More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    write literature guide

    1

    Generates structured Chinese and English literature guides from academic papers with technical precision.

    $12.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    write literature guide

    write literature guide

    Example session with this skill installed

    Create a Chinese literature guide for the paper 'Deep Learning for Structural Health Monitoring' found in my files. Include a reference section and focus on the experimental methodology.

    • Read your context and instructions
    • Compiled the write literature guide

    I have analyzed the provided paper on Structural Health Monitoring. Following the standard template, I have extracted the core technical facts and structured them into the required Chinese literature guide format.

    【文献导读】深度学习在结构健康监测中的应用研究

    论文信息

    • 题名: Deep Learning for Structural Health Monitoring: A Comprehensive Review
    • 作者: Zhang, Y., & Chen, J.
    • 期刊: Mechanical Systems and Signal Processing
    • DOI: 10.1016/j.ymssp.2023.110001
    • 年份: 2023
    • 卷期页: Vol. 185, pp. 45-67

    摘要
    本文综述了深度学习在结构健康监测(SHM)领域的最新进展。重点讨论了卷积神经网络(CNN)和长短期记忆网络(LSTM)在损伤识别与性能预测中的应用,分析了数据增强技术在处理非平衡数据集时的有效性。

    研究背景
    传统的SHM方法高度依赖人工特征提取,难以处理复杂环境下的非线性振动信号。随着传感器技术的普及,海量高维数据的实时处理成为工程瓶颈,亟需自动化端到端算法。

    研究方法

    1. 数据采集: 利用加速度传感器收集桥梁模型在不同载荷下的振动响应。
    2. 模型架构: 采用1D-CNN进行特征自动提取,结合双向LSTM捕捉时序相关性。
    3. 损失函数: 引入加权交叉熵损失以解决正常数据多于损伤数据的样本不平衡问题。

    结果

    • 准确率: 在Z24桥梁基准数据集上实现98.5%的损伤识别精度。
    • 鲁棒性: 在引入5%高斯白噪声的情况下,识别成功率保持在92%以上。
    • 效率: 推理时间相比于传统SVM方法降低了约60%。

    结论
    深度学习方法在SHM中表现出优异的自动化能力。未来的研究应侧重于提升物理一致性神经网络(PINN)的应用,以增强模型的可解释性。

    引用
    Zhang, Y., & Chen, J. (2023). Deep Learning for Structural Health Monitoring: A Comprehensive Review. Mechanical Systems and Signal Processing, 185, 45-67.

    Next steps

    • Review the 研究方法 section to ensure specific sensor parameters match your project.
    • Request a .docx version to apply the internal template formatting.
    • Provide a second paper to generate a comparative bilingual summary.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    This skill automates the creation of structured Chinese or English literature guides from academic papers, translations, or research notes. It targets technical and engineering research, extracting critical data points including methodologies, experimental conditions, and quantitative findings. By following a strict extraction hierarchy, it ensures that output remains grounded in source material while maintaining professional academic formatting.

    What it does

    • Structured Extraction identifies key metadata, research objectives, methodologies, and datasets from source documents.
    • Bilingual Support generates guides in Chinese, English, or bilingual formats regardless of the source language.
    • Technical Summarization distills complex engineering papers into concise sections covering background, methods, results, and conclusions.
    • Visual Mapping extracts and lists relevant figure and table titles to provide context for technical readers.
    • Document Formatting exports content to .docx files following specific layout rules and templates.

    How it works

    1. Inventory Files categorizes provided papers, notes, and samples to identify the primary source and reference styles.
    2. Determine Language sets the target output language based on user instruction or context.
    3. Extract Facts prioritizes reading of existing notes and conclusions to build a fact sheet of metrics and methods.
    4. Draft Guide follows a fixed column sequence (e.g., Paper Info, Abstract, Background, Methods) for the selected language.
    5. Quality Check verifies all numbers, names, and citations against the source text to prevent hallucination.

    Frameworks & tools

    This skill utilizes specialized logic defined in references/guide-rules.md for section templates, writing styles, and quality checklists. It supports PDF and text processing for extraction and OpenXML for .docx generation.

    Why this beats prompting it yourself

    Generic prompts often produce flowery summaries that miss technical nuances or fail to follow strict academic headers. This skill enforces a specific structural hierarchy and quality checklist derived from a professional sample library, ensuring consistent formatting for large literature reviews.

    Use cases

    • Draft professional literature guides for technical laboratory internal sharing.
    • Convert raw research notes and paper PDFs into standardized bilingual reports.
    • Translate and format English engineering papers into structured Chinese guides.
    • Perform quality control and formatting alignment on existing draft guides.

    Known limitations

    Does not support audio or video sources. Requires clear source text to extract metadata accurately. Formatting for .docx is restricted to the specific rules defined in the reference file.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Listed1 day ago

    What's inside

    Frequently Asked Questions