@getollie/cli 0.0.5 → 0.2.1

package/library/web_applications-web_visuals/webpage-tree-growing-animation.json

@@ -1,68 +0,0 @@
-{
-  "index": 447,
-  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to provide executable code for demonstration when possible. Create a webpage showing a tree growing.",
-  "checklist": [
-    {
-      "id": 0,
-      "title": "Is the tree growing animation fully implemented?",
-      "description": "Review whether the code accurately implements a tree growth animation through HTML/CSS/JavaScript, showing progression from seed/sapling to full tree. Check for clear visual stages of growth, proper timing, and smooth transitions between stages. Score 0 if no animation exists, 5 if only basic static-to-static transitions are implemented, and 10 if the animation shows organic, natural growth patterns.",
-      "maxScore": 10
-    },
-    {
-      "id": 1,
-      "title": "Is the tree structure anatomically realistic?",
-      "description": "Evaluate whether the tree implementation includes proper botanical elements (trunk, branches, leaves, possibly roots) with natural branching patterns. Check if the branching algorithm follows realistic principles like L-systems or fractal patterns. Deduct 5 points if the tree structure is overly simplistic (just a trunk and few branches), and 3 points if the branching angles are unnaturally uniform. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 2,
-      "title": "Are environmental factors incorporated into the tree growth?",
-      "description": "Assess whether the code integrates environmental elements that affect the tree's growth (e.g., simulated sunlight, seasons, weather conditions, or user interaction). Check if these factors visibly influence the tree's development direction, speed, or appearance. Deduct 5 points if no environmental factors exist, and 3 points if factors exist but have minimal visual impact on growth. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 3,
-      "title": "Is the rendering technique appropriate and efficient?",
-      "description": "Examine the technical approach used for rendering the tree (Canvas, SVG, CSS, WebGL, etc.) and whether it's appropriate for the complexity of the animation. Check for performance optimization like limiting redraws to changed elements only. Deduct 5 points for excessive DOM manipulation causing jank, 5 points if the technique chosen severely limits visual quality, and 3 points if no performance considerations are evident. 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 window resizing, browser compatibility issues, different screen sizes, etc.) and provides appropriate fallbacks. Code with strong robustness should gracefully degrade on older browsers and respond appropriately to viewport changes, giving 10 points. If the robustness is average, give 5 points, and if no edge cases are handled, give 0 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 5,
-      "title": "Are there any innovative features that are eye-catching?",
-      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Interactive elements allowing users to influence growth 2. Day/night cycle affecting the tree 3. Wildlife/insects appearing around the tree 4. Seasonal changes with appropriate visuals). 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 animation systems working simultaneously) 2. Function modules unrelated to tree growth (e.g., unnecessary UI elements) 3. Fancy effects that affect performance (e.g., excessive particle systems that slow down the page). 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 rendering logic/animation/user interaction), code organization, and maintainability. Deduct 5 points if global state pollution is found or if 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 of concerns. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 8,
-      "title": "Does the visual presentation meet professional design standards?",
-      "description": "Evaluate whether the overall design follows modern design principles: 1) Harmonious color palette appropriate for natural elements 2) Proper visual balance and composition 3) Attention to detail in tree textures and environment. Deduct 3 points for unrealistic coloring, 5 points for poor composition that distracts from the tree, and 5 points for low-quality visual assets. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 9,
-      "title": "Is the animation smooth and natural-looking?",
-      "description": "Judge whether the growth animation conforms to natural growth patterns: 1) Smooth interpolation between growth stages 2) Appropriate timing that balances between visible growth and realism 3) Natural movement like subtle swaying or response to simulated wind. Deduct 5 points for jerky transitions, 3 points for unnaturally linear growth rates, and 5 points for static elements that should move naturally. The full score is 10 points.",
-      "maxScore": 10
-    }
-  ],
-  "class": "Web Applications-Web Visuals",
-  "difficulty": "easy"
-}

package/library/web_applications-web_visuals/webpage-white-cat-playing-ping-pong.json

