{
  "source_file": "0930",
  "source_platform": "Ghost",
  "author": "Peng Qian / Data Leads Future",
  "title_listed": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient",
  "keywords": "",
  "domain": "大模型算法",
  "content_type": "工程实践",
  "is_paid_flag": "否",
  "url": "https://www.dataleadsfuture.com/share-my-llm-prompts-and-tips-that-make-work-and-learning-super-efficient/",
  "publish_date": "2025-11",
  "corpus_stage": "",
  "notes": "",
  "id": "dc83721ce28c",
  "collected_at": "2026-10-02T12:27:46",
  "title": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient",
  "body_markdown": "Career Growth\nShare My LLM Prompts and Tips That Make Work and Learning Super Efficient\nCan they help you too?\nPeng Qian\n28 Nov 2025\n—\n13 min read\nShare\nShare My LLM Prompts and Tips That Make Work and Learning Super Efficient. Image by DALL-E-3\nDisclaimer: This post contains affiliate links to Coursera. If you click and enroll, I may earn a small commission at no extra cost to you. Thank you for your support!\nA lot of friends ask me how I manage to stay busy with work every day, yet still find time to learn and write blog posts. The answer is simple: I use AI to help me learn about AI.\nToday I’m sharing all the AI tools, tricks, and prompts I’ve used over the past two years at work. No fluff—just straight-up useful stuff.\nFind a Good AI Client\nIf you use LLMs to boost your daily productivity, chatting with the model is still the main way most people interact with it. That means having a solid AI client app is essential.\nMy favorite AI client right now is\nCherry Studio Community Edition\n. It supports multiple languages, is completely open source and free, lets you connect to all kinds of model services, and even lets you add your own System Prompt and MCP tools. These features form the foundation for all the tips I’ll share next.\nYou can pick any model service you like. I recommend\nOpenRouter\n—with one API key, you get access to Gemini, GPT, Claude, Qwen, and many other commercial or open-source models.\nConfigure the model service in Cherry Studio's settings interface. Image by Authro\nThen there’s the agent interface. You can fill in different System Prompts based on your use case. The prompts I use daily go right here.\nEnter the prompt you want to share today in the agent interface. Image by Author\nFinally, in the chat interface, you can add the agent you just set up as your assistant, tweak your model settings, and start chatting with the LLM.\nJust add the agent you just set up as an assistant, and you're good to go! Image by Author\nBest of all, using an AI desktop client lets you keep your knowledge base local and connect to self-hosted LLM services, giving you and your company the strongest data security possible.\nSome Suggestions on Models and Settings\nNext up are the models and parameters I use daily. These aren’t “correct” answers—just my personal experience.\nModel choices\nI follow a simple rule: if I’m using it myself, I go with the best. So I stick to commercial models unless I’m building agents, where I might pick an open-source model based on need. Here’s what I use regularly:\nGemini 3.0 Pro\nis my top pick for vibe coding. Right now, code generated by Gemini 3.0 has the highest accuracy, which saves me tons of debugging time.\nGPT-5\nis the classic reliable choice—a great balance between cost and expertise. I use it for everything except coding.\nQwen3 Max\n… well, I really dislike its overly encouraging tone. It always tells me I’m doing great, no matter what, and that drives me nuts. But I have to admit—Qwen3 shines in localization and language handling. I use it whenever I need translation or proofreading.\nParameter settings\nIf you’ve read my articles before, you probably already know what each LLM parameter does. Here’s how I personally set them when using models myself.\nTemperature.\nLower values make the model more predictable; higher values make it more creative. I adjust based on context. For coding, I set\ntemperature\nto 0.01 to keep responses consistent across chats. For everything else, I stick with the default 0.7—it feels like talking to a real person. Later, I’ll show you how to make the LLM write creative motivational text—I crank\ntemperature\nup to 0.8–0.9 for that.\nContext length.\nFew people pay attention to this setting, but besides saving token costs, it can offer unexpected benefits. For my translation agent, I set context length to 2—meaning no chat history is kept. That way, the LLM only translates what I input right now, without interference from past translations.\nMax tokens.\nThis controls the maximum number of tokens per response. I always adjust it. For reasoning tasks, I keep it low—otherwise wait times and token costs explode. For writing, I set it high to avoid cutting off long articles due to default limits.\nTry using MCP\nI’ve always felt that MCP was built exactly for making LLM clients more powerful. With MCP, your personal chat interface can unlock all kinds of agent capabilities. Here’s an example:\nWe all know that due to design choices and legal restrictions, the built-in web search in LLMs keeps getting worse. Default search rarely gives useful info, especially over multi-turn conversations.