ppt-template-creator
把使用者的 PPT 範本做成可重複使用的範本 skill
中文翻譯
---
name: ppt-template-creator
description: 從使用者提供的 PowerPoint 範本建立自給自足的 PPT 範本 SKILL（不是簡報）。只有在使用者想把自己的範本做成可重複使用的 skill 時才用。要建立實際的簡報，請改用 pptx skill。
---
# PPT 範本建立器
**這個 skill 建立的是 SKILL，不是簡報。** 當使用者想把自己的 PowerPoint 範本變成之後可以重複產生簡報的 skill 時，才用這個。如果使用者只是要做一份簡報，請改用 `pptx` skill。
產生出來的 skill 包含：
- `assets/template.pptx`：範本檔
- `SKILL.md`：完整的使用說明（不需要再參照這個 meta skill）
**關於建立 skill 的一般最佳實務**，請參考 `skill-creator` skill。這個 skill 只專注在 PPT 專屬的做法。
## 工作流程
1. **使用者提供範本**（.pptx 或 .potx）
2. **分析範本**：萃取版面配置、佔位符、尺寸
3. **初始化 skill**：用 `skill-creator` skill 建立 skill 的結構
4. **加入範本**：把 .pptx 複製到 `assets/template.pptx`
5. **撰寫 SKILL.md**：照下面的範本，填入 PPT 專屬的細節
6. **建立範例**：產生一份範例簡報來驗證
7. **打包**：用 `skill-creator` skill 打包成 .skill 檔
## 步驟 2：分析範本
**關鍵：要萃取精確的佔位符位置**，這決定了內容區域的邊界。
```python
from pptx import Presentation
prs = Presentation(template_path)
print(f"Dimensions: {prs.slide_width/914400:.2f}\" x {prs.slide_height/914400:.2f}\"")
print(f"Layouts: {len(prs.slide_layouts)}")
for idx, layout in enumerate(prs.slide_layouts):
print(f"\n[{idx}] {layout.name}:")
for ph in layout.placeholders:
try:
ph_idx = ph.placeholder_format.idx
ph_type = ph.placeholder_format.type
# 重要：以英吋為單位萃取精確位置
left = ph.left / 914400
top = ph.top / 914400
width = ph.width / 914400
height = ph.height / 914400
print(f" idx={ph_idx}, type={ph_type}")
print(f" x={left:.2f}\", y={top:.2f}\", w={width:.2f}\", h={height:.2f}\"")
except:
pass
```
**要記錄的關鍵尺寸：**
- **標題位置**：標題佔位符在哪裡？
- **副標題／說明**：副標題那一行在哪裡？
- **頁尾佔位符**：頁尾／來源出現在哪裡？
- **內容區域**：副標題和頁尾「之間」的空間就是你的內容區域
### 找出內容真正的起始位置
**關鍵：** 內容區域不一定緊接在副標題佔位符之後開始。很多範本在副標題和內容區域之間有視覺邊框、線條或保留空間。
**最佳做法：** 找 Layout 2 或類似、有 OBJECT 佔位符的「內容」版面配置，這個佔位符的 `y` 位置就是內容實際該開始的地方。
```python
# 找出 OBJECT 佔位符，以決定內容真正的起始位置
for idx, layout in enumerate(prs.slide_layouts):
for ph in layout.placeholders:
try:
if ph.placeholder_format.type == 7: # OBJECT type
top = ph.top / 914400
print(f"Layout [{idx}] {layout.name}: OBJECT starts at y={top:.2f}\"")
# 這個 y 值就是你的內容該開始的位置！
except:
pass
```
**範例：** 某個範本可能是：
- 副標題結束在 y=1.38"
- 但 OBJECT 佔位符從 y=1.90" 開始
- 中間的空隙（0.52"）是保留給邊框／線條用的，**不要把內容放進去**
內容起始位置要用 OBJECT 佔位符的 `y`，不要用副標題的結束位置。
## 步驟 5：撰寫 SKILL.md
產生出來的 skill 應該有這個結構：
```
[company]-ppt-template/
├── SKILL.md
└── assets/
└── template.pptx
```
### 產生的 SKILL.md 範本
產生的 SKILL.md 必須**自給自足**，所有說明都內嵌在裡面。使用下面這個範本，把方括號的值用你分析的結果填進去：
````markdown
---
name: [company]-ppt-template
description: [Company] PowerPoint template for creating presentations. Use when creating [Company]-branded pitch decks, board materials, or client presentations.
