scientific-slides by davila7/claude-code-templates
npx skills add https://github.com/davila7/claude-code-templates --skill scientific-slides科学演示是交流研究成果、分享发现并与学术和专业受众互动的重要媒介。本技能提供了创建有效科学演示的全面指导,涵盖从结构设计、内容开发到视觉设计和演讲准备的全过程。
核心重点:适用于会议、研讨会、答辩和专业演讲的口头演示。
关键设计理念:科学演示应具备视觉吸引力和研究支撑。务必避免枯燥、文字密集的幻灯片。优秀的科学演示结合了:
请记住:枯燥的演示 = 被遗忘的科学。在通过恰当引用保持科学严谨性的同时,让你的幻灯片在视觉上令人难忘。
此技能适用于以下场景:
此技能使用 Nano Banana Pro AI 自动生成出色的演示幻灯片。
根据输出格式,有两种工作流程:
使用 Nano Banana Pro 将每张幻灯片生成为完整图像,然后合并成 PDF。这能产生最具视觉冲击力的效果。
工作原理:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
步骤 1:规划每张幻灯片
在生成之前,为你的演示文稿创建详细计划:
# 演示文稿计划:机器学习导论
## 幻灯片 1:标题页
- 标题:"机器学习:从理论到实践"
- 副标题:"AI 大会 2025"
- 演讲者:Jane Smith 博士,XYZ 大学
- 视觉:现代抽象神经网络背景
## 幻灯片 2:引言
- 标题:"为何机器学习至关重要"
- 要点:行业采用、突破性应用、未来潜力
- 视觉:展示不同机器学习应用的图标(医疗保健、金融、机器人技术)
## 幻灯片 3:核心概念
- 标题:"三种学习类型"
- 内容:监督学习、无监督学习、强化学习
- 视觉:三部分示意图,展示每种类型及示例
... (为所有幻灯片继续)
步骤 2:生成每张幻灯片
使用 generate_slide_image.py 脚本创建每张幻灯片。
关键:格式一致性协议
为确保演示文稿中所有幻灯片的格式统一:
定义格式目标,并在每个提示词中包含它:
生成后续幻灯片时,始终使用 --attach 附加前一张幻灯片:
默认作者为 "K-Dense",除非指定了其他名称
在提示词中直接包含引用,用于参考研究的幻灯片:
为结果幻灯片附加现有图表/数据(对于数据驱动的演示文稿至关重要):
figures/、results/、plots/、images/)--attach 包含这些图表,以便 Nano Banana Pro 可以整合它们:
--attach fig1.png --attach fig2.png包含格式一致性、引用和图表附加的示例:
# 标题页(第一张幻灯片 - 确立样式)
python scripts/generate_slide_image.py "演示文稿标题页:'机器学习:从理论到实践'。副标题:'AI 大会 2025'。演讲者:K-Dense。格式目标:深蓝色背景 (#1a237e)、白色文字、金色点缀 (#ffc107)、极简设计、无衬线字体、充足边距、无装饰元素。" -o slides/01_title.png
# 包含引用的内容幻灯片(附加前一张幻灯片以保持一致性)
python scripts/generate_slide_image.py "演示文稿幻灯片标题为'为何机器学习至关重要'。三个要点配简单图标:1) 行业采用,2) 突破性应用,3) 未来潜力。引用:在底部以小号文字包含:(LeCun 等, 2015; Goodfellow 等, 2016)。格式目标:匹配附加幻灯片样式 - 深蓝色背景、白色文字、金色点缀、极简专业设计、无视觉杂乱。" -o slides/02_intro.png --attach slides/01_title.png
# 包含多个引用的背景幻灯片
python scripts/generate_slide_image.py "演示文稿幻灯片标题为'深度学习革命'。关键里程碑:ImageNet 突破 (2012)、Transformer 架构 (2017)、GPT 模型 (2018-至今)。引用:在底部显示参考文献:(Krizhevsky 等, 2012; Vaswani 等, 2017; Brown 等, 2020)。格式目标:完全匹配附加幻灯片样式 - 相同颜色、字体、极简设计。" -o slides/03_background.png --attach slides/02_intro.png
# 结果幻灯片 - 附加工作目录中的实际数据图表
# 首先,检查存在哪些图表:ls figures/ 或 ls results/
python scripts/generate_slide_image.py "演示文稿幻灯片标题为'模型性能结果'。创建一张幻灯片来展示附加的准确率图表。要突出的关键发现:1) 达到 95% 准确率,2) 比基线高出 12%,3) 在测试集上表现一致。引用:在底部包含:(我们的结果, 2025)。格式目标:完全匹配附加幻灯片样式。" -o slides/04_results.png --attach slides/03_background.png --attach figures/accuracy_chart.png
# 结果幻灯片 - 多图表比较
python scripts/generate_slide_image.py "演示文稿幻灯片标题为'改进前后对比'。使用两张附加的图表构建一张并排比较幻灯片。左侧:基线结果,右侧:我们改进后的结果。添加简要标签解释改进之处。格式目标:完全匹配附加幻灯片样式。" -o slides/05_comparison.png --attach slides/04_results.png --attach figures/baseline.png --attach figures/improved.png