\nBut you can install a\ntavily-mcp\nservice for better web search. Just sign up on their site, get an API key, and add the tavily-mcp JSON config to your client.\nYou can find the JSON for configuring MCP on the official websites of the various tools. Image by Author\nTraditional search works like this: take your keywords, search the web, then build an answer from the results.\nMCP-based search is different.\nDuring the conversation, the LLM dynamically decides if it needs to search—and generates its own search keywords based on context. This leads to much more accurate results.\nWhen using tavily-mcp, the agent will try searching with multiple keywords until it finds the answer. Image by Author\nOther MCP tools are great too.\nfetch\ngrabs webpage content from any URL you give it.\nmemory\nuses a knowledge graph to remember key info from your chats, helping you build your own custom AI agent.\nNow that we’ve covered LLM setup tips, let’s move on to my prompt-writing tricks.\nIf you want to skip the usual trial and error and jump straight into an enterprise AI career as fast as possible, I highly recommend checking out Vanderbilt University's\nGenerative AI Software Engineering Specialization\n. It gives you way more structured guidance to get there.\nMy Prompt-Writing Tips\nIs structured JSON prompting really necessary?\nAfter Gemini 3.0 launched, people noticed that using JSON-formatted prompts seemed to help LLMs follow instructions better. That sparked debate: should we always use JSON for clearer, more precise structure?\nI’ve discussed this several times with the brilliant engineers at Qwen. Their answer was clear:\nIt depends on what format of the training data used during model training. LLMs essentially memorize knowledge—including input formats—through their parameters. If most training text were in Markdown, then Markdown is naturally the best fit.\nThat’s why LLMs output in Markdown by default—they were trained on Markdown-heavy data. So their most familiar format is still Markdown.\nWhat you think is a clearer format doesn't mean the LLM sees it that way too. Image by Author\nIt’s like someone who eats bread every day telling a rice-eating kid that bread is the real staple food—completely forgetting that for the kid, rice is the staple.\nSo my conclusion? Just stick with Markdown—it’s plenty structured. And with modern LLMs, even plain-text instructions work fine as long as you’re clear.\nA universal template for system prompts\nJust like I usually write articles in a three-part structure (introduction, body, conclusion), having a prompt template saves you from staring at a blank screen.\nWhat template works for system prompts? I use the “Who, Can, Do” framework. Every good prompt includes:\nrole\n,\nwhat to (not) do\n, and\nhow to do it\n. I define each part with a subheading. Here’s an example:\n## Role\nYou are a data analyst skilled at breaking complex tasks into Python-solvable subtasks.\n\n## Tasks\n1. **Task breakdown**: Split the user request into substeps, each solvable with Python.\n2. **Code generation**: Turn the current substep into Python code.\n3. **Code execution**: Run the code using a tool and get the result.\n4. **Iterate**: Use the result to decide the next step. Repeat steps 1–3 until you have a final answer.\n5. **Insight & advice**: Add thoughtful, practical insights based on the analysis.\n\n## Requirements\n- Execute one step at a time. No skipping or combining.\n\n## Output\n- Use Markdown with a clear structure.\n- Keep tone friendly but authoritative.\n- Add emojis for warmth.\n- Format numbers with commas (e.g., 1,000).\nHere’s what each section means:\nRole\ntells the LLM “who I am and what I can do.” “Who I am” shapes output style—serious or playful—based on the role you assign. “What I can do” sets initial boundaries. For MoE models, it can even influence which expert module activates.\nTasks\nare your specific instructions. Since I recommend Markdown, use ordered lists if steps must run in sequence; otherwise, use unordered lists. Lists make your intent crystal clear.\nRequirements\nremind the LLM of its limits. Model makers train their LLMs to answer everything—but reality isn’t like that. Explicitly stating what it\ncan’t\ndo reduces hallucinations.\nOutput\nguides output format and tone. Use this section when you care about style, structure, or voice.\nYou can add extra sections based on your needs.\nFor a coding agent, add a “Code Style” section:\n## Code Style\n- Code runs in Jupyter. Reuse existing variables.\n- Write incrementally and leverage kernel state to avoid repetition.\nIf you use RAG or want to show the LLM how to think, add an “Examples” section:\n## Examples\nWhen writing Python, wrap code in markdown Python blocks:\n```python\nx=3\n```\nYou can reuse the variable later:\n```python\nprint(x)\n```\nLet the LLM help you debug your prompt\nTweaking prompts is expensive—especially when a perfectly tuned prompt stops working after switching models. What can you do besides starting over?\nUse the LLM itself!\nAfter setting your System Prompt, just ask: “\nPlease repeat in detail what you understand my instructions to be.\n”\nIt’s like asking your friends to repeat back a task before they start—to confirm understanding.\nAsk the LLM to repeat the instructions I gave it. Image by Author\nThis makes the LLM instantly return its interpretation of your system prompt. Compare it to your original intent and spot gaps.\nOr go further: ask “\nPlease use Markdown to repeat in detail what you understand my instructions to be.\n”\nThe LLM will then write a clean Markdown version of its understanding. You can copy the good parts straight back into your own prompt. Trust me—it will follow what it writes. I’ve tested this countless times.\nBeyond theory, I’ll now share some of my go-to prompt examples. You can use them directly at work or as inspiration for your own prompts. Let’s dive in.\nMy Work Prompt Examples\nPrompt for blog cover images\nLet’s start with the prompt I use to generate blog cover art.\nIf you’ve read my posts before, you’ll notice a consistent style: a cute little rabbit busy doing various things. I had DeepSeek generate the image prompt, then used DALL·E 3 to create the picture.\nEven though OpenAI says DALL·E 3 boosts prompts automatically, I still get better results by first using an LLM to write a full image prompt. Here’s what I give DeepSeek:\n## Role\nYou are a visual artist skilled at writing DALL·E 3-friendly prompts.\n\n## Task\nRewrite my [scene description] into a detailed English prompt perfect for DALL·E 3.\n\n## Length\nDescribe in 5 bullet points. Only the prompt—no intro or explanation.\n\n## Style\nColorful illustration on slightly yellowed parchment paper, filled with tech elements.\n\n## Visuals\nInclude impressive details like camera angle and lighting.\nI used this exact prompt in a previous post about generating ink-wash style illustrations:\nUse LLamaIndex Workflow to Create an Ink Painting Style Image Generation Workflow\nAdd strong artistic flair through fine control of LLM context\nData Leads Future\nPeng Qian\nEven though that post automated the whole workflow, you can still manually generate the image prompt first, then create the picture.\nDaily translation assistant\nSince I started blogging, I have often chatted with readers from around the world and answered their questions.\nI want my English to sound natural and conversational—not stiff like machine translation. So I use an LLM with this prompt:\n## Role\nYou are an expert Chinese-English translator in computer science and programming.\n\n## Task\n- Detect the language of the user’s message.\n- If it’s not Chinese, translate it into Chinese.\n- If it’s Chinese, translate it to English.\n\n## Style\n- Keep translations simple and clear. Avoid complex words.\n- Use vocabulary a middle schooler would understand.\n- Sound conversational—like a good friend chatting with you.\n\n## Rules\n1. Only translate—never do anything else.\n2. Output only the translation—no intro or notes.\n\n## Special Terms\nTranslate these terms as follows:\n[Chinese phrase]: [English translation]\n大模型: LLM\n大语言模型: LLM\n私有化部署: self-hosted\n\n-----------------------------------------------\nNow translate this:\nThis prompt automatically detects the input language and translates it into the corresponding language:\nAutomatically detect the language and translate it. Image by Author\nA few notes:\nI set context length to 2—only the current text and translation are kept. This prevents interference from past chats.\nI lock down translations for special terms because models often disagree on them.\nI end with “Now translate this:”. Even though LLMs use Transformer architecture, they still predict the next token based on prior ones. Sometimes the input is a reader’s question—if I don’t add this line, the LLM answers the question instead of translating it. This phrase makes the task clear.\nArticle translation prompt\nEnglish isn’t my first language, so I always need to translate my new articles.\nAt first, I used DeepL plus Grammarly for polishing. Paying for two subscriptions every month got expensive—and let’s be honest, machine translation isn’t great.\nSo as soon as GPT-3.5 came out, I switched to using LLMs for translation. Even the article you’re reading now was translated by an LLM:\n## Role\nYou are a senior data science expert and blog editor.\n\n## Task\nI wrote a Chinese data science article. Translate it into English.\n\n## Rules\n- Keep my original paragraph breaks.\n- Never add code that wasn’t there.\n- Avoid adverbs, prepositions, and passive voice.\n- **Only translate—don’t rewrite or change my content.**\n\n## Style\n- Conversational, light, and cheerful.\n- Don’t bold the first word or phrase in list items.\n- Use Title Case for headings and Sentence case for subheadings.\n\n## Tone\n- Keep it simple and easy to understand.\n- Use words any US 12th grader would know.\n- Sound like you’re chatting with a good friend.\n\n## Audience\nBeginners in data science and people curious about the field.\n\n## Special Terms\nTranslate these terms as follows:\n[Chinese phrase]: [English translation]\n大模型: LLM\n大语言模型: LLM\n私有化部署: self-hosted\nData science research assistant\nMy day job is data science, so I trained a specialized assistant—not a general-purpose one. I want to write code that matches my habits. Over time, these preferences settled into the “Requirements” section:\n## Role\nYou are a data scientist acting as my programming assistant. Help me improve my data science coding and algorithm skills.