---
# [Company] PPT Template
Template: `assets/template.pptx` ([WIDTH]" x [HEIGHT]", [N] layouts)
## Creating Presentations
```python
from pptx import Presentation
prs = Presentation("path/to/skill/assets/template.pptx")
# DELETE all existing slides first
while len(prs.slides) > 0:
rId = prs.slides._sldIdLst[0].rId
prs.part.drop_rel(rId)
del prs.slides._sldIdLst[0]
# Add slides from layouts
slide = prs.slides.add_slide(prs.slide_layouts[LAYOUT_IDX])
```
## Key Layouts
| Index | Name | Use For |
|-------|------|---------|
| [0] | [Layout Name] | [Cover/title slide] |
| [N] | [Layout Name] | [Content with bullets] |
| [N] | [Layout Name] | [Two-column layout] |
## Placeholder Mapping
**CRITICAL: Include exact positions (x, y coordinates) for each placeholder.**
### Layout [N]: [Name]
| idx | Type | Position | Use |
|-----|------|----------|-----|
| [idx] | TITLE (1) | y=[Y]" | Slide title |
| [idx] | BODY (2) | y=[Y]" | Subtitle/description |
| [idx] | BODY (2) | y=[Y]" | Footer |
| [idx] | BODY (2) | y=[Y]" | Source/notes |
### Content Area Boundaries
**Document the safe content area for custom shapes/tables/charts:**
```
Content Area (for Layout [N]):
- Left margin: [X]" (content starts here)
- Top: [Y]" (below subtitle placeholder)
- Width: [W]"
- Height: [H]" (ends before footer)
For 4-quadrant layouts:
- Left column: x=[X]", width=[W]"
- Right column: x=[X]", width=[W]"
- Top row: y=[Y]", height=[H]"
- Bottom row: y=[Y]", height=[H]"
```
**Why this matters:** Custom content (textboxes, tables, charts) must stay within these boundaries to avoid overlapping with template placeholders like titles, footers, and source lines.
## Filling Content
**Do NOT add manual bullet characters** - slide master handles formatting.
```python
# Fill title
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
if shape.placeholder_format.type == 1: # TITLE
shape.text = "Slide Title"
# Fill content with hierarchy (level 0 = header, level 1 = bullet)
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
idx = shape.placeholder_format.idx
if idx == [CONTENT_IDX]:
tf = shape.text_frame
for para in tf.paragraphs:
para.clear()
content = [
("Section Header", 0),
("First bullet point", 1),
("Second bullet point", 1),
]
tf.paragraphs[0].text = content[0][0]
tf.paragraphs[0].level = content[0][1]
for text, level in content[1:]:
p = tf.add_paragraph()
p.text = text
p.level = level
```
## Example: Cover Slide
```python
slide = prs.slides.add_slide(prs.slide_layouts[[COVER_IDX]])
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
idx = shape.placeholder_format.idx
if idx == [TITLE_IDX]:
shape.text = "Company Name"
elif idx == [SUBTITLE_IDX]:
shape.text = "Presentation Title | Date"
```
## Example: Content Slide
```python
slide = prs.slides.add_slide(prs.slide_layouts[[CONTENT_IDX]])
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
ph_type = shape.placeholder_format.type
idx = shape.placeholder_format.idx
if ph_type == 1:
shape.text = "Executive Summary"
elif idx == [BODY_IDX]:
tf = shape.text_frame
for para in tf.paragraphs:
para.clear()
content = [
("Key Findings", 0),
("Revenue grew 40% YoY to $50M", 1),
("Expanded to 3 new markets", 1),
("Recommendation", 0),
("Proceed with strategic initiative", 1),
]
tf.paragraphs[0].text = content[0][0]
tf.paragraphs[0].level = content[0][1]
for text, level in content[1:]:
p = tf.add_paragraph()
p.text = text
p.level = level
```
````
## 步驟 6：建立範例輸出
產生一份範例簡報來驗證這個 skill 能用。把它跟 skill 放在一起，當作參考。
## 產生的 skill 要遵守的 PPT 專屬規則
1. **範本放在 assets/**：一定要把 .pptx 檔一起打包
2. **SKILL.md 自給自足**：所有說明都內嵌，不參照外部檔案
3. **不要手動加項目符號**：用 `paragraph.level` 表示階層
4. **先刪投影片**：加新投影片之前，一定要先清掉現有的投影片
5. **用 idx 記錄佔位符**：佔位符的 idx 值是各範本專屬的英文原文
---
name: ppt-template-creator
description: Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.