@@ -1,68 +0,0 @@
-{
-  "index": 1344,
-  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to ensure the generated code is executable for display. You are a skilled web designer - please help me design a webpage that shows a white cat playing ping pong, using HTML language.",
-  "checklist": [
-    {
-      "id": 0,
-      "title": "Is the core ping pong animation implemented?",
-      "description": "Review whether the code creates a functional animation of a white cat playing ping pong. Check for proper motion paths of the ball, realistic paddle movement, and cat character reactions. Score 0 if there's no animation, 5 if only basic static positioning exists, and 10 if there's a complete animation loop with proper physics.",
-      "maxScore": 10
-    },
-    {
-      "id": 1,
-      "title": "Is the white cat character properly designed and animated?",
-      "description": "Evaluate whether the cat is clearly identifiable as white, has proper proportions, and demonstrates appropriate movements for ping pong (like swinging motions, reaction poses). Deduct 3 points if the cat lacks defining features, 5 points if it's not clearly white, and 5 points if it has no animation or interaction with the ping pong elements. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 2,
-      "title": "Is the ping pong game environment properly visualized?",
-      "description": "Check whether the code creates a convincing ping pong setting with appropriate elements (table, net, paddle, ball) with correct proportions and positioning. Deduct 3 points for each missing essential element, 5 points if the spatial relationship between elements is incorrect. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 3,
-      "title": "Is the implementation technically appropriate?",
-      "description": "Assess whether the code uses appropriate HTML/CSS/JS techniques for the animation. Check for modern approaches like CSS animations, canvas, SVG, or proper JavaScript animation frameworks instead of outdated methods. Deduct 5 points for deprecated techniques (like <marquee>), 3 points for excessive use of images where vector graphics would be more appropriate. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 4,
-      "title": "Is the code robust?",
-      "description": "Evaluate whether the code can handle common abnormal situations (such as browser resizing, different screen sizes, script errors) and provides graceful fallbacks. 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. User-controlled cat movements 2. Sound effects for ping pong hits 3. Score tracking system 4. Day/night mode toggle). 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 animation controls) 2. Function modules unrelated to the cat playing ping pong 3. Fancy effects that affect performance (e.g., unnecessary complex 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 animation logic/view layers), code organization, and maintainability. Deduct 5 points if global style/script pollution is found; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there are no comments for complex logic. 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 3) Professional typography (if text is included). Deduct 3 points for each crowded visual element, 5 points for a glaring color combination, and 5 points for poor composition that makes the scene unclear. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 9,
-      "title": "Is the dynamic interaction smooth and responsive?",
-      "description": "Judge whether the animations conform to human perception characteristics: 1) Smooth motion without stuttering 2) Appropriate animation timing (not too slow or fast) 3) Natural physics in ball movement and bouncing. Deduct 5 points for jerky animations, 3 points for unrealistic physics, and 5 points for animations that run at inappropriate speeds making the ping pong game look unnatural. The full score is 10 points.",
-      "maxScore": 10
-    }
-  ],
-  "class": "Web Applications-Web Visuals",
-  "difficulty": "easy"
-}

package/library/web_applications-web_visuals/wechat-mini-program-image-functionality.json