# 方法学幻灯片 - 附加现有示意图
python scripts/generate_slide_image.py "演示文稿幻灯片标题为'系统架构'。展示附加的架构图并附简要解释要点:1) 输入处理,2) 模型推理,3) 输出生成。格式目标:完全匹配附加幻灯片样式。" -o slides/06_architecture.png --attach slides/05_comparison.png --attach diagrams/system_architecture.png
重要提示:创建结果幻灯片之前,始终:
ls -la figures/ 或 ls -la results/提示词模板:
在每个提示词中包含以下元素(根据需要自定义):
[幻灯片内容描述]
引用:在底部包含:(作者1 等, 年份; 作者2 等, 年份)
格式目标:[背景颜色], [文字颜色], [点缀颜色], 极简专业设计, 无装饰元素, 与附加幻灯片样式一致。
步骤 3:合并为 PDF
# 将所有幻灯片合并成一个 PDF 演示文稿
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
创建 PowerPoint 演示文稿时,使用 Nano Banana Pro 为每张幻灯片生成图像和图表,然后使用 PPTX 技能单独添加文本。
工作原理:
--visual-only 标志的 Nano Banana Pro 为幻灯片创建图像步骤 1:为每张幻灯片生成视觉元素
# 为引言幻灯片生成图表
python scripts/generate_slide_image.py "展示机器学习应用的专业插图:医疗诊断、金融分析、自动驾驶汽车和机器人技术。现代扁平化设计,白色背景上的彩色图标。" -o figures/ml_applications.png --visual-only
# 为方法学幻灯片生成示意图
python scripts/generate_slide_image.py "显示输入层、三个隐藏层和输出层的神经网络架构图。简洁、技术风格,带节点连接。蓝灰色配色方案。" -o figures/neural_network.png --visual-only
# 为结果生成概念图
python scripts/generate_slide_image.py "展示改进前后的对比:左侧显示杂乱数据,右侧显示有序见解。用箭头连接两者。专业商务风格。" -o figures/results_visual.png --visual-only
步骤 2:使用 PPTX 技能构建 PowerPoint
使用 PPTX 技能的 html2pptx 工作流程创建包含以下内容的幻灯片:
完整的 PPTX 创建文档请参见 document-skills/pptx/SKILL.md。
使用 Nano Banana Pro AI 生成演示幻灯片或视觉元素。
# 完整幻灯片(默认)- 将完整幻灯片生成为图像
python scripts/generate_slide_image.py "幻灯片描述" -o output.png
# 仅视觉元素 - 仅生成用于嵌入 PPT 的图像/图表
python scripts/generate_slide_image.py "视觉描述" -o output.png --visual-only
# 附加参考图像(Nano Banana Pro 将看到这些)
python scripts/generate_slide_image.py "创建一张解释此图表的幻灯片" -o slide.png --attach chart.png
python scripts/generate_slide_image.py "将这些合并成一张比较幻灯片" -o compare.png --attach before.png --attach after.png
选项:
-o, --output:输出文件路径(必需)--attach IMAGE:附加图像文件作为生成的上下文(可多次使用)--visual-only:仅生成视觉元素/图表,而非完整幻灯片--iterations:最大优化迭代次数(默认:2)--api-key:OpenRouter API 密钥(或设置 OPENROUTER_API_KEY 环境变量)-v, --verbose:详细输出附加参考图像:
当你希望 Nano Banana Pro 将现有图像作为上下文查看时,使用 --attach:
环境设置:
export OPENROUTER_API_KEY='your_api_key_here'
# 获取密钥地址:https://openrouter.ai/keys
将多张幻灯片图像合并为单个 PDF。
# 合并 PNG 文件
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
# 按顺序合并特定文件
python scripts/slides_to_pdf.py title.png intro.png methods.png -o talk.pdf
# 从目录合并(按文件名排序)
python scripts/slides_to_pdf.py slides/ -o presentation.pdf
选项:
-o, --output:输出 PDF 路径(必需)--dpi:PDF 分辨率(默认:150)-v, --verbose:详细输出提示: 为幻灯片命名时加上数字以便正确排序:01_title.png、02_intro.png 等。
对于完整幻灯片,请包含:
示例提示词:
标题页:
"医学研究报告的标题页。标题:'癌症免疫疗法的进展'。副标题:'2024 年临床试验结果'。专业医学主题,背景带有微妙的 DNA 双螺旋。海军蓝和白色配色方案。"
内容页:
"演示文稿幻灯片标题为'关键发现'。三个要点:1) 响应率提高 40%,2) 副作用减少,3) 生存期延长。包含相关医学图标。简洁、专业设计,绿白配色。"
示意图页:
"展示研究方法的演示文稿幻灯片。标题:'研究设计'。流程图显示:患者筛选 → 随机化 → 治疗组(A、B、对照组) → 随访 → 分析。CONSORT 风格流程图。专业学术风格。"
对于要嵌入 PowerPoint 的图像,仅关注视觉元素:
"展示机器学习流程的流程图:数据收集 → 预处理 → 模型训练 → 验证 → 部署。简洁技术风格,蓝灰色配色。"
"云服务器的概念图,包含数据流和连接设备。现代扁平化设计,适用于商务演示。"
"细胞分裂过程的科学示意图,显示有丝分裂各阶段。教育风格,带标签,色盲友好配色。"
除了幻灯片生成,还可使用 scientific-schematics 技能制作技术示意图:
何时使用 scientific-schematics 替代:
如何生成示意图:
python scripts/generate_schematic.py "你的示意图描述" -o figures/output.png
有关创建示意图的详细指导,请参阅 scientific-schematics 技能文档。
构建具有清晰叙事流程和适合不同场景结构的演示文稿。详细指导请参阅 references/presentation_structure.md。
通用故事脉络:
特定演讲类型结构:
创建专业、可读性强且易于理解的幻灯片,以增强理解。完整的设计指南请参阅 references/slide_design_principles.md。
反面模式:避免枯燥、文字密集的演示文稿
❌ 导致演示文稿枯燥且易被遗忘的因素:
✅ 使演示文稿引人入胜且令人难忘的因素:
核心设计原则:
视觉优先方法(关键):
简洁有力:
增强吸引力的排版:
增强冲击力的色彩:
增强视觉趣味的布局:
为演示场景调整科学图表。详细指导请参阅 references/data_visualization_slides.md。
与期刊图表的区别:
可视化最佳实践:
需避免的常见错误:
不同的演示场景需要不同的方法。关于每种类型的全面指导,请参阅 references/talk_types_guide.md。
会议演讲(10-20 分钟):
学术研讨会(45-60 分钟):
论文答辩(45-60 分钟):
项目资助提案(10-20 分钟):
期刊俱乐部(20-45 分钟):
最适合:视觉震撼的幻灯片、快速创建、非技术受众
这是默认且推荐的方法。 使用 AI 将每张幻灯片生成为完整图像。
工作流程:
generate_slide_image.py 生成每张幻灯片slides_to_pdf.py 合并为 PDF# 生成幻灯片
python scripts/generate_slide_image.py "标题:引言..." -o slides/01.png
python scripts/generate_slide_image.py "标题:方法..." -o slides/02.png
# 合并为 PDF
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
优势:
最适合:
最适合:可编辑的幻灯片、自定义设计、基于模板的工作流程
参考:完整文档请参见 document-skills/pptx/SKILL.md
使用带 --visual-only 的 Nano Banana Pro 生成图像,然后添加文本构建 PPTX。
关键资源:
assets/powerpoint_design_guide.md:完整的 PowerPoint 设计指南html2pptx.md:程序化创建工作流程rearrange.py、inventory.py、replace.py、thumbnail.py工作流程:
generate_slide_image.py --visual-only 生成视觉元素优势:
最适合:数学内容、一致的格式、版本控制
参考:完整文档请参见 references/beamer_guide.md
可用模板:
assets/beamer_template_conference.tex:15 分钟会议演讲assets/beamer_template_seminar.tex:45 分钟学术研讨会assets/beamer_template_defense.tex:学位论文答辩工作流程:
优势:
通过视觉检查实现迭代改进。完整工作流程请参阅 references/visual_review_workflow.md。
视觉验证工作流程:
步骤 1:生成 PDF(如果还不是 PDF)
步骤 2:转换为图像
# 使用 pdf_to_images 脚本
python scripts/pdf_to_images.py presentation.pdf review/slide --dpi 150
# 或使用 pptx 技能的缩略图工具
python ../document-skills/pptx/scripts/thumbnail.py presentation.pptx review/thumb
步骤 3:系统检查
检查每张幻灯片的以下问题:
步骤 4:记录问题
创建问题日志:
幻灯片编号 | 问题类型 | 描述 | 优先级
--------|-----------|-------------|----------
3 | 文本溢出 | 要点 4 超出框体 | 高
7 | 重叠 | 图表与标题重叠 | 高
12 | 字体大小 | 坐标轴标签过小 | 中
步骤 5:应用修复
对源文件进行修正:
步骤 6:重新验证
重复步骤 1-5,直到没有关键问题为止。
停止标准:
确保演示文稿符合分配的时间。全面的时间指导请参阅 assets/timing_guidelines.md。
每分钟一张幻灯片的规则:
时间分配:
练习要求:
时间检查点:
对于 15 分钟演讲:
应急策略:
自动化验证:
# 验证幻灯片数量、时间、文件大小
python scripts/validate_presentation.py presentation.pdf --duration 15
# 生成报告,内容包括:
# - 幻灯片数量与建议范围对比
# - 文件大小警告
# - 幻灯片尺寸
# - 字体大小问题(PowerPoint)
# - 编译成功与否(Beamer)
手动验证清单:
