q-presentations

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

q-presentations — AI-Powered Slide Deck Generator

q-presentations — AI驱动的幻灯片生成工具

Built on the foundation of baoyu-slide-deck by baoyu, extended with organic content positioning, smart logo branding, and video-overlay-aware layout.
基于baoyu开发的baoyu-slide-deck构建,新增了自然内容定位、智能Logo品牌植入和适配视频叠加的布局功能。

Usage

使用方法

bash
/q-presentations path/to/content.md
/q-presentations path/to/content.md --style sketch-notes
/q-presentations path/to/content.md --audience executives
/q-presentations path/to/content.md --lang zh
/q-presentations path/to/content.md --slides 10
/q-presentations path/to/content.md --outline-only
/q-presentations  # Then paste content
bash
/q-presentations path/to/content.md
/q-presentations path/to/content.md --style sketch-notes
/q-presentations path/to/content.md --audience executives
/q-presentations path/to/content.md --lang zh
/q-presentations path/to/content.md --slides 10
/q-presentations path/to/content.md --outline-only
/q-presentations  # 然后粘贴内容

Script Directory

脚本目录

Agent Execution Instructions:
  1. Determine this SKILL.md file's directory path as
    SKILL_DIR
  2. Script path =
    ${SKILL_DIR}/scripts/<script-name>
ScriptPurpose
scripts/gen_slide.py
Generate slide images via Gemini API
scripts/overlay_logo.py
Apply Dr. Q logo overlay
scripts/merge_slides.py
Merge slides into PowerPoint (Python)
scripts/merge-to-pptx.ts
Merge slides into PowerPoint (Bun/TS)
scripts/merge-to-pdf.ts
Merge slides into PDF (Bun/TS)
Agent执行说明:
  1. 确定本SKILL.md文件的目录路径为
    SKILL_DIR
  2. 脚本路径 =
    ${SKILL_DIR}/scripts/<script-name>
脚本用途
scripts/gen_slide.py
通过Gemini API生成幻灯片图片
scripts/overlay_logo.py
应用Dr. Q Logo叠加
scripts/merge_slides.py
将幻灯片合并为PowerPoint(Python实现)
scripts/merge-to-pptx.ts
将幻灯片合并为PowerPoint(Bun/TS实现)
scripts/merge-to-pdf.ts
将幻灯片合并为PDF(Bun/TS实现)

Options

选项

OptionDescription
--style <name>
Visual style: preset name,
custom
, or custom style name
--audience <type>
Target: beginners, intermediate, experts, executives, general
--lang <code>
Output language (en, zh, ja, etc.)
--slides <number>
Target slide count (8-25 recommended, max 30)
--outline-only
Generate outline only, skip image generation
--prompts-only
Generate outline + prompts, skip images
--images-only
Generate images from existing prompts directory
--regenerate <N>
Regenerate specific slide(s):
--regenerate 3
or
--regenerate 2,5,8
--logo <position>
Logo placement: top-right (default), bottom-right, top-left, bottom-left, none
--video-overlay <side>
Side reserved for video overlay: right (default), left, bottom, none
Slide Count by Content Length:
ContentSlides
< 1000 words5-10
1000-3000 words10-18
3000-5000 words15-25
> 5000 words20-30 (consider splitting)
选项说明
--style <name>
视觉风格:预设名称、
custom
(自定义)或自定义风格名称
--audience <type>
目标受众:beginners(初学者)、intermediate(中级用户)、experts(专家)、executives(高管)、general(普通用户)
--lang <code>
输出语言(en、zh、ja等)
--slides <number>
目标幻灯片数量(推荐8-25张,最多30张)
--outline-only
仅生成大纲,跳过图片生成
--prompts-only
生成大纲+提示词,跳过图片生成
--images-only
从现有提示词目录生成图片
--regenerate <N>
重新生成指定幻灯片:
--regenerate 3
--regenerate 2,5,8
--logo <position>
Logo位置:top-right(右上角,默认)、bottom-right(右下角)、top-left(左上角)、bottom-left(左下角)、none(无)
--video-overlay <side>
预留视频叠加的侧边:right(右侧,默认)、left(左侧)、bottom(底部)、none(无)
按内容长度推荐幻灯片数量:
内容幻灯片数量
< 1000词5-10张
1000-3000词10-18张
3000-5000词15-25张
> 5000词20-30张(建议拆分)

