Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

storyboard-to-slides故事板到幻灯片

Agent Skill

storyboard-to-slides 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

544

周安装

22

GitHub Stars

1,117

下载量

171
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:storyboard-to-slides(故事板到幻灯片)
来源仓库:https://github.com/moosegoose0701/skill-compose
仓库路径:skills/storyboard-to-slides
安装命令:
npx skills add https://github.com/moosegoose0701/skill-compose --skill storyboard-to-slides
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/moosegoose0701/skill-compose --skill storyboard-to-slides

简介

storyboard-to-slides 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 适用于快速信息收集和筛选的场景,如研究、调研或内容创作。
  • 通过关键词匹配和来源分析,帮助 Agent 高效定位相关内容。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 可结合来源仓库和原始 README 继续核验具体用法和实现细节。

SKILL.md

Storyboard to Slides

Assemble a polished PPTX from a storyboard CSV + image files using python-pptx.

Dependencies

# pip install python-pptx Pillow

Input Format

Expects storyboard.csv with columns: slide_no, slide_type, title, bullet_points, image_prompt, speaker_notes, layout

And image files named slide_{no}.png for each row.

Workflow

1. Read the Storyboard

import csv

with open("storyboard.csv", "r", encoding="utf-8") as f:
    reader = csv.DictReader(f)
    slides = list(reader)

2. Initialize the Presentation

from pptx import Presentation
from pptx.util import Inches, Pt, Emu
from pptx.dml.color import RGBColor

prs = Presentation()
prs.slide_width = Inches(13.333)   # 16:9
prs.slide_height = Inches(7.5)

For 4:3 slides: Inches(10) x Inches(7.5).

3. Define Theme Constants

# Customize per project
THEME = {
    "bg_color": RGBColor(0x1A, 0x1A, 0x2E),     # dark navy
    "title_color": RGBColor(0xFF, 0xFF, 0xFF),
    "text_color": RGBColor(0xE0, 0xE0, 0xE0),
    "accent_color": RGBColor(0x64, 0xB5, 0xF6),
    "title_font": "Arial",
    "body_font": "Arial",
    "title_size": Pt(36),
    "body_size": Pt(18),
}

Choose colors that contrast well with the generated images. For light images use dark text overlay with semi-transparent background; for dark images use white text.

4. Layout Implementations

full_bg — Full-screen background image + overlay text

from pptx.util import Inches, Pt, Emu
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN, MSO_ANCHOR

def add_full_bg_slide(prs, img_path, title, subtitle="", theme=THEME):
    slide = prs.slides.add_slide(prs.slide_layouts[6])  # blank
    # Background image
    slide.shapes.add_picture(img_path, 0, 0, prs.slide_width, prs.slide_height)
    # Semi-transparent overlay
    overlay = slide.shapes.add_shape(
        1, 0, 0, prs.slide_width, prs.slide_height  # MSO_SHAPE.RECTANGLE = 1
    )
    overlay.fill.solid()
    overlay.fill.fore_color.rgb = RGBColor(0, 0, 0)
    overlay.shadow.inherit = False
    overlay.line.fill.background()
    # Set overlay transparency via XML (access the shape's XML element, not the fill object)
    from pptx.oxml.ns import qn
    solid = overlay._element.find(f'.//{qn("a:solidFill")}')
    if solid is not None:
        srgb = solid.find(qn("a:srgbClr"))
        if srgb is not None:
            alpha = srgb.makeelement(qn("a:alpha"), {"val": "40000"})  # 40% opacity
            srgb.append(alpha)
    # Title
    txBox = slide.shapes.add_textbox(Inches(1), Inches(2.5), Inches(11), Inches(2))
    tf = txBox.text_frame
    tf.word_wrap = True
    p = tf.paragraphs[0]
    p.text = title
    p.font.size = Pt(44)
    p.font.bold = True
    p.font.color.rgb = theme["title_color"]
    p.alignment = PP_ALIGN.CENTER
    if subtitle:
        p2 = tf.add_paragraph()
        p2.text = subtitle
        p2.font.size = Pt(24)
        p2.font.color.rgb = theme["text_color"]
        p2.alignment = PP_ALIGN.CENTER
    return slide

left_img_right_text — Image left, text right

def add_left_img_right_text(prs, img_path, title, bullets, theme=THEME):
    slide = prs.slides.add_slide(prs.slide_layouts[6])
    # Solid background
    bg = slide.background
    fill = bg.fill
    fill.solid()
    fill.fore_color.rgb = theme["bg_color"]
    # Image on left (half width)
    slide.shapes.add_picture(img_path, 0, 0, Inches(6.5), prs.slide_height)
    # Title
    txBox = slide.shapes.add_textbox(Inches(7), Inches(0.5), Inches(5.8), Inches(1.2))
    tf = txBox.text_frame
    tf.word_wrap = True
    p = tf.paragraphs[0]
    p.text = title
    p.font.size = theme["title_size"]
    p.font.bold = True
    p.font.color.rgb = theme["title_color"]
    # Bullets
    txBox2 = slide.shapes.add_textbox(Inches(7), Inches(2), Inches(5.8), Inches(4.5))
    tf2 = txBox2.text_frame
    tf2.word_wrap = True
    for i, line in enumerate(bullets.split("\n")):
        line = line.strip().lstrip("•-").strip()
        if not line:
            continue
        p = tf2.paragraphs[0] if i == 0 else tf2.add_paragraph()
        p.text = f"  {line}"
        p.font.size = theme["body_size"]
        p.font.color.rgb = theme["text_color"]
        p.space_after = Pt(12)
    return slide