定义背景:
研究与文献综述(使用 research-lookup 技能):
制定内容大纲:
15 分钟演讲大纲示例:
1. 标题(30 秒)
2. 钩子:引人入胜的问题(60 秒)[通过 research-lookup 引用 1-2 篇论文]
3. 背景(90 秒)[引用 3-4 篇确立背景的关键论文]
4. 研究问题(45 秒)[引用显示空白的论文]
5. 方法概述(2 分钟)
6-8. 主要结果 1(3 分钟,3 张幻灯片)
9-10. 主要结果 2(2 分钟,2 张幻灯片)
11-12. 结果 3 或验证(2 分钟,2 张幻灯片)
13-14. 讨论与意义(2 分钟)[与 2-3 项先前研究比较]
15. 结论(45 秒)
16. 致谢(15 秒)
注意:在创建幻灯片之前,使用 research-lookup 查找用于背景(幻灯片 2-4)
和讨论(幻灯片 13-14)的论文。
选择实现方法:
选项 A:PowerPoint(通过 PPTX 技能)
assets/powerpoint_design_guide.mddocument-skills/pptx/SKILL.md选项 B:LaTeX Beamer
references/beamer_guide.mdassets/ 中选择合适的模板设计考虑因素(使其具有视觉吸引力):
填充幻灯片(视觉优先策略):
视觉内容要求(使幻灯片引人入胜):
Scientific presentations are a critical medium for communicating research, sharing findings, and engaging with academic and professional audiences. This skill provides comprehensive guidance for creating effective scientific presentations, from structure and content development to visual design and delivery preparation.
Key Focus : Oral presentations for conferences, seminars, defenses, and professional talks.
CRITICAL DESIGN PHILOSOPHY : Scientific presentations should be VISUALLY ENGAGING and RESEARCH-BACKED. Avoid dry, text-heavy slides at all costs. Great scientific presentations combine:
Remember : Boring presentations = forgotten science. Make your slides visually memorable while maintaining scientific rigor through proper citations.
This skill should be used when:
This skill uses Nano Banana Pro AI to generate stunning presentation slides automatically.
There are two workflows depending on output format:
Generate each slide as a complete image using Nano Banana Pro, then combine into a PDF. This produces the most visually stunning results.
How it works:
Step 1: Plan Each Slide
Before generating, create a detailed plan for your presentation:
# Presentation Plan: Introduction to Machine Learning
## Slide 1: Title Slide
- Title: "Machine Learning: From Theory to Practice"
- Subtitle: "AI Conference 2025"
- Speaker: Dr. Jane Smith, University of XYZ
- Visual: Modern abstract neural network background
## Slide 2: Introduction
- Title: "Why Machine Learning Matters"
- Key points: Industry adoption, breakthrough applications, future potential
- Visual: Icons showing different ML applications (healthcare, finance, robotics)
## Slide 3: Core Concepts
- Title: "The Three Types of Learning"
- Content: Supervised, Unsupervised, Reinforcement
- Visual: Three-part diagram showing each type with examples
... (continue for all slides)
Step 2: Generate Each Slide
Use the generate_slide_image.py script to create each slide.