Style System

风格系统

Presets

预设风格

PresetDimensionsBest For
blueprint
(Default)
grid + cool + technical + balancedArchitecture, system design
chalkboard
organic + warm + handwritten + balancedEducation, tutorials
corporate
clean + professional + geometric + balancedInvestor decks, proposals
minimal
clean + neutral + geometric + minimalExecutive briefings
sketch-notes
organic + warm + handwritten + balancedEducational, tutorials
watercolor
organic + warm + humanist + minimalLifestyle, wellness
dark-atmospheric
clean + dark + editorial + balancedEntertainment, gaming
notion
clean + neutral + geometric + denseProduct demos, SaaS
bold-editorial
clean + vibrant + editorial + balancedProduct launches, keynotes
editorial-infographic
clean + cool + editorial + denseTech explainers, research
fantasy-animation
organic + vibrant + handwritten + minimalEducational storytelling
intuition-machine
clean + cool + technical + denseTechnical docs, academic
pixel-art
pixel + vibrant + technical + balancedGaming, developer talks
scientific
clean + cool + technical + denseBiology, chemistry, medical
vector-illustration
clean + vibrant + humanist + balancedCreative, children's content
vintage
paper + warm + editorial + balancedHistorical, heritage
预设特点适用场景
blueprint
(默认)
网格+冷色调+技术风+均衡架构设计、系统设计
chalkboard
自然风+暖色调+手写体+均衡教育、教程
corporate
简洁+专业+几何风+均衡投资者演示、提案
minimal
简洁+中性+几何风+极简高管简报
sketch-notes
自然风+暖色调+手写体+均衡教育、教程
watercolor
自然风+暖色调+人文风+极简生活方式、健康养生
dark-atmospheric
简洁+深色+社论风+均衡娱乐、游戏
notion
简洁+中性+几何风+信息密集产品演示、SaaS
bold-editorial
简洁+鲜艳+社论风+均衡产品发布、主题演讲
editorial-infographic
简洁+冷色调+社论风+信息密集技术讲解、研究报告
fantasy-animation
自然风+鲜艳+手写体+极简教育类叙事内容
intuition-machine
简洁+冷色调+技术风+信息密集技术文档、学术内容
pixel-art
像素风+鲜艳+技术风+均衡游戏、开发者演讲
scientific
简洁+冷色调+技术风+信息密集生物、化学、医学
vector-illustration
简洁+鲜艳+人文风+均衡创意内容、儿童内容
vintage
纸张质感+暖色调+社论风+均衡历史、文化遗产

Style Dimensions

风格维度

DimensionOptionsDescription
Textureclean, grid, organic, pixel, paperVisual texture and background treatment
Moodprofessional, warm, cool, vibrant, dark, neutralColor temperature and palette style
Typographygeometric, humanist, handwritten, editorial, technicalHeadline and body text styling
Densityminimal, balanced, denseInformation density per slide
Full specs:
references/dimensions/*.md
维度选项说明
Texture(质感)clean(简洁)、grid(网格)、organic(自然)、pixel(像素)、paper(纸张)视觉质感与背景处理
Mood(氛围)professional(专业)、warm(温暖)、cool(冷峻)、vibrant(鲜艳)、dark(深色)、neutral(中性)色温与调色板风格
Typography(排版)geometric(几何)、humanist(人文)、handwritten(手写)、editorial(社论)、technical(技术)标题与正文字体风格
Density(密度)minimal(极简)、balanced(均衡)、dense(密集)单页幻灯片的信息密度
完整规格:
references/dimensions/*.md

Auto Style Selection

自动风格选择

Content SignalsPreset
tutorial, learn, education, guide, beginner
sketch-notes
classroom, teaching, school, chalkboard
chalkboard
architecture, system, data, analysis, technical
blueprint
creative, children, kids, cute
vector-illustration
briefing, academic, research, bilingual
intuition-machine
executive, minimal, clean, simple
minimal
saas, product, dashboard, metrics
notion
investor, quarterly, business, corporate
corporate
launch, marketing, keynote, magazine
bold-editorial
entertainment, music, gaming, atmospheric
dark-atmospheric
explainer, journalism, science communication
editorial-infographic
story, fantasy, animation, magical
fantasy-animation
gaming, retro, pixel, developer
pixel-art
biology, chemistry, medical, scientific
scientific
history, heritage, vintage, expedition
vintage
lifestyle, wellness, travel, artistic
watercolor
Default
blueprint
内容信号预设风格
tutorial(教程)、learn(学习)、education(教育)、guide(指南)、beginner(初学者)
sketch-notes
classroom(课堂)、teaching(教学)、school(学校)、chalkboard(黑板)
chalkboard
architecture(架构)、system(系统)、data(数据)、analysis(分析)、technical(技术)
blueprint
creative(创意)、children(儿童)、kids(孩子)、cute(可爱)
vector-illustration
briefing(简报)、academic(学术)、research(研究)、bilingual(双语)
intuition-machine
executive(高管)、minimal(极简)、clean(简洁)、simple(简单)
minimal
saas、product(产品)、dashboard(仪表盘)、metrics(指标)
notion
investor(投资者)、quarterly(季度)、business(商业)、corporate(企业)
corporate
launch(发布)、marketing(营销)、keynote(主题演讲)、magazine(杂志)
bold-editorial
entertainment(娱乐)、music(音乐)、gaming(游戏)、atmospheric(氛围感)
dark-atmospheric
explainer(讲解)、journalism(新闻)、science communication(科学传播)
editorial-infographic
story(故事)、fantasy(奇幻)、animation(动画)、magical(魔幻)
fantasy-animation
gaming(游戏)、retro(复古)、pixel(像素)、developer(开发者)
pixel-art
biology(生物)、chemistry(化学)、medical(医学)、scientific(科学)
scientific
history(历史)、heritage(遗产)、vintage(复古)、expedition(探险)
vintage
lifestyle(生活方式)、wellness(健康)、travel(旅行)、artistic(艺术)
watercolor
默认
blueprint