@@ -1,68 +0,0 @@
-{
-  "index": 768,
-  "question": "You are a code expert. Please use your professional knowledge to generate accurate and professional responses. Be sure to provide executable code whenever possible. Write code for a WeChat Mini Program that implements image functionality. You can use Vant components or not.",
-  "checklist": [
-    {
-      "id": 0,
-      "title": "Is the core image functionality fully implemented?",
-      "description": "Check if the code includes essential image handling functions like uploading, displaying, previewing, and possibly editing images. Score 0 if the image functionality is not implemented, 5 if only basic image display is provided, and 10 if comprehensive image handling (upload, preview, zoom, etc.) is included.",
-      "maxScore": 10
-    },
-    {
-      "id": 1,
-      "title": "Is the WeChat Mini Program file structure correctly organized?",
-      "description": "Verify that the code follows the standard WeChat Mini Program structure with proper organization of app.js, app.json, app.wxss, and page folders containing .js, .json, .wxml, and .wxss files. Deduct 5 points if crucial configuration files are missing, 3 points if the structure is disorganized. Full score requires proper component encapsulation and clear separation of concerns.",
-      "maxScore": 10
-    },
-    {
-      "id": 2,
-      "title": "Are WeChat Mini Program API permissions properly handled?",
-      "description": "Evaluate whether the code correctly requests user permissions for accessing device camera/album, ensures scope.writePhotosAlbum for saving images, and handles user rejection scenarios. Deduct 5 points if permissions are hardcoded without user consent, and 3 points if rejection handling is missing. Full score requires comprehensive permission flows with clear user guidance.",
-      "maxScore": 10
-    },
-    {
-      "id": 3,
-      "title": "Is the image component integration properly implemented?",
-      "description": "Assess whether the code correctly implements image components (either native or Vant). Check for proper handling of image loading states, lazy loading for performance, and fallback mechanisms for failed loads. Deduct 5 points if there's no loading state management, 3 points if image caching strategies are missing. Full score requires optimized image delivery with proper error handling.",
-      "maxScore": 10
-    },
-    {
-      "id": 4,
-      "title": "Is the code robust?",
-      "description": "Evaluate whether the code can handle common abnormal situations (such as network errors during image upload/download, oversized images, unsupported formats, etc.) and provide friendly error prompts or recovery mechanisms. Code with strong robustness should be able to effectively handle these edge cases, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 5,
-      "title": "Are there any innovative features that are eye-catching?",
-      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Image filters/effects 2. Smart cropping/compression 3. OCR text extraction from images). 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 image handling functions 2. Function modules unrelated to image processing 3. Fancy effects that affect performance (e.g., excessive animations during image 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 UI/logic/network layers), component reusability, and build process optimization. Deduct 5 points if global state pollution is found or component patterns are not used; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if there are no performance optimizations for image loading and processing. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 8,
-      "title": "Does the interface vision meet professional design standards?",
-      "description": "Evaluate whether the overall design follows WeChat Mini Program design principles: 1) Consistent with WeChat's visual language 2) Proper layout spacing (following the 8px grid system) 3) Professional typography (legible text with proper contrast for image overlays). Deduct 3 points for each inconsistent UI element, 5 points for poor image presentation layout, and 5 points for accessibility issues with image interactions. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 9,
-      "title": "Is the dynamic interaction smooth and seamless?",
-      "description": "Judge whether the image-related interactions meet user expectations: 1) Image loading indicators appear within 100ms 2) Smooth transitions between image states (loading/preview/full view) 3) Responsive touch gestures for image manipulation. Deduct 5 points for operations without visual feedback, 3 points for jerky animations during image transitions, and 5 points for unresponsive image interactions. The full score is 10 points.",
-      "maxScore": 10
-    }
-  ],
-  "class": "Web Applications-Web Visuals",
-  "difficulty": "easy"
-}

package/library/web_applications-web_visuals/xiaohongshu-style-html-image-code-for-screenshots.json