top_img_bottom_text — Image top, text bottom

def add_top_img_bottom_text(prs, img_path, title, bullets, theme=THEME):
    slide = prs.slides.add_slide(prs.slide_layouts[6])
    bg = slide.background
    bg.fill.solid()
    bg.fill.fore_color.rgb = theme["bg_color"]
    # Image on top (60% height)
    slide.shapes.add_picture(img_path, 0, 0, prs.slide_width, Inches(4.5))
    # Title
    txBox = slide.shapes.add_textbox(Inches(0.8), Inches(4.8), Inches(11.5), Inches(0.8))
    tf = txBox.text_frame
    tf.word_wrap = True
    p = tf.paragraphs[0]
    p.text = title
    p.font.size = Pt(28)
    p.font.bold = True
    p.font.color.rgb = theme["title_color"]
    # Bullets
    txBox2 = slide.shapes.add_textbox(Inches(0.8), Inches(5.7), Inches(11.5), Inches(1.5))
    tf2 = txBox2.text_frame
    tf2.word_wrap = True
    for i, line in enumerate(bullets.split("\n")):
        line = line.strip().lstrip("•-").strip()
        if not line:
            continue
        p = tf2.paragraphs[0] if i == 0 else tf2.add_paragraph()
        p.text = f"  {line}"
        p.font.size = Pt(16)
        p.font.color.rgb = theme["text_color"]
    return slide

center_text — Section divider / title-only

def add_center_text_slide(prs, img_path, title, subtitle="", theme=THEME):
    slide = prs.slides.add_slide(prs.slide_layouts[6])
    if img_path and os.path.exists(img_path):
        slide.shapes.add_picture(img_path, 0, 0, prs.slide_width, prs.slide_height)
        # Add overlay same as full_bg
    else:
        bg = slide.background
        bg.fill.solid()
        bg.fill.fore_color.rgb = theme["bg_color"]
    txBox = slide.shapes.add_textbox(Inches(2), Inches(2.8), Inches(9), Inches(2))
    tf = txBox.text_frame
    tf.word_wrap = True
    p = tf.paragraphs[0]
    p.text = title
    p.font.size = Pt(40)
    p.font.bold = True
    p.font.color.rgb = theme["title_color"]
    p.alignment = PP_ALIGN.CENTER
    if subtitle:
        p2 = tf.add_paragraph()
        p2.text = subtitle
        p2.font.size = Pt(20)
        p2.font.color.rgb = theme["text_color"]
        p2.alignment = PP_ALIGN.CENTER
    return slide

two_column — Two-column text (for data slides)

def add_two_column_slide(prs, img_path, title, bullets, theme=THEME):
    slide = prs.slides.add_slide(prs.slide_layouts[6])
    bg = slide.background
    bg.fill.solid()
    bg.fill.fore_color.rgb = theme["bg_color"]
    # Title
    txBox = slide.shapes.add_textbox(Inches(0.8), Inches(0.5), Inches(11.5), Inches(1))
    tf = txBox.text_frame
    p = tf.paragraphs[0]
    p.text = title
    p.font.size = theme["title_size"]
    p.font.bold = True
    p.font.color.rgb = theme["title_color"]
    # Split bullets into two columns
    lines = [l.strip().lstrip("•-").strip() for l in bullets.split("\n") if l.strip()]
    mid = len(lines) // 2
    left_lines, right_lines = lines[:mid], lines[mid:]
    for col_idx, (col_lines, left_pos) in enumerate([(left_lines, 0.8), (right_lines, 7.0)]):
        txBox = slide.shapes.add_textbox(Inches(left_pos), Inches(1.8), Inches(5.5), Inches(5))
        tf = txBox.text_frame
        tf.word_wrap = True
        for i, line in enumerate(col_lines):
            p = tf.paragraphs[0] if i == 0 else tf.add_paragraph()
            p.text = f"  {line}"
            p.font.size = theme["body_size"]
            p.font.color.rgb = theme["text_color"]
            p.space_after = Pt(10)
    if img_path and os.path.exists(img_path):
        slide.shapes.add_picture(img_path, Inches(9.5), Inches(4.5), Inches(3.5), Inches(2.5))
    return slide

5. Assembly Loop

import os

LAYOUT_MAP = {
    "full_bg": add_full_bg_slide,
    "left_img_right_text": add_left_img_right_text,
    "top_img_bottom_text": add_top_img_bottom_text,
    "center_text": add_center_text_slide,
    "two_column": add_two_column_slide,
}

for row in slides:
    no = row["slide_no"]
    layout = row.get("layout", "left_img_right_text")
    img_path = f"slide_{no}.png"
    title = row.get("title", "")
    bullets = row.get("bullet_points", "")

    fn = LAYOUT_MAP.get(layout, add_left_img_right_text)

    if layout in ("full_bg", "center_text"):
        fn(prs, img_path, title, subtitle=bullets, theme=THEME)
    else:
        fn(prs, img_path, title, bullets, theme=THEME)

prs.save("presentation.pptx")

6. Post-Assembly Checks

After saving, verify:

  • File size is reasonable (images embedded increase size)
  • Slide count matches storyboard row count
  • Report the output filename and size to the user

Font Notes

  • python-pptx embeds font name references, not font files
  • Safe cross-platform fonts: Arial, Calibri, Helvetica
  • For CJK content: specify "Microsoft YaHei", "Noto Sans CJK SC", or "PingFang SC"
  • If the user specifies a custom font, check availability first

Tips

  • Always use prs.slide_layouts[6] (blank layout) for full control
  • Images should match the slide aspect ratio to avoid stretching
  • For dark themes, use light text; for light themes, use dark text
  • Keep the overlay opacity between 30%–50% for readability over images
  • Speaker notes: slide.notes_slide.notes_text_frame.text = notes

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.04%
按下载量换算56

Claude

32.12%
按下载量换算55

Cursor

19.05%
按下载量换算33

Gemini CLI

10.3%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills