Check if data validation is implemented (date format, required fields, conflict detection). Score 0 if basic input functionality is missing, 5 if only simple input is implemented without validation, and 10 if complete input system with validation and local storage is included.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the reminder scheduling and timing mechanism properly implemented?",
+      "description": "Check whether the reminder system uses appropriate timing mechanisms (setTimeout/setInterval) to monitor scheduled dates and times. Evaluate if the system can handle multiple concurrent reminders and accurately trigger at specified times. Deduct 5 points if timing accuracy is poor (>30 seconds deviation), and 3 points if background timing doesn't work when browser tab is inactive. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Is the QQ Music integration and external application control implemented?",
+      "description": "Evaluate whether the system successfully integrates with QQ Music application launch functionality. Check if the code uses appropriate methods (shell commands, registry, or protocol handlers) to open and close QQ Music. Verify if the specific song 'Today Is a Good Day' can be automatically played. Deduct 5 points if only basic app launch is implemented without specific song control, and 3 points if the stop functionality doesn't properly terminate the music application.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is the complete reminder lifecycle and state management constructed?",
+      "description": "Check whether the code includes complete reminder lifecycle management, including reminder creation, modification, deletion, and completion marking. Evaluate if the system maintains proper state tracking for active/inactive reminders and handles reminder history. Deduct 5 points if reminder persistence is not implemented, and 3 points if there's no mechanism to handle missed or expired reminders. Give 10 points if fully implemented with comprehensive state management.",
+      "maxScore": 10
+    },
+    {
+      "id": 4,
+      "title": "Is the code robust?",
+      "description": "Evaluate whether the code can handle common abnormal situations (such as invalid date input, system permission denial for external app launch, missing QQ Music installation, etc.) and provide friendly error prompts or fallback mechanisms. Code with strong robustness should effectively handle these edge cases, giving 10 points. If robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 5,
+      "title": "Are there any innovative features that are eye-catching?",
+      "description": "Check whether the code includes surprise features that enhance the user experience (e.g., 1. Custom ringtone selection 2. Snooze functionality 3. Meeting category classification 4. Calendar view integration 5. Notification sound volume 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 timer mechanisms coexisting) 2. Function modules unrelated to meeting reminders (e.g., built-in games or weather widgets) 3. Overly complex animations that affect performance (e.g., excessive visual effects during reminder triggers). Deduct 3 points for each redundancy found, and directly deduct 10 points if core reminder 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 management/UI/reminder logic layers), code organization, and error handling implementation. Deduct 5 points if global state pollution is found or proper separation of concerns is not implemented; deduct 5 points if code duplication rate is too high (over 30%); deduct 5 points if no configuration management is implemented for external application paths. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 8,
+      "title": "Does the interface design meet professional standards?",
+      "description": "Evaluate whether the overall design follows modern UI/UX principles: 1) Harmonious color scheme suitable for productivity tools (no more than 3 primary colors) 2) Proper layout spacing with clear visual hierarchy (element spacing follows 8px grid system) 3) Professional typography (body font size ≥ 14px, line height ≥ 1.5). Deduct 3 points for each cluttered visual element, 5 points for poor color contrast affecting readability, and 5 points for inconsistent layout structure. Full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 9,
+      "title": "Is the user interaction smooth and intuitive?",
+      "description": "Judge whether the interaction design follows usability principles: 1) Form input feedback delay ≤ 100ms 2) Smooth transitions between different views (300-500ms duration) 3) Clear visual feedback for reminder states and actions 4) Intuitive button placement and labeling. Deduct 5 points for each operation lacking immediate feedback, 3 points for confusing navigation flow, and 5 points for poorly positioned critical function buttons (reminder/stop). Full score is 10 points.",
+      "maxScore": 10
+    }
+  ],
+  "class": "Utility Tools-Daily Office Tasks",
+  "difficulty": "medium"
+}

package/library/utility_tools-daily_office_tasks/memo-application-with-audio-playback.json

@@ -0,0 +1,68 @@
+{
+  "index": 993,
+  "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 purposes. Could you write a memo application that can play audio?",
+  "checklist": [
+    {
+      "id": 0,
+      "title": "Is the memo functionality fully implemented?",
+      "description": "Review whether the code implements complete memo functionality including creating, editing, saving, and deleting memos. Check for proper text formatting options, search functionality, and categorization features. Score 0 if the basic memo operations are missing, 5 if only rudimentary operations exist, and 10 if all expected features of a modern memo application are present.",
+      "maxScore": 10
+    },
+    {
+      "id": 1,
+      "title": "Is the audio playback integration complete?",
+      "description": "Evaluate the audio playback implementation including controls (play, pause, stop, seek), support for common audio formats (MP3, WAV, OGG), volume adjustment, and playback rate control. Check if proper error handling for unsupported formats or playback failures exists. Deduct 3 points if basic playback controls are missing, 3 points if format support is limited, and 4 points if error handling is inadequate. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 2,
+      "title": "Does the application handle audio recording capabilities?",
+      "description": "Check whether the application allows users to record audio directly within the memo interface, including microphone access permissions handling, recording indicators, and saving recorded audio with the memo. Verify that the recording quality options are available and that recordings can be edited/trimmed before saving. Deduct 5 points if recording functionality is missing, 3 points if quality control is absent, and 2 points if editing capabilities are not provided. The full score is 10 points.",
+      "maxScore": 10
+    },
+    {
+      "id": 3,
+      "title": "Is proper audio-text association implemented?",
+      "description": "Assess whether the application effectively links audio files with the corresponding memo text, such as timestamps for audio references in text, visual indicators for audio attachments, and the ability to navigate text while audio plays. Check for synchronization between text edits and associated audio. Deduct 4 points if audio-text linking is absent, 3 points if visual indicators are missing, and 3 points if navigation during playback isn't supported. 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 audio format incompatibility, recording permission denials, storage limitations, 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. Speech-to-text transcription of audio memos 2. Voice command controls 3. Audio visualization during playback 4. AI-powered audio summarization). 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 audio playback engines coexisting) 2. Function modules unrelated to memo or audio purposes (e.g., a built-in game) 3. Fancy effects that affect performance (e.g., excessive animations during audio playback). 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 memo logic/audio handling/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. Assess audio-specific interactions such as waveform responsiveness and playback progress indicators. 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": "Utility Tools-Daily Office Tasks",
+  "difficulty": "medium"
+}