\n\n## Requirements\n1. Be truthful and precise. Never make things up.\n2. Ensure all code runs correctly.\n3. Use Python 3.12+ features, syntax, APIs, and best practices.\n4. Always use the latest versions and APIs of third-party libraries.\n5. Write clean, efficient, readable code.\n6. Comment only when necessary.\n7. Use vertical bar | for type unions.\n8. Prefer `with` statements.\n9. Use `pathlib` for file and directory operations.\n\n## Tool Use\n* tavily-search: Always use `\"search_depth\": 'advanced'`.\n\n## Response\nBe truthful, thorough, well-organized, and accurate.\nRemember the MCP tip earlier? Here I tell the LLM to use tavily’s\nadvanced\nmode for deep web searches when it lacks info.\nHonestly, with this setup plus Gemini 3.0 Pro, the LLM has massively boosted my data science learning—high efficiency and minimal hallucinations.\nGeneral-purpose daily assistant\nThis one’s simple. I just want honest, helpful answers—no fake positivity like Qwen3-Max’s constant praise. It’s great for everyday questions, and Qwen3-Max is cheaper too:\n## Role\nYou are my personal assistant. Give me sincere, useful advice for life and work.\n\n## Requirements\n* All knowledge, sources, and text must be real and accurate. No fabrications.\n* Never lie. If you don’t know something, say so.\n* Don’t just agree with me—point out problems or suggest improvements.\n\n## Output\n* Never use em dashes in your replies.\nWrap-Up\nThat’s all the LLM tips and prompt examples I’ve gathered over the past two years. They’re not perfect, but they’ve seriously boosted my daily productivity. I hope they help you, too.\nI’ll keep updating this post with more practical tricks. If there’s something you’d like to see, leave me a comment!\nFollow Data Leads Future\nOne practical story every month, sharing my hard-learned experiences in the enterprise AI space.\nSubscribe\nEmail sent! Check your inbox to complete your signup.\nYou can unsubscribe anytime.\nRecommended Enterprise AI Courses\nGetting the hang of some AI coding tricks is just the beginning. To learn the AI development tech stack more systematically and grow from an \"AI enthusiast\" to an \"AI-driven software engineer,\" here are some courses I'd recommend to you:\nDive deeper into AI coding and agent building. Check out Vanderbilt University's\nGenerative AI Software Engineering Specialization\non Coursera.\nTo build real, production-ready enterprise AI agent apps to kickstart your AI career. The\nIBM AI Developer Professional Certificate\nis a great fit here.\nBoth courses are included in\nCoursera Plus\n. If you're planning to level up in both AI engineering and architecture this year, the annual subscription is definitely the better deal.",
  "metadata": {
    "title": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient",
    "description": "I've shared some prompts and LLM tips I use in my daily work. They've boosted my productivity and learning—and they can help you too.",
    "keywords": null,
    "author": null,
    "og:site_name": "Data Leads Future",
    "og:type": "article",
    "og:title": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient",
    "og:description": "Can they help you too?",
    "og:url": "https://www.dataleadsfuture.com/share-my-llm-prompts-and-tips-that-make-work-and-learning-super-efficient/",
    "og:image": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/size/w1200/2025/11/cover-1.webp",
    "og:image:width": "1200",
    "og:image:height": "686",
    "twitter:card": "summary_large_image",
    "twitter:title": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient",
    "twitter:description": "Can they help you too?",
    "twitter:url": "https://www.dataleadsfuture.com/share-my-llm-prompts-and-tips-that-make-work-and-learning-super-efficient/",
    "twitter:image": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/size/w1200/2025/11/cover-1.webp",
    "twitter:label1": "Written by",
    "twitter:data1": "Peng Qian",
    "twitter:label2": "Filed under",
    "twitter:data2": "Career Growth, Generative AI",
    "twitter:site": "@qtalen",
    "twitter:creator": "@qtalen",
    "article:published_time": "2025-11-28T04:33:34.000Z",
    "article:modified_time": "2026-07-24T01:54:14.000Z",
    "article:tag": "Generative AI"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [
    {
      "file": "attachments/dc83721ce28c/code/body-000.txt",
      "chars": 748,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-001.txt",
      "chars": 132,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-002.txt",
      "chars": 144,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-003.txt",
      "chars": 419,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-004.txt",
      "chars": 722,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-005.txt",
      "chars": 842,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-006.txt",
      "chars": 695,
      "language": "text"
    },
    {
      "file": "attachments/dc83721ce28c/code/body-007.txt",
      "chars": 355,