CRITICAL: Formatting Consistency Protocol
To ensure unified formatting across all slides in a presentation:
Define a Formatting Goal at the start of your presentation and include it in EVERY prompt:
Always attach the previous slide when generating subsequent slides using --attach:
Default author is "K-Dense" unless another name is specified
Include citations directly in the prompt for slides that reference research:
Attach existing figures/data for results slides (CRITICAL for data-driven presentations):
Example with formatting consistency, citations, and figure attachments:
# Title slide (first slide - establishes the style)
python scripts/generate_slide_image.py "Title slide for presentation: 'Machine Learning: From Theory to Practice'. Subtitle: 'AI Conference 2025'. Speaker: K-Dense. FORMATTING GOAL: Dark blue background (#1a237e), white text, gold accents (#ffc107), minimal design, sans-serif fonts, generous margins, no decorative elements." -o slides/01_title.png
# Content slide with citations (attach previous slide for consistency)
python scripts/generate_slide_image.py "Presentation slide titled 'Why Machine Learning Matters'. Three key points with simple icons: 1) Industry adoption, 2) Breakthrough applications, 3) Future potential. CITATIONS: Include at bottom in small text: (LeCun et al., 2015; Goodfellow et al., 2016). FORMATTING GOAL: Match attached slide style - dark blue background, white text, gold accents, minimal professional design, no visual clutter." -o slides/02_intro.png --attach slides/01_title.png
# Background slide with multiple citations
python scripts/generate_slide_image.py "Presentation slide titled 'Deep Learning Revolution'. Key milestones: ImageNet breakthrough (2012), transformer architecture (2017), GPT models (2018-present). CITATIONS: Show references at bottom: (Krizhevsky et al., 2012; Vaswani et al., 2017; Brown et al., 2020). FORMATTING GOAL: Match attached slide style exactly - same colors, fonts, minimal design." -o slides/03_background.png --attach slides/02_intro.png
# RESULTS SLIDE - Attach actual data figure from working directory
# First, check what figures exist: ls figures/ or ls results/
python scripts/generate_slide_image.py "Presentation slide titled 'Model Performance Results'. Create a slide presenting the attached accuracy chart. Key findings to highlight: 1) 95% accuracy achieved, 2) Outperforms baseline by 12%, 3) Consistent across test sets. CITATIONS: Include at bottom: (Our results, 2025). FORMATTING GOAL: Match attached slide style exactly." -o slides/04_results.png --attach slides/03_background.png --attach figures/accuracy_chart.png
# RESULTS SLIDE - Multiple figures comparison
python scripts/generate_slide_image.py "Presentation slide titled 'Before vs After Comparison'. Build a side-by-side comparison slide using the two attached figures. Left: baseline results, Right: our improved results. Add brief labels explaining the improvement. FORMATTING GOAL: Match attached slide style exactly." -o slides/05_comparison.png --attach slides/04_results.png --attach figures/baseline.png --attach figures/improved.png
# METHODOLOGY SLIDE - Attach existing diagram
python scripts/generate_slide_image.py "Presentation slide titled 'System Architecture'. Present the attached architecture diagram with brief explanatory bullet points: 1) Input processing, 2) Model inference, 3) Output generation. FORMATTING GOAL: Match attached slide style exactly." -o slides/06_architecture.png --attach slides/05_comparison.png --attach diagrams/system_architecture.png
IMPORTANT: Before creating results slides, always:
ls -la figures/ or ls -la results/Prompt Template:
Include these elements in every prompt (customize as needed):
[Slide content description]
CITATIONS: Include at bottom: (Author1 et al., Year; Author2 et al., Year)
FORMATTING GOAL: [Background color], [text color], [accent color], minimal professional design, no decorative elements, consistent with attached slide style.
Step 3: Combine to PDF
# Combine all slides into a PDF presentation
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
When creating PowerPoint presentations, use Nano Banana Pro to generate images and figures for each slide, then add text separately using the PPTX skill.
How it works:
--visual-only flag to create images for slidesStep 1: Generate Visuals for Each Slide
# Generate a figure for the introduction slide
python scripts/generate_slide_image.py "Professional illustration showing machine learning applications: healthcare diagnosis, financial analysis, autonomous vehicles, and robotics. Modern flat design, colorful icons on white background." -o figures/ml_applications.png --visual-only
# Generate a diagram for the methods slide
python scripts/generate_slide_image.py "Neural network architecture diagram showing input layer, three hidden layers, and output layer. Clean, technical style with node connections. Blue and gray color scheme." -o figures/neural_network.png --visual-only
# Generate a conceptual graphic for results
python scripts/generate_slide_image.py "Before and after comparison showing improvement: left side shows cluttered data, right side shows organized insights. Arrow connecting them. Professional business style." -o figures/results_visual.png --visual-only
Step 2: Build PowerPoint with PPTX Skill
Use the PPTX skill's html2pptx workflow to create slides that include:
See document-skills/pptx/SKILL.md for complete PPTX creation documentation.
Generate presentation slides or visuals using Nano Banana Pro AI.
# Full slide (default) - generates complete slide as image
python scripts/generate_slide_image.py "slide description" -o output.png
# Visual only - generates just the image/figure for embedding in PPT
python scripts/generate_slide_image.py "visual description" -o output.png --visual-only
# With reference images attached (Nano Banana Pro will see these)
python scripts/generate_slide_image.py "Create a slide explaining this chart" -o slide.png --attach chart.png
python scripts/generate_slide_image.py "Combine these into a comparison slide" -o compare.png --attach before.png --attach after.png
Options:
-o, --output: Output file path (required)--attach IMAGE: Attach image file(s) as context for generation (can use multiple times)--visual-only: Generate just the visual/figure, not a complete slide--iterations: Max refinement iterations (default: 2)--api-key: OpenRouter API key (or set OPENROUTER_API_KEY env var)-v, --verbose: Verbose outputAttaching Reference Images:
Use --attach when you want Nano Banana Pro to see existing images as context:
Environment Setup:
export OPENROUTER_API_KEY='your_api_key_here'
# Get key at: https://openrouter.ai/keys
Combine multiple slide images into a single PDF.