---
# PPT Template Creator
**This skill creates SKILLS, not presentations.** Use this when a user wants to turn their PowerPoint template into a reusable skill that can generate presentations later. If the user just wants to create a presentation, use the `pptx` skill instead.
The generated skill includes:
- `assets/template.pptx` - the template file
- `SKILL.md` - complete instructions (no reference to this meta skill needed)
**For general skill-building best practices**, refer to the `skill-creator` skill. This skill focuses on PPT-specific patterns.
## Workflow
1. **User provides template** (.pptx or .potx)
2. **Analyze template** - extract layouts, placeholders, dimensions
3. **Initialize skill** - use the `skill-creator` skill to set up the skill structure
4. **Add template** - copy .pptx to `assets/template.pptx`
5. **Write SKILL.md** - follow template below with PPT-specific details
6. **Create example** - generate sample presentation to validate
7. **Package** - use the `skill-creator` skill to package into a .skill file
## Step 2: Analyze Template
**CRITICAL: Extract precise placeholder positions** - this determines content area boundaries.
```python
from pptx import Presentation
prs = Presentation(template_path)
print(f"Dimensions: {prs.slide_width/914400:.2f}\" x {prs.slide_height/914400:.2f}\"")
print(f"Layouts: {len(prs.slide_layouts)}")
for idx, layout in enumerate(prs.slide_layouts):
print(f"\n[{idx}] {layout.name}:")
for ph in layout.placeholders:
try:
ph_idx = ph.placeholder_format.idx
ph_type = ph.placeholder_format.type
# IMPORTANT: Extract exact positions in inches
left = ph.left / 914400
top = ph.top / 914400
width = ph.width / 914400
height = ph.height / 914400
print(f" idx={ph_idx}, type={ph_type}")
print(f" x={left:.2f}\", y={top:.2f}\", w={width:.2f}\", h={height:.2f}\"")
except:
pass
```
**Key measurements to document:**
- **Title position**: Where does the title placeholder sit?
- **Subtitle/description**: Where is the subtitle line?
- **Footer placeholders**: Where do footers/sources appear?
- **Content area**: The space BETWEEN subtitle and footer is your content area
### Finding the True Content Start Position
**CRITICAL:** The content area does NOT always start immediately after the subtitle placeholder. Many templates have a visual border, line, or reserved space between the subtitle and content area.
**Best approach:** Look at Layout 2 or similar "content" layouts that have an OBJECT placeholder - this placeholder's `y` position indicates where content should actually start.
```python
# Find the OBJECT placeholder to determine true content start
for idx, layout in enumerate(prs.slide_layouts):
for ph in layout.placeholders:
try:
if ph.placeholder_format.type == 7: # OBJECT type
top = ph.top / 914400
print(f"Layout [{idx}] {layout.name}: OBJECT starts at y={top:.2f}\"")
# This y value is where your content should start!
except:
pass
```
**Example:** A template might have:
- Subtitle ending at y=1.38"
- But OBJECT placeholder starting at y=1.90"
- The gap (0.52") is reserved for a border/line - **do not place content there**
Use the OBJECT placeholder's `y` position as your content start, not the subtitle's end position.
## Step 5: Write SKILL.md
The generated skill should have this structure:
```
[company]-ppt-template/
├── SKILL.md
└── assets/
└── template.pptx
```
### Generated SKILL.md Template
The generated SKILL.md must be **self-contained** with all instructions embedded. Use this template, filling in the bracketed values from your analysis:
````markdown
---
name: [company]-ppt-template
description: [Company] PowerPoint template for creating presentations. Use when creating [Company]-branded pitch decks, board materials, or client presentations.