Design Philosophy

设计理念

Decks designed for reading and sharing, not live presentation:
  • Each slide self-explanatory without verbal commentary
  • Logical flow when scrolling
  • All necessary context within each slide
  • Optimized for social media sharing
See
references/design-guidelines.md
for:
  • Audience-specific principles
  • Visual hierarchy
  • Content density guidelines
  • Color and typography selection
  • Font recommendations
See
references/layouts.md
for layout options.
幻灯片组专为阅读与分享设计,而非现场演示:
  • 每张幻灯片无需口头讲解即可独立理解
  • 滚动浏览时逻辑连贯
  • 所有必要上下文均包含在单张幻灯片内
  • 优化适配社交媒体分享
查看
references/design-guidelines.md
获取:
  • 受众专属设计原则
  • 视觉层次结构
  • 内容密度指南
  • 色彩与排版选择
  • 字体推荐
查看
references/layouts.md
获取布局选项。

Organic Positioning Principle

自然定位原则

See
references/organic-positioning.md
for full rules. Key principles:
  • Per-slide
    // VISUAL
    paragraphs describe where content IS using natural spatial words
  • Never include a global
    ## CONTENT PLACEMENT
    section in prompts
  • Never mention empty space, reserved zones, or percentages
  • Never tell the image generator what NOT to put somewhere
  • Background spec in
    STYLE_INSTRUCTIONS
    is 1-2 lines max — never add Uniformity sub-sections or per-slide background reminders
  • The less you say about the background, the more consistent it will be
完整规则请查看
references/organic-positioning.md
。核心原则:
  • 单页幻灯片的
    // VISUAL
    段落使用自然空间词汇描述内容的位置
  • 提示词中切勿包含全局
    ## CONTENT PLACEMENT
    章节
  • 切勿提及空白区域、预留区域或百分比
  • 切勿告知图像生成工具某个位置不能放置内容
  • STYLE_INSTRUCTIONS
    中的背景说明最多1-2行——切勿添加Uniformity子章节或每页幻灯片的背景提示
  • 关于背景的描述越少,风格一致性越强

File Management

文件管理

Output Directory

输出目录

slide-deck/{topic-slug}/
├── source-{slug}.{ext}
├── outline.md
├── prompts/
│   └── 01-slide-cover.md, 02-slide-{slug}.md, ...
├── 01-slide-cover.png, 02-slide-{slug}.png, ...
├── {topic-slug}.pptx
└── {topic-slug}.pdf
Slug: Extract topic (2-4 words, kebab-case). Example: "Introduction to Machine Learning" →
intro-machine-learning
Conflict Handling: See Step 1.3 for existing content detection and user options.
slide-deck/{topic-slug}/
├── source-{slug}.{ext}
├── outline.md
├── prompts/
│   └── 01-slide-cover.md, 02-slide-{slug}.md, ...
├── 01-slide-cover.png, 02-slide-{slug}.png, ...
├── {topic-slug}.pptx
└── {topic-slug}.pdf
Slug(主题缩写): 提取主题(2-4个词,短横线分隔)。示例:"Introduction to Machine Learning" →
intro-machine-learning
冲突处理: 现有内容检测与用户选项请查看步骤1.3。