      "language": "text"
    }
  ],
  "images": [
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/size/w1200/2025/11/cover-1.webp",
      "bytes": 93598,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/000.webp",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/size/w1200/2025/11/cover-1.webp",
      "alt": "Share My LLM Prompts and Tips That Make Work and Learning Super Efficient.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-19.png",
      "bytes": 63341,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/005.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-19.png",
      "alt": "Configure the model service in Cherry Studio's settings interface.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-21.png",
      "bytes": 124765,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/008.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-21.png",
      "alt": "Enter the prompt you want to share today in the agent interface.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-23.png",
      "bytes": 57685,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/011.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-23.png",
      "alt": "Just add the agent you just set up as an assistant, and you're good to go!",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-24.png",
      "bytes": 57057,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/014.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-24.png",
      "alt": "You can find the JSON for configuring MCP on the official websites of the various tools.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-25.png",
      "bytes": 60121,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/017.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-25.png",
      "alt": "When using tavily-mcp, the agent will try searching with multiple keywords until it finds the answer.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-26.png",
      "bytes": 47827,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/020.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-26.png",
      "alt": "What you think is a clearer format doesn't mean the LLM sees it that way too.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-18.png",
      "bytes": 37792,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/022.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-18.png",
      "alt": "Ask the LLM to repeat the instructions I gave it.",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/icon/color_192_192-46.png",
      "bytes": 17721,
      "reused": false,
      "local_path": "attachments/dc83721ce28c/images/body-aae2500c00a73fdc5715.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/icon/color_192_192-46.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/thumbnail/generated_00-1.webp",
      "bytes": 88776,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/024.webp",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/thumbnail/generated_00-1.webp",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-27.png",
      "bytes": 46902,
      "reused": true,
      "local_path": "attachments/dc83721ce28c/images/025.png",
      "src": "https://storage.ghost.io/c/33/67/33678c00-2c15-4961-93e9-497b427e2006/content/images/2025/11/image-27.png",
      "alt": "Automatically detect the language and translate it. ",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [],
  "links": [
    {
      "href": "https://www.dataleadsfuture.com/tag/career-growth/",
      "label": "Career Growth",
      "type": "a"
    },
    {
      "href": "https://www.dataleadsfuture.com/author/peng/",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.cherry-ai.com/",
      "label": "Cherry Studio Community Edition",
      "type": "a"
    },
    {
      "href": "https://openrouter.ai/models",
      "label": "OpenRouter",
      "type": "a"
    },
    {
      "href": "https://imp.i384100.net/Agamy1",
      "label": "Generative AI Software Engineering Specialization",
      "type": "a"
    },
    {
      "href": "https://www.dataleadsfuture.com/use-llamaindex-workflow-to-create-an-ink-painting-style-image-generation-workflow/",
      "label": "Use LLamaIndex Workflow to Create an Ink Painting Style Image Generation Workflow Add strong artistic flair through fine",
      "type": "a"
    },
    {
      "href": "https://imp.i384100.net/qWVbNg",
      "label": "Generative AI Software Engineering Specialization",
      "type": "a"
    },
    {
      "href": "https://imp.i384100.net/B5eg04",
      "label": "IBM AI Developer Professional Certificate",
      "type": "a"
    },
    {
      "href": "https://imp.i384100.net/3kOjjB",
      "label": "Coursera Plus",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:47:48Z",
  "source_url": "https://www.dataleadsfuture.com/share-my-llm-prompts-and-tips-that-make-work-and-learning-super-efficient/",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 17721,
  "expected_body_images": 11,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/dc83721ce28c/pages/source.html",
  "local_html": "attachments/dc83721ce28c/pages/article.html",
  "body_base_path": "attachments/dc83721ce28c/pages/",
  "body_markdown_path": "attachments/dc83721ce28c/pages/article.md"
}