# Combine PNG files
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
# Combine specific files in order
python scripts/slides_to_pdf.py title.png intro.png methods.png -o talk.pdf
# From directory (sorted by filename)
python scripts/slides_to_pdf.py slides/ -o presentation.pdf
Options:
-o, --output: Output PDF path (required)--dpi: PDF resolution (default: 150)-v, --verbose: Verbose outputTip: Name slides with numbers for correct ordering: 01_title.png, 02_intro.png, etc.
For complete slides, include:
Example prompts:
Title slide:
"Title slide for a medical research presentation. Title: 'Advances in Cancer Immunotherapy'. Subtitle: 'Clinical Trial Results 2024'. Professional medical theme with subtle DNA helix in background. Navy blue and white color scheme."
Content slide:
"Presentation slide titled 'Key Findings'. Three bullet points: 1) 40% improvement in response rate, 2) Reduced side effects, 3) Extended survival outcomes. Include relevant medical icons. Clean, professional design with green and white colors."
Diagram slide:
"Presentation slide showing the research methodology. Title: 'Study Design'. Flowchart showing: Patient Screening → Randomization → Treatment Groups (A, B, Control) → Follow-up → Analysis. CONSORT-style flow diagram. Professional academic style."
For images to embed in PowerPoint, focus on the visual element only:
"Flowchart showing machine learning pipeline: Data Collection → Preprocessing → Model Training → Validation → Deployment. Clean technical style, blue and gray colors."
"Conceptual illustration of cloud computing with servers, data flow, and connected devices. Modern flat design, suitable for business presentation."
"Scientific diagram of cell division process showing mitosis phases. Educational style with labels, colorblind-friendly colors."
In addition to slide generation, use the scientific-schematics skill for technical diagrams:
When to use scientific-schematics instead:
How to generate schematics:
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.
Build presentations with clear narrative flow and appropriate structure for different contexts. For detailed guidance, refer to references/presentation_structure.md.
Universal Story Arc :
Talk-Specific Structures :
Create professional, readable, and accessible slides that enhance understanding. For complete design guidelines, refer to references/slide_design_principles.md.
ANTI-PATTERN: Avoid Dry, Text-Heavy Presentations
❌ What Makes Presentations Dry and Forgettable:
✅ What Makes Presentations Engaging and Memorable:
Core Design Principles :
Visual-First Approach (CRITICAL):
Simplicity with Impact :
Typography for Engagement :
Color for Impact :
Layout for Visual Interest :
Adapt scientific figures for presentation context. For detailed guidance, refer to references/data_visualization_slides.md.
Key Differences from Journal Figures :
Visualization Best Practices :
Common Mistakes to Avoid :
Different presentation contexts require different approaches. For comprehensive guidance on each type, refer to references/talk_types_guide.md.
Conference Talks (10-20 minutes):
Academic Seminars (45-60 minutes):
Thesis Defenses (45-60 minutes):
Grant Pitches (10-20 minutes):
Journal Clubs (20-45 minutes):
Best for : Visually stunning slides, fast creation, non-technical audiences
This is the default and recommended approach. Generate each slide as a complete image using AI.
Workflow :
generate_slide_image.pyslides_to_pdf.py# Generate slides
python scripts/generate_slide_image.py "Title: Introduction..." -o slides/01.png
python scripts/generate_slide_image.py "Title: Methods..." -o slides/02.png
# Combine to PDF
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
Advantages :
Best for :
Best for : Editable slides, custom designs, template-based workflows
Reference : See document-skills/pptx/SKILL.md for complete documentation
Use Nano Banana Pro with --visual-only to generate images, then build PPTX with text.
Key Resources :
assets/powerpoint_design_guide.md: Complete PowerPoint design guidehtml2pptx.md: Programmatic creation workflowrearrange.py, inventory.py, replace.py, thumbnail.pyWorkflow :
generate_slide_image.py --visual-onlyAdvantages :
Best for : Mathematical content, consistent formatting, version control
Reference : See references/beamer_guide.md for complete documentation
Templates Available :
assets/beamer_template_conference.tex: 15-minute conference talkassets/beamer_template_seminar.tex: 45-minute academic seminarassets/beamer_template_defense.tex: Dissertation defenseWorkflow :
Advantages :
Implement iterative improvement through visual inspection. For complete workflow, refer to references/visual_review_workflow.md.