---
# [Company] PPT Template
Template: `assets/template.pptx` ([WIDTH]" x [HEIGHT]", [N] layouts)
## Creating Presentations
```python
from pptx import Presentation
prs = Presentation("path/to/skill/assets/template.pptx")
# DELETE all existing slides first
while len(prs.slides) > 0:
rId = prs.slides._sldIdLst[0].rId
prs.part.drop_rel(rId)
del prs.slides._sldIdLst[0]
# Add slides from layouts
slide = prs.slides.add_slide(prs.slide_layouts[LAYOUT_IDX])
```
## Key Layouts
| Index | Name | Use For |
|-------|------|---------|
| [0] | [Layout Name] | [Cover/title slide] |
| [N] | [Layout Name] | [Content with bullets] |
| [N] | [Layout Name] | [Two-column layout] |
## Placeholder Mapping
**CRITICAL: Include exact positions (x, y coordinates) for each placeholder.**
### Layout [N]: [Name]
| idx | Type | Position | Use |
|-----|------|----------|-----|
| [idx] | TITLE (1) | y=[Y]" | Slide title |
| [idx] | BODY (2) | y=[Y]" | Subtitle/description |
| [idx] | BODY (2) | y=[Y]" | Footer |
| [idx] | BODY (2) | y=[Y]" | Source/notes |
### Content Area Boundaries
**Document the safe content area for custom shapes/tables/charts:**
```
Content Area (for Layout [N]):
- Left margin: [X]" (content starts here)
- Top: [Y]" (below subtitle placeholder)
- Width: [W]"
- Height: [H]" (ends before footer)
For 4-quadrant layouts:
- Left column: x=[X]", width=[W]"
- Right column: x=[X]", width=[W]"
- Top row: y=[Y]", height=[H]"
- Bottom row: y=[Y]", height=[H]"
```
**Why this matters:** Custom content (textboxes, tables, charts) must stay within these boundaries to avoid overlapping with template placeholders like titles, footers, and source lines.
## Filling Content
**Do NOT add manual bullet characters** - slide master handles formatting.
```python
# Fill title
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
if shape.placeholder_format.type == 1: # TITLE
shape.text = "Slide Title"
# Fill content with hierarchy (level 0 = header, level 1 = bullet)
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
idx = shape.placeholder_format.idx
if idx == [CONTENT_IDX]:
tf = shape.text_frame
for para in tf.paragraphs:
para.clear()
content = [
("Section Header", 0),
("First bullet point", 1),
("Second bullet point", 1),
]
tf.paragraphs[0].text = content[0][0]
tf.paragraphs[0].level = content[0][1]
for text, level in content[1:]:
p = tf.add_paragraph()
p.text = text
p.level = level
```
## Example: Cover Slide
```python
slide = prs.slides.add_slide(prs.slide_layouts[[COVER_IDX]])
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
idx = shape.placeholder_format.idx
if idx == [TITLE_IDX]:
shape.text = "Company Name"
elif idx == [SUBTITLE_IDX]:
shape.text = "Presentation Title | Date"
```
## Example: Content Slide
```python
slide = prs.slides.add_slide(prs.slide_layouts[[CONTENT_IDX]])
for shape in slide.shapes:
if hasattr(shape, 'placeholder_format'):
ph_type = shape.placeholder_format.type
idx = shape.placeholder_format.idx
if ph_type == 1:
shape.text = "Executive Summary"
elif idx == [BODY_IDX]:
tf = shape.text_frame
for para in tf.paragraphs:
para.clear()
content = [
("Key Findings", 0),
("Revenue grew 40% YoY to $50M", 1),
("Expanded to 3 new markets", 1),
("Recommendation", 0),
("Proceed with strategic initiative", 1),
]
tf.paragraphs[0].text = content[0][0]
tf.paragraphs[0].level = content[0][1]
for text, level in content[1:]:
p = tf.add_paragraph()
p.text = text
p.level = level
```
````
## Step 6: Create Example Output
Generate a sample presentation to validate the skill works. Save it alongside the skill for reference.
## PPT-Specific Rules for Generated Skills
1. **Template in assets/** - always bundle the .pptx file
2. **Self-contained SKILL.md** - all instructions embedded, no external references
3. **No manual bullets** - use `paragraph.level` for hierarchy
4. **Delete slides first** - always clear existing slides before adding new ones
5. **Document placeholders by idx** - placeholder idx values are template-specific