@@ -1,68 +0,0 @@
-{
-  "index": 732,
-  "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 display. Generate HTML code in Xiaohongshu (Little Red Book) style, where the retrieved code format should be image code (not text or requiring image link replacement), so I can directly take screenshots and post to Xiaohongshu. The retrieved code format should be image code (not text or requiring image link replacement), so I can directly take screenshots and post to Xiaohongshu.",
-  "checklist": [
-    {
-      "id": 0,
-      "title": "Is the HTML structure properly implemented in Xiaohongshu style?",
-      "description": "Evaluate if the HTML structure follows Xiaohongshu's characteristic layout with card-based design, proper use of divs for content blocks, and appropriate heading hierarchy. Check if it includes essential Xiaohongshu UI elements like the avatar circle, like/comment buttons, and hashtag styling. Score 0 if the structure doesn't resemble Xiaohongshu at all, 5 if basic elements are present but poorly organized, and 10 if the structure precisely mirrors Xiaohongshu's format.",
-      "maxScore": 10
-    },
-    {
-      "id": 1,
-      "title": "Does the code include appropriate image implementation for screenshots?",
-      "description": "Check whether images are properly implemented as embedded data URLs or base64 encoded strings instead of external URLs. Verify that no image requires manual link replacement. Images should render directly when the HTML is loaded. Score 0 if images are implemented as external links requiring replacement, 5 if images are implemented but with poor optimization, and 10 if all images are perfectly embedded for direct screenshot capability.",
-      "maxScore": 10
-    },
-    {
-      "id": 2,
-      "title": "Is the Xiaohongshu visual styling accurately reproduced?",
-      "description": "Evaluate if the CSS accurately reproduces Xiaohongshu's distinctive visual style, including the characteristic color palette (red brand color #FF2442), rounded corners (8-12px), shadow effects, font choices, and content spacing. Score 0 if styling doesn't match Xiaohongshu, 5 if basic styling is similar but lacks precision, and 10 if the styling is indistinguishable from the actual Xiaohongshu app.",
-      "maxScore": 10
-    },
-    {
-      "id": 3,
-      "title": "Are interactive elements properly implemented for demonstration purposes?",
-      "description": "Assess if the code includes Xiaohongshu-specific interactions like double-tap to like, horizontal scroll galleries, expandable text sections, and floating action buttons. Check if these are implemented with appropriate JavaScript that works in a standalone HTML file. Deduct 3 points if essential interactions are missing, 5 points if interactions are buggy, and award full 10 points for perfectly implemented interactions that mirror the Xiaohongshu experience.",
-      "maxScore": 10
-    },
-    {
-      "id": 4,
-      "title": "Is the code robust?",
-      "description": "Evaluate whether the code can handle common abnormal situations (such as image loading failures, responsive layout breakpoints, touch vs. mouse interactions, etc.) and provide fallbacks or graceful degradation. Code with strong robustness should work across different browsers and viewports, giving 10 points. If the robustness is average, give 5 points, and if no exceptions are handled, give 0 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 5,
-      "title": "Are there any innovative features that are eye-catching?",
-      "description": "Check whether the code includes surprise features that enhance the experience (e.g., 1. Animated like button effects 2. Simulated comment typing animation 3. Parallax scrolling for images). 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 styling with overlapping CSS rules 2. Function modules unrelated to Xiaohongshu's core experience 3. Fancy effects that affect performance (e.g., excessive animations or 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 structure/style/behavior), code reusability, and performance optimization. Deduct 5 points if global style pollution is found; deduct 5 points if the code duplication rate is too high (over 30%); deduct 5 points if no performance considerations are implemented (such as image optimization, animation throttling). The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 8,
-      "title": "Does the interface vision meet Xiaohongshu's aesthetic standards?",
-      "description": "Evaluate whether the overall design follows Xiaohongshu's distinct aesthetic principles: 1) Warm, vibrant color scheme dominated by reds and pinks 2) Clean white space with proper content density 3) Typography that balances readability with stylistic flair (proper use of weights and sizes). Deduct 3 points for each misaligned visual element, 5 points for incorrect brand colors, and 5 points for improper content proportions. The full score is 10 points.",
-      "maxScore": 10
-    },
-    {
-      "id": 9,
-      "title": "Is the mobile responsiveness properly implemented?",
-      "description": "Judge whether the design adapts properly to mobile viewports: 1) Proper meta viewport tag implementation 2) Fluid layouts that adjust to different screen sizes 3) Touch-friendly tap targets (minimum 44×44px). Deduct 5 points for horizontal scrollbars on mobile, 3 points for overlapping elements at certain breakpoints, and 5 points for text that becomes illegible at mobile sizes. The full score is 10 points.",
-      "maxScore": 10
-    }
-  ],
-  "class": "Web Applications-Web Visuals",
-  "difficulty": "medium"
-}