Visual Validation Workflow :
Step 1: Generate PDF (if not already PDF)
Step 2: Convert to Images
# Using the pdf_to_images script
python scripts/pdf_to_images.py presentation.pdf review/slide --dpi 150
# Or use pptx skill's thumbnail tool
python ../document-skills/pptx/scripts/thumbnail.py presentation.pptx review/thumb
Step 3: Systematic Inspection
Check each slide for:
Step 4: Document Issues
Create issue log:
Slide # | Issue Type | Description | Priority
--------|-----------|-------------|----------
3 | Text overflow | Bullet 4 extends beyond box | High
7 | Overlap | Figure overlaps with caption | High
12 | Font size | Axis labels too small | Medium
Step 5: Apply Fixes
Make corrections to source files:
Step 6: Re-Validate
Repeat Steps 1-5 until no critical issues remain.
Stopping Criteria :
Ensure presentations fit allocated time. For comprehensive timing guidance, refer to assets/timing_guidelines.md.
The One-Slide-Per-Minute Rule :
Time Allocation :
Practice Requirements :
Timing Checkpoints :
For 15-minute talk:
Emergency Strategies :
Automated Validation :
# Validate slide count, timing, file size
python scripts/validate_presentation.py presentation.pdf --duration 15
# Generates report on:
# - Slide count vs. recommended range
# - File size warnings
# - Slide dimensions
# - Font size issues (PowerPoint)
# - Compilation success (Beamer)
Manual Validation Checklist :
Define Context :
Research and Literature Review (Use research-lookup skill):
Develop Content Outline :
Example Outline for 15-Minute Talk :
1. Title (30 sec)
2. Hook: Compelling problem (60 sec) [Cite 1-2 papers via research-lookup]
3. Background (90 sec) [Cite 3-4 key papers establishing context]
4. Research question (45 sec) [Cite papers showing gap]
5. Methods overview (2 min)
6-8. Main result 1 (3 min, 3 slides)
9-10. Main result 2 (2 min, 2 slides)
11-12. Result 3 or validation (2 min, 2 slides)
13-14. Discussion and implications (2 min) [Compare to 2-3 prior studies]
15. Conclusions (45 sec)
16. Acknowledgments (15 sec)
NOTE: Use research-lookup to find papers for background (slides 2-4)
and discussion (slides 13-14) BEFORE creating slides.
Choose Implementation Method :
Option A: PowerPoint (via PPTX skill)
assets/powerpoint_design_guide.mddocument-skills/pptx/SKILL.mdOption B: LaTeX Beamer
references/beamer_guide.mdassets/Design Considerations (Make It Visually Appealing):
Populate Slides (Visual-First Strategy):
VISUAL CONTENT REQUIREMENTS (Make Slides Engaging):
Scientific Content (Research-Backed):
Text Guidelines (Less is More):
Generate Images :
# Convert PDF to images
python scripts/pdf_to_images.py presentation.pdf review/slides
# Or create thumbnail grid
python ../document-skills/pptx/scripts/thumbnail.py presentation.pptx review/grid
Systematic Review :
Common Issues to Fix :
Iteration :
Practice Schedule :
What to Practice :
Refinement Based on Practice :
Technical Checks :
Content Final :
Delivery Prep :
Research Lookup (Critical for Scientific Presentations):
Scientific Writing :
PPTX Skill :
Data Visualization :
Dry, Boring Presentations (CRITICAL TO AVOID):
Too Much Content :
Too Much Text :
Missing Research Context :
Poor Narrative :
Rushing Through Results :
Generic, Default Appearance :
Text-Heavy, Visual-Poor :
Small Fonts :
Low Contrast :
Cluttered Slides :
Inconsistent Formatting :
Missing Visual Hierarchy :
Not Practicing :
No Time Checkpoints :
Going Over Time :
Skipping Conclusions :
generate_slide_image.py - Generate slides or visuals with AI:
# Full slide (for PDF workflow)
python scripts/generate_slide_image.py "Title: Introduction\nContent: Key points" -o slide.png
# Visual only (for PPT workflow)
python scripts/generate_slide_image.py "Diagram description" -o figure.png --visual-only
# Options:
# -o, --output Output file path (required)
# --visual-only Generate just the visual, not complete slide
# --iterations N Max refinement iterations (default: 2)
# -v, --verbose Verbose output
slides_to_pdf.py - Combine slide images into PDF:
# From glob pattern
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
# From directory (sorted by filename)
python scripts/slides_to_pdf.py slides/ -o presentation.pdf
# Options:
# -o, --output Output PDF path (required)
# --dpi N PDF resolution (default: 150)
# -v, --verbose Verbose output
validate_presentation.py :
python scripts/validate_presentation.py presentation.pdf --duration 15
# Checks:
# - Slide count vs. recommended range
# - File size warnings
# - Slide dimensions
# - Font sizes (PowerPoint)
# - Compilation (Beamer)
pdf_to_images.py :