Language Handling

语言处理

Detection Priority:
  1. --lang
    flag (explicit)
  2. EXTEND.md
    language
    setting
  3. User's conversation language (input language)
  4. Source content language
Rule: ALL responses use user's preferred language:
  • Questions and confirmations
  • Progress reports
  • Error messages
  • Completion summaries
Technical terms (style names, file paths, code) remain in English.
检测优先级:
  1. --lang
    参数(显式指定)
  2. EXTEND.md中的
    language
    设置
  3. 用户对话语言(输入语言)
  4. 源内容语言
规则: 所有回复均使用用户偏好语言:
  • 问题与确认信息
  • 进度报告
  • 错误信息
  • 完成总结
技术术语(风格名称、文件路径、代码)保留英文。

Workflow

工作流程

Copy this checklist and check off items as you complete them:
Slide Deck Progress:
- [ ] Step 0: Skill announcement (first run only)
- [ ] Step 1: Setup & Analyze
  - [ ] 1.1 Load preferences
  - [ ] 1.2 Analyze content
  - [ ] 1.3 Check existing
- [ ] Step 2: Confirmation (Round 1 + optional Round 2 + q-presentations questions)
- [ ] Step 3: Generate outline
- [ ] Step 4: Review outline (conditional)
- [ ] Step 5: Generate prompts
- [ ] Step 6: Review prompts (conditional)
- [ ] Step 7: Generate images
- [ ] Step 7.5: Logo overlay
- [ ] Step 8: Merge to PPTX/PDF
- [ ] Step 9: Output summary
复制以下清单并在完成项时勾选:
幻灯片组进度:
- [ ] 步骤0:技能介绍(首次运行时显示)
- [ ] 步骤1:设置与分析
  - [ ] 1.1 加载偏好设置
  - [ ] 1.2 分析内容
  - [ ] 1.3 检查现有内容
- [ ] 步骤2:确认设置(第一轮+可选第二轮+q-presentations专属问题)
- [ ] 步骤3:生成大纲
- [ ] 步骤4:审核大纲(可选)
- [ ] 步骤5:生成提示词
- [ ] 步骤6:审核提示词(可选)
- [ ] 步骤7:生成图片
- [ ] 步骤7.5:添加Logo叠加
- [ ] 步骤8:合并为PPTX/PDF
- [ ] 步骤9:输出总结

Flow

流程顺序

Announce → Input → Preferences → Analyze → [Check Existing?] → Confirm (1-2 rounds + positioning) → Outline → [Review?] → Prompts → [Review?] → Images → Logo → Merge → Complete
介绍 → 输入 → 偏好设置 → 分析 → [检查现有内容?] → 确认(1-2轮+专属问题) → 大纲 → [审核?] → 提示词 → [审核?] → 图片 → Logo → 合并 → 完成

Step 0: Skill Announcement

步骤0:技能介绍

On first invocation, display:
q-presentations — AI-powered slide deck generator Built on the foundation of baoyu-slide-deck by baoyu, extended with organic content positioning, smart logo branding, and video-overlay-aware layout.
Ready to create your next presentation.
首次调用时显示:
q-presentations — AI驱动的幻灯片生成工具 基于baoyu开发的baoyu-slide-deck构建,新增了自然内容定位、智能Logo品牌植入和适配视频叠加的布局功能。
准备好创建您的下一份演示文稿了。

Step 1: Setup & Analyze

步骤1:设置与分析

1.1 Load Preferences (EXTEND.md)
Use Bash to check EXTEND.md existence (priority order):
bash
undefined
1.1 加载偏好设置(EXTEND.md)
使用Bash检查EXTEND.md是否存在(优先级顺序):
bash
undefined

Check project-level first

先检查项目级目录

test -f .q-skills/q-presentations/EXTEND.md && echo "project"
test -f .q-skills/q-presentations/EXTEND.md && echo "project"

Then user-level

再检查用户级目录

test -f "$HOME/.q-skills/q-presentations/EXTEND.md" && echo "user"

| Path | Location |
|------|----------|
| `.q-skills/q-presentations/EXTEND.md` | Project directory |
| `$HOME/.q-skills/q-presentations/EXTEND.md` | User home |

**When EXTEND.md Found** → Read, parse, output summary to user.

**When EXTEND.md Not Found** → First-time setup using AskUserQuestion or proceed with defaults.

Schema: `references/config/preferences-schema.md`

**1.2 Analyze Content**

1. Save source content (if pasted, save as `source.md`)
   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
2. Follow `references/analysis-framework.md` for content analysis
3. Analyze content signals for style recommendations
4. Detect source language
5. Determine recommended slide count
6. Generate topic slug from content