package/src/cli.ts

@@ -1,81 +0,0 @@
-#!/usr/bin/env bun
-
-import { spawn } from "node:child_process";
-import process from "node:process";
-import { Command } from "@commander-js/extra-typings";
-import { buildPrompt } from "./prompt";
-import * as path from "node:path";
-
-// Manually parse arguments to handle -- separator
-const separatorIndex = process.argv.indexOf("--");
-const ollieArgs = separatorIndex === -1 ? process.argv : process.argv.slice(0, separatorIndex);
-const pochiArgs = separatorIndex === -1 ? [] : process.argv.slice(separatorIndex + 1);
-
-const program = new Command()
-  .name("ollie")
-  .description("Spawn a pochi subprocess with a web URL prompt");
-
-program
-  .command("eval", { isDefault: true })
-  .description("Evaluate a web URL")
-  .requiredOption("-u, --url <url>", "Web URL to evaluate")
-  .requiredOption("-q, --question <text>", "Original question/task that led to creating the sourceDir/url")
-  .requiredOption("-d, --dir <path>", "Source code directory to evaluate")
-  .action(async (options) => {
-    try {
-      const exitCode = await runPochi(options, pochiArgs);
-      process.exit(exitCode);
-    } catch (error) {
-      if (error instanceof Error) {
-        console.error(error.message);
-      } else {
-        console.error("Unknown error while running pochi");
-      }
-
-      process.exit(1);
-    }
-  });
-
-program
-  .command("library")
-  .description("Show the library directory")
-  .action(() => {
-    console.log(getChecklistDir());
-  });
-
-
-await program.parseAsync(ollieArgs);
-
-async function runPochi(options: {url: string, dir: string, question: string}, pochiArgs: string[]): Promise<number> {
-  const instructions = buildPrompt(options.url, options.dir, options.question);
-  return new Promise((resolve, reject) => {
-    const child = spawn("pochi", pochiArgs, {
-      cwd: getChecklistDir(),
-      stdio: ["pipe", "inherit", "inherit"],
-      env: {
-        ...process.env,
-        POCHI_CUSTOM_INSTRUCTIONS: instructions,
-      }
-    });
-
-    child.on("error", (error) => {
-      reject(new Error(`Failed to start pochi: ${error.message}`));
-    });
-
-    child.stdin.write(`Please start evaluation\n`);
-    child.stdin.end();
-
-    child.on("close", (code, signal) => {
-      if (signal) {
-        reject(new Error(`pochi terminated with signal ${signal}`));
-        return;
-      }
-
-      resolve(code ?? 0);
-    });
-  });
-}
-
-function getChecklistDir(): string {
-  return path.join(__filename, "../../", "library");
-}

package/src/prompt.ts

@@ -1,128 +0,0 @@
-export function buildPrompt(url: string, sourceDir: string, question: string): string {
-  const questionContext = question ? `\nThe source directory and URL were created in response to the following task:\n"${question}"\n` : '';
-
-  const RuleTemplate = `
-# Code Review Evaluation Task
-
-You are a seasoned and meticulous code review expert, proficient in multiple programming languages, front-end technologies, and interaction design. Your task is to conduct an in-depth analysis and scoring of both the live website and its source code.
-
-Your evaluation should cover implementation quality, design, architecture, performance, and adherence to best practices. Leverage your coding expertise and aesthetic judgment to thoroughly examine both the live website and source code. Be strict and cautious when awarding full marks for each dimension.
-
-## Role Definition
-
-**Responsibilities:** Act as an authoritative member of a technical review committee, ensuring objectivity, comprehensiveness, and impartiality.
-
-**Attitude:** Rigorous, professional, and unsparing, with a keen eye for detail and potential risks.
-
-**Additional Traits:** Possess exceptional aesthetic sensibility, with high standards for visual appeal and user experience.
-
-## Evaluation Target
-
-**URL to evaluate:** ${url}
-
-**Source code location:** ${sourceDir} (read ONLY page.tsx file(s))
-${questionContext}
-
-## Scoring Criteria
-
-Before starting the evaluation, generate scoring criteria based on the original question:
-- DO NOT use readFile before you have located the checklist; you MUST obtain the filepath using system-reminder or listFiles first, otherwise you may encounter errors if the file does not exist.
-- Use listFiles with recursive enabled on the current working directory to locate the checklist most relevant to the original task.
-- Find 3-4 related examples to generate scoring criteria based on them; there should be at most 10 criteria.
-- Write down the scoring criteria using executeCommand with "echo".
-- The web page is designed to be self-contained, with everything included in the page.tsx file, so do not treat this as a maintainability flaw.
-
-Example:
-{
-  "checklist": [
-    {
-      "title": "Are download and project application features properly implemented?",
-      "description": "Check whether the code provides functionality to download individual or multiple sound effects in common formats (WAV, MP3) and the ability to apply selected effects to audio projects (e.g., timeline integration, batch processing). Deduct 3 points for each missing download format, 5 points if there's no batch download option, and 4 points if project application functionality is incomplete. The full score is 10 points."
-    },
-    ...
-  ]
-}
-
-## Evaluation Steps
-
-1. Visit the URL and thoroughly analyze the live website.
-2. Take snapshots if needed to capture the visual design and user experience.
-3. Read ONLY the page.tsx file(s) in the directory: ${sourceDir} to understand the implementation.
-4. Analyze the code structure and organization based on the page.tsx file.
-5. Check for proper error handling, testing, and documentation in the page.tsx file.
-6. Evaluate based on all the provided scoring criteria.
-7. Always generate the reasoning first, then provide the score.
-8. Provide detailed reasoning for your scores, citing specific examples from both the live site and source code.
-
----
-
-## CRITICAL CONSTRAINTS
-
-### 1. READ-ONLY EVALUATION
-
-⚠️ **You MUST NOT use any file modification tools during evaluation:**
-- writeToFile
-- applyDiff
-- multiApplyDiff
-
-This is a **READ-ONLY** evaluation process. You should only observe, analyze, and score—never modify any files.
-
-### 2. OUTPUT FORMAT REQUIREMENTS
-
-⚠️ **When using attemptCompletion to submit your final result:**
-- Output ONLY the raw JSON object.
-- NO markdown code blocks (\`\`\`json).
-- NO explanatory text before or after the JSON.
-- NO additional commentary.
-
-<negative_example>
-\`\`\`json
-{
-  "checklist": [...]
-  "score": 32,
-}
-\`\`\`
-</negative_example>
-
-<negative_example>
-Here is my evaluation:
-{
-  "checklist": [...]
-  "score": 32,
-}
-
-The evaluation is complete.
-</negative_example>
-
-Do not put the score before the reasoning.
-<negative_example>
-{
-  "checklist": [
-    {
-      ...
-      "score": 1,
-      "reasoning": "..."
-    },
-    ...
-  ],
-}
-</negative_example>
-
-<positive_example>
-{
-  "checklist": [
-    {
-      "title": "Are download and project application features properly implemented?",
-      "description": "Check whether the code provides functionality to download individual or multiple sound effects in common formats (WAV, MP3) and the ability to apply selected effects to audio projects (e.g., timeline integration, batch processing). Deduct 3 points for each missing download format, 5 points if there's no batch download option, and 4 points if project application functionality is incomplete. The full score is 10 points.",
-      "reasoning": "The code implements download functionality for WAV and MP3 formats, but lacks batch download and project application features. Deducting 5 points for batch download and 4 points for project application, resulting in a score of 1 point.",
-      "score": 1
-    },
-    ...
-  ],
-  "score": 32
-}
-</positive_example>
-`.trim();
-
-  return RuleTemplate;
-}