python scripts/pdf_to_images.py presentation.pdf output/slide --dpi 150
# Converts PDF to images for visual inspection
# Supports: JPG, PNG
# Adjustable DPI
# Page range selection
From document-skills/pptx/scripts/:
thumbnail.py: Create thumbnail gridsrearrange.py: Duplicate and reorder slidesinventory.py: Extract text contentreplace.py: Update text programmaticallyRecommended :
Comprehensive guides for specific aspects:
references/presentation_structure.md : Detailed structure for all talk types, timing allocation, opening/closing strategies, transition techniquesreferences/slide_design_principles.md : Typography, color theory, layout, accessibility, visual hierarchy, design workflowreferences/data_visualization_slides.md : Simplifying figures, chart types, progressive disclosure, common mistakes, recreation workflowreferences/talk_types_guide.md : Specific guidance for conferences, seminars, defenses, grants, journal clubs, with examplesreferences/beamer_guide.md : Complete LaTeX Beamer documentation, themes, customization, advanced features, compilationreferences/visual_review_workflow.md : PDF to images conversion, systematic inspection, issue documentation, iterative improvementassets/beamer_template_conference.tex : 15-minute conference talk templateassets/beamer_template_seminar.tex : 45-minute academic seminar templateassets/beamer_template_defense.tex : Dissertation defense templateassets/powerpoint_design_guide.md : Complete PowerPoint design and implementation guideassets/timing_guidelines.md : Comprehensive timing, pacing, and practice strategiesResearch & Plan (45 minutes):
Generate Slides with Nano Banana Pro (1-2 hours):
Important: Use consistent formatting, attach previous slides, and include citations!
# Title slide (establishes style - default author: K-Dense)
python scripts/generate_slide_image.py "Title slide: 'Your Research Title'. Conference name, K-Dense. FORMATTING GOAL: [your color scheme], minimal professional design, no decorative elements, clean and corporate." -o slides/01_title.png
# Introduction slide with citations (attach previous for consistency)
python scripts/generate_slide_image.py "Slide titled 'Why This Matters'. Three key points with simple icons. CITATIONS: Include at bottom: (Smith et al., 2023; Jones et al., 2024). FORMATTING GOAL: Match attached slide style exactly." -o slides/02_intro.png --attach slides/01_title.png
# Continue for each slide (always attach previous, include citations where relevant)
python scripts/generate_slide_image.py "Slide titled 'Methods'. Key methodology points. CITATIONS: (Based on Chen et al., 2022). FORMATTING GOAL: Match attached slide style exactly." -o slides/03_methods.png --attach slides/02_intro.png
# Combine to PDF
python scripts/slides_to_pdf.py slides/*.png -o presentation.pdf
3. Review & Iterate (30 minutes):
* Open the PDF and review each slide
* Regenerate any slides that need improvement
* Re-combine to PDF
4. Practice (2-3 hours):
* Practice 3-5 times with timer
* Aim for 13-14 minutes (leave buffer)
* Record yourself, watch playback
* **Prepare for questions** (use research-lookup to anticipate)
5. Finalize (30 minutes):
* Generate backup/appendix slides if needed
* Save multiple copies
* Test on presentation computer
Total time: ~5-6 hours for quality AI-generated presentation
If you need editable slides (e.g., for company templates):
Plan slides as above
Generate visuals with --visual-only flag:
python scripts/generate_slide_image.py "diagram description" -o figures/fig1.png --visual-only
Build PPTX using the PPTX skill with generated images
Add text separately using PPTX workflow
See document-skills/pptx/SKILL.md for complete PowerPoint workflow.
Remember :
Weekly Installs
525
Repository
GitHub Stars
22.6K
First Seen
Jan 21, 2026
Security Audits
Gen Agent Trust HubPassSocketFailSnykWarn
Installed on
opencode451
gemini-cli428
codex420
cursor408
github-copilot387
claude-code376
头脑风暴技能:AI协作设计流程,将创意转化为完整规范与实施计划
77,000 周安装
IMAP SMTP 邮件处理技能 - 开源邮件客户端集成开发工具
609 周安装
腾讯云CloudBase云函数开发指南:事件函数与HTTP函数部署调试全攻略
609 周安装
Power BI DAX 公式优化器 - 提升性能、可读性与可维护性的专家指南
7,400 周安装
cook-cli:CLI开发结构化工作流工具 - Plan→Code→Review→Test四阶段
2 周安装
AGENTS.md 通用 AI 代理配置指南 | 兼容 Claude、Cursor、GitHub Copilot 等 25+ 代理
2 周安装
Base链.basename.eth域名注册教程 - 智能体钱包名称注册完整指南
2 周安装
figures/, results/, plots/, images/)--attach to include these figures so Nano Banana Pro can incorporate them:
--attach fig1.png --attach fig2.png