**1.3 Check Existing Content**

Use Bash to check if output directory exists:

```bash
test -d "slide-deck/{topic-slug}" && echo "exists"
If directory exists, use AskUserQuestion with options: Regenerate outline, Regenerate images, Backup and regenerate, Exit.
Save to
analysis.md
with: Topic, audience, content signals, recommended style, recommended slide count, language detection.
test -f "$HOME/.q-skills/q-presentations/EXTEND.md" && echo "user"

| 路径 | 位置 |
|------|----------|
| `.q-skills/q-presentations/EXTEND.md` | 项目目录 |
| `$HOME/.q-skills/q-presentations/EXTEND.md` | 用户主目录 |

**找到EXTEND.md时** → 读取、解析并向用户输出摘要。

**未找到EXTEND.md时** → 首次设置使用AskUserQuestion或使用默认值。

 schema(架构):`references/config/preferences-schema.md`

**1.2 分析内容**

1. 保存源内容(如果是粘贴的内容,保存为`source.md`)
   - **备份规则**: 如果`source.md`已存在,重命名为`source-backup-YYYYMMDD-HHMMSS.md`
2. 按照`references/analysis-framework.md`进行内容分析
3. 分析内容信号以推荐风格
4. 检测源内容语言
5. 确定推荐的幻灯片数量
6. 从内容中生成主题slug

**1.3 检查现有内容**

使用Bash检查输出目录是否存在:

```bash
test -d "slide-deck/{topic-slug}" && echo "exists"
如果目录已存在,使用AskUserQuestion提供选项:重新生成大纲、重新生成图片、备份并重新生成、退出。
保存到
analysis.md
:包含主题、受众、内容信号、推荐风格、推荐幻灯片数量、语言检测结果。

Step 2: Confirmation

步骤2:确认设置

Three parts: Round 1 (always), Round 2 (if custom), q-presentations questions (always).
Language: Use user's input language or saved language preference.
三部分:第一轮(必选)、第二轮(自定义时可选)、q-presentations专属问题(必选)。
语言: 使用用户输入语言或保存的语言偏好。

Round 1 (Always) — same as baoyu

第一轮(必选)——与baoyu相同

Use AskUserQuestion for all 5 questions:
  1. Style: Recommended preset vs alternatives vs custom dimensions
  2. Audience: General / Beginners / Experts / Executives
  3. Slide Count: Recommended vs fewer vs more
  4. Review Outline: Yes (recommended) / No
  5. Review Prompts: Yes (recommended) / No
使用AskUserQuestion提出以下5个问题:
  1. 风格: 推荐预设风格 vs 其他选项 vs 自定义维度
  2. 受众: 普通用户 / 初学者 / 专家 / 高管
  3. 幻灯片数量: 推荐数量 vs 更少 vs 更多
  4. 审核大纲: 是(推荐) / 否
  5. 审核提示词: 是(推荐) / 否

Round 2 (Only if "Custom dimensions" selected)

第二轮(仅当选择“自定义维度”时)

Use AskUserQuestion for 4 dimensions: Texture, Mood, Typography, Density.
使用AskUserQuestion询问4个维度:Texture(质感)、Mood(氛围)、Typography(排版)、Density(密度)。

q-presentations Questions (Always)

q-presentations专属问题(必选)

Question: Video Overlay Side
header: "Video"
question: "Where will the video overlay appear in post-production?"
options:
  - label: "Right side (Recommended)"
    description: "Content anchors left/center-left"
  - label: "Left side"
    description: "Content anchors center-right/right"
  - label: "Bottom"
    description: "Content anchors upper area"
  - label: "None"
    description: "Content centered freely, no video overlay"
Question: Logo Placement
header: "Logo"
question: "Logo placement?"
options:
  - label: "Top-right (Recommended)"
    description: "Dr. Q logo at top-right corner"
  - label: "Bottom-right"
    description: "Dr. Q logo at bottom-right corner"
  - label: "None"
    description: "No logo overlay"
Derive content anchor direction from video overlay answer:
Video Overlay SideContent Anchor Direction
RightLeft (upper-left, center-left, bottom-left)
LeftRight (upper-right, center-right, bottom-right)
BottomTop (upper area, top-center)
NoneCenter (freely positioned)
After Confirmation: Store all preferences including
video_overlay_side
,
content_anchor
,
logo_position
.
问题:视频叠加侧边
header: "视频设置"
question: "后期制作中视频叠加将出现在哪个侧边?"
options:
  - label: "右侧(推荐)"
    description: "内容锚定在左侧/中左侧"
  - label: "左侧"
    description: "内容锚定在中右侧/右侧"
  - label: "底部"
    description: "内容锚定在上部区域"
  - label: "无"
    description: "内容自由居中,无视频叠加"
问题:Logo位置
header: "Logo设置"
question: "Logo位置?"
options:
  - label: "右上角(推荐)"
    description: "Dr. Q Logo位于右上角"
  - label: "右下角"
    description: "Dr. Q Logo位于右下角"
  - label: "无"
    description: "无Logo叠加"
根据视频叠加答案推导内容锚定方向:
视频叠加侧边内容锚定方向
右侧左侧(左上、中左、左下)
左侧右侧(右上、中右、右下)
底部顶部(上部区域、顶部居中)
居中(自由定位)
确认后: 保存所有偏好设置,包括
video_overlay_side
content_anchor
logo_position

Step 3: Generate Outline

步骤3:生成大纲

Create outline using the confirmed style from Step 2.
Style Resolution:
  • If preset selected → Read
    references/styles/{preset}.md
  • If custom dimensions → Read dimension files from
    references/dimensions/
    and combine
Generate:
  1. Follow
    references/outline-template.md
    for structure
  2. Build STYLE_INSTRUCTIONS from style or dimensions
  3. Apply confirmed audience, language, slide count
  4. CRITICAL — Organic Positioning (see
    references/organic-positioning.md
    ):
    • Background in STYLE_INSTRUCTIONS: ONE concise line (Color + Texture). Use "flat" and "edge to edge" for uniformity. No Uniformity sub-section.
    • Per-slide
      // VISUAL
      paragraphs: Describe where content IS using natural spatial words based on the content anchor direction. Never mention empty space, reserved zones, or percentages.
  5. Add metadata to outline header:
    **Content Anchor**: [left/right/top/center]
    **Video Overlay**: [right/left/bottom/none]
    **Logo**: [top-right/bottom-right/none]
  6. Save as
    outline.md
After generation:
  • If
    --outline-only
    , stop here
  • If
    skip_outline_review
    is true → Skip Step 4, go to Step 5
  • Otherwise → Continue to Step 4
使用步骤2中确认的风格创建大纲。
风格解析:
  • 如果选择预设风格 → 读取
    references/styles/{preset}.md
  • 如果选择自定义维度 → 读取
    references/dimensions/
    中的维度文件并组合
生成步骤:
  1. 按照
    references/outline-template.md
    的结构创建
  2. 根据风格或维度构建STYLE_INSTRUCTIONS
  3. 应用已确认的受众、语言、幻灯片数量
  4. 关键——自然定位(查看
    references/organic-positioning.md
    ):
    • STYLE_INSTRUCTIONS中的背景说明:仅1行简洁描述(颜色+质感)。使用“flat(纯色)”和“edge to edge(全屏)”保证一致性。不要添加Uniformity子章节。
    • 每页幻灯片的
      // VISUAL
      段落:根据内容锚定方向,使用自然空间词汇描述内容的位置。切勿提及空白区域、预留区域或百分比。
  5. 向大纲头部添加元数据:
    **内容锚定方向**: [left/right/top/center]
    **视频叠加**: [right/left/bottom/none]
    **Logo**: [top-right/bottom-right/none]
  6. 保存为
    outline.md
生成后:
  • 如果使用
    --outline-only
    ,在此处停止
  • 如果
    skip_outline_review
    为true → 跳过步骤4,直接进入步骤5
  • 否则 → 继续步骤4

Step 4: Review Outline (Conditional)

步骤4:审核大纲(可选)

Skip if user selected "No, skip outline review" in Step 2.
Display slide-by-slide summary table. Use AskUserQuestion: Proceed / Edit outline / Regenerate.
如果用户在步骤2中选择“否,跳过大纲审核”则跳过此步骤。
显示逐页幻灯片摘要表格。使用AskUserQuestion提供选项:继续 / 编辑大纲 / 重新生成。

Step 5: Generate Prompts

步骤5:生成提示词

  1. Read
    references/base-prompt.md
  2. For each slide in outline:
    • Extract STYLE_INSTRUCTIONS from outline (not from style file again)
    • Add slide-specific content
    • If
      Layout:
      specified, include layout guidance from
      references/layouts.md
    • CRITICAL — Organic Positioning: Copy Background line from STYLE_INSTRUCTIONS exactly (1-2 lines). Do NOT expand into verbose uniformity paragraphs. Do NOT add per-slide "Background must be..." sentences. Do NOT add lists of what to avoid.
  3. Save to
    prompts/
    directory
    • Backup rule: If prompt file exists, rename to backup
After generation:
  • If
    --prompts-only
    , stop here
  • If
    skip_prompt_review
    is true → Skip Step 6, go to Step 7
  • Otherwise → Continue to Step 6
  1. 读取
    references/base-prompt.md
  2. 针对大纲中的每张幻灯片:
    • 从大纲中提取STYLE_INSTRUCTIONS(不再从风格文件读取)
    • 添加幻灯片专属内容
    • 如果指定了
      Layout:
      ,从
      references/layouts.md
      中添加布局指导
    • 关键——自然定位:直接复制STYLE_INSTRUCTIONS中的背景行(1-2行)。不要扩展为冗长的一致性描述段落。不要添加每页幻灯片的“背景必须...”语句。不要添加禁止内容的列表。
  3. 保存到
    prompts/
    目录
    • 备份规则: 如果提示词文件已存在,重命名为备份文件
生成后:
  • 如果使用
    --prompts-only
    ,在此处停止
  • 如果
    skip_prompt_review
    为true → 跳过步骤6,直接进入步骤7
  • 否则 → 继续步骤6

Step 6: Review Prompts (Conditional)

步骤6:审核提示词(可选)

Skip if user selected "No, skip prompt review" in Step 2.
Display prompt list. Use AskUserQuestion: Proceed / Edit prompts / Regenerate.
如果用户在步骤2中选择“否,跳过提示词审核”则跳过此步骤。
显示提示词列表。使用AskUserQuestion提供选项:继续 / 编辑提示词 / 重新生成。

Step 7: Generate Images

步骤7:生成图片

For
--images-only
: Start here with existing prompts.
For
--regenerate N
: Only regenerate specified slide(s).
Standard flow:
  1. For each slide:
    • Backup rule: If image file exists, rename to backup
    • Generate image using Python script:
      bash
      python ${SKILL_DIR}/scripts/gen_slide.py <prompt-file> <output-png>
    • Report progress: "Generated X/N" (in user's language)
  2. Auto-retry once on failure before reporting error
  3. Generate sequentially
使用
--images-only
: 从此步骤开始,使用现有提示词。
使用
--regenerate N
: 仅重新生成指定幻灯片。
标准流程:
  1. 针对每张幻灯片:
    • 备份规则: 如果图片文件已存在,重命名为备份文件
    • 使用Python脚本生成图片:
      bash
      python ${SKILL_DIR}/scripts/gen_slide.py <prompt-file> <output-png>
    • 报告进度:“已生成X/N张”(使用用户语言)
  2. 生成失败时自动重试一次,然后报告错误
  3. 按顺序生成

Step 7.5: Logo Overlay

步骤7.5:添加Logo叠加

After all images are generated, apply logo:
bash
python ${SKILL_DIR}/scripts/overlay_logo.py <slide-deck-dir> --position <logo-position> --style <style-name>
  • Position comes from Step 2 logo placement answer
  • --style
    flag enables auto-invert for dark background styles (technical, storytelling, chalkboard, dark-atmospheric, etc.)
  • If logo placement is "none", add
    --skip
    flag
所有图片生成完成后,添加Logo:
bash
python ${SKILL_DIR}/scripts/overlay_logo.py <slide-deck-dir> --position <logo-position> --style <style-name>
  • 位置来自步骤2中Logo位置的答案
  • --style
    参数可针对深色背景风格(technical、storytelling、chalkboard、dark-atmospheric等)自动反转Logo颜色
  • 如果Logo位置为“none”,添加
    --skip
    参数

Step 8: Merge to PPTX and PDF

步骤8:合并为PPTX和PDF

Option A — Python (PPTX only):
bash
python ${SKILL_DIR}/scripts/merge_slides.py <slide-deck-dir>
Option B — Bun/TypeScript (PPTX + PDF):
bash
npx -y bun ${SKILL_DIR}/scripts/merge-to-pptx.ts <slide-deck-dir>
npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts <slide-deck-dir>
选项A — Python(仅生成PPTX):
bash
python ${SKILL_DIR}/scripts/merge_slides.py <slide-deck-dir>
选项B — Bun/TypeScript(生成PPTX+PDF):
bash
npx -y bun ${SKILL_DIR}/scripts/merge-to-pptx.ts <slide-deck-dir>
npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts <slide-deck-dir>

Step 9: Output Summary

步骤9:输出总结

Slide Deck Complete!

Topic: [topic]
Style: [preset name or custom dimensions]
Content Anchor: [direction]
Video Overlay Zone: [side]
Logo: [position]
Location: [directory path]
Slides: N total

- 01-slide-cover.png - Cover
- 02-slide-intro.png - Content
- ...
- {NN}-slide-back-cover.png - Back Cover

Outline: outline.md
PPTX: {topic-slug}.pptx
PDF: {topic-slug}.pdf
幻灯片组已完成!

主题: [主题]
风格: [预设名称或自定义维度]
内容锚定方向: [方向]
视频叠加区域: [侧边]
Logo: [位置]
存储位置: [目录路径]
幻灯片总数: N张

- 01-slide-cover.png - 封面
- 02-slide-intro.png - 内容页
- ...
- {NN}-slide-back-cover.png - 封底

大纲: outline.md
PPTX: {topic-slug}.pptx
PDF: {topic-slug}.pdf

Partial Workflows

部分工作流程

OptionWorkflow
--outline-only
Steps 1-3 only (stop after outline)
--prompts-only
Steps 1-5 (generate prompts, skip images)
--images-only
Skip to Step 7 (requires existing prompts/)
--regenerate N
Regenerate specific slide(s) only
选项工作流程
--outline-only
仅步骤1-3(生成大纲后停止)
--prompts-only
步骤1-5(生成提示词,跳过图片)
--images-only
直接进入步骤7(需要现有提示词目录)
--regenerate N
仅重新生成指定幻灯片

Slide Modification

幻灯片修改

Quick Reference

快速参考

ActionCommandManual Steps
Edit
--regenerate N
Update prompt file FIRST → Regenerate image → Regenerate PDF
AddManualCreate prompt → Generate image → Renumber subsequent → Update outline → Regenerate PDF
DeleteManualRemove files → Renumber subsequent → Update outline → Regenerate PDF
See
references/modification-guide.md
for complete details.
操作命令手动步骤
编辑
--regenerate N
先更新提示词文件 → 重新生成图片 → 重新生成PDF
添加手动创建提示词 → 生成图片 → 重命名后续幻灯片 → 更新大纲 → 重新生成PDF
删除手动删除文件 → 重命名后续幻灯片 → 更新大纲 → 重新生成PDF
完整详情请查看
references/modification-guide.md

File Naming

文件命名规则

Format:
NN-slide-[slug].png
  • NN
    : Two-digit sequence (01, 02, ...)
  • slug
    : Kebab-case from content (2-5 words, unique)
格式:
NN-slide-[slug].png
  • NN
    : 两位数字序号(01、02...)
  • slug
    : 从内容中提取的短横线分隔名称(2-5个词,唯一)

References

参考文档

FileContent
references/analysis-framework.md
Content analysis for presentations
references/outline-template.md
Outline structure and format
references/organic-positioning.md
Organic content positioning and background rules
references/modification-guide.md
Edit, add, delete slide workflows
references/content-rules.md
Content and style guidelines
references/design-guidelines.md
Audience, typography, colors, visual elements
references/layouts.md
Layout options and selection tips
references/base-prompt.md
Base prompt for image generation
references/dimensions/*.md
Dimension specifications (texture, mood, typography, density)
references/dimensions/presets.md
Preset → dimension mapping
references/styles/<style>.md
Full style specifications
references/config/preferences-schema.md
EXTEND.md structure
文件内容
references/analysis-framework.md
演示文稿内容分析框架
references/outline-template.md
大纲结构与格式
references/organic-positioning.md
自然内容定位与背景规则
references/modification-guide.md
编辑、添加、删除幻灯片的工作流程
references/content-rules.md
内容与风格指南
references/design-guidelines.md
受众、排版、色彩、视觉元素指南
references/layouts.md
布局选项与选择技巧
references/base-prompt.md
图片生成基础提示词
references/dimensions/*.md
维度规格(质感、氛围、排版、密度)
references/dimensions/presets.md
预设风格与维度的映射关系
references/styles/<style>.md
完整风格规格
references/config/preferences-schema.md
EXTEND.md结构

Notes

注意事项

  • Image generation: 10-30 seconds per slide
  • Auto-retry once on generation failure
  • Use stylized alternatives for sensitive public figures
  • Maintain style consistency across all slides
  • Step 2 confirmation required — do not skip
  • Never include photorealistic images of prominent individuals
  • Never include placeholder slides for author name, date, etc.
  • 图片生成:每张幻灯片10-30秒
  • 生成失败时自动重试一次,然后报告错误
  • 对敏感公众人物使用风格化替代图像
  • 保持所有幻灯片风格一致
  • 必须完成步骤2的确认——不可跳过
  • 切勿使用知名人物的写实图像
  • 切勿添加作者姓名、日期等占位符幻灯片

Extension Support

扩展支持

Custom configurations via EXTEND.md. See Step 1.1 for paths and supported options.
通过EXTEND.md进行自定义配置。路径与支持选项请查看步骤1.1