SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsvideo-text-storyboard

video-text-storyboard

Design & creation

View repository

Updated 10-16 06:52

About this skill

video-text-storyboard

Note: If this is your first time using it, make sure videoclaw is installed:uvx videoclaw --help

Trigger Scenarios

Triggered when the user says the following:

  • "Help me generate a storyboard"
  • "Help me write a video script"
  • "Help me design how to shoot this video"
  • "Help me make a video plan"

Input

Obtain by asking follow-up questions in sequence via AskUserQuestion:

  1. Video Type(first question, choose one from multiple options)

    • Story type (emotional short film, micro film)
    • Product showcase type (brand advertisement, e-commerce video)
    • Character action type (wuxia, dance, combat)
    • Scenery travel type (natural scenery, city street photography)

  2. Video Theme: "What does this video want to tell / showcase?"

  3. Material Source(choose one of two)

    • I have images, upload directly
    • Help me generate material images with AI (→ first call t2i to generate material images, then proceed to storyboard generation)

  4. Type-specific Follow-up Questions(branch based on the result of step 1)

    Type Follow-up Content
    Story type Character appearance description / style (comedy/warm/epic feel)
    Product showcase type Product name and appearance description / brand tone (high-end/tech feel/light and fashionable)
    Character action type Character appearance description / action type (wuxia/dance/combat/stunts)
    Scenery travel type Shooting location/scene description / atmosphere (healing/epic feel/documentary style)

  5. Duration: "How long does the video need to be? 15 seconds / 30 seconds"

Generation Key Points

After loading the skill, use the context to generate the text storyboard.

Template Selection

Based on the video type selected by the user, load the corresponding references file:

After loading the corresponding file, use the template structure and examples in it to generate the storyboard.

Storyboard Generation Key Points

Each storyboard includes:

  • Time Range: precise seconds (e.g., 2-6 seconds)
  • Visual: scene + action + dialogue + emotion, merged into one field
  • Sound Effect: the background sound effect of this shot

Qualified Example

Input: Make an animation video of a frost king's coronation

Output：

【素材介绍】：
【@图1】黄色圆滚滚小怪兽，无鼻设计，头顶小橘子
【@图2】冰封圣剑，剑身蓝光流转
【@图3】冰之王冠，由冰晶碎片拼接而成
【@图4】冰封王座，台阶和座椅有冰晶纹路
【@图5】极寒冰封王座大殿场景，浮空冰峰刺破阴云

【场景描写】：
极寒冰封之地，浮空冰峰刺破阴云，寒风呼啸，冰封大殿寂静威严

【背景音】：
史诗感 夹杂冰面细微碎裂声

【分镜】：
【特写圣剑】（0-4秒）
画面：特写【@图2】冰封圣剑，剑身蓝光流转，插在寒冰基座上
音效：冰裂声、低沉嗡鸣

【拔剑】（4-8秒）
画面：镜头后拉。【@图1】黄色小怪兽肉垫爪子紧紧握住【@图2】剑柄，用力向上拔剑
音效：拔剑声、冰裂声

【冰甲覆身】（8-12秒）
画面：全身镜头。【@图1】小怪兽用力拔出圣剑瞬间，无数冰晶碎片从四面八方飞聚而来，瞬间拼接成完整冰甲覆盖全身
音效：剑鸣、冰晶碰撞声

【戴上王冠】（12-16秒）
画面：【@图1】小怪兽抬手，无数冰晶冰片从空中飞聚而来，拼成【@图3】冰之王冠；小怪兽将王冠戴在头上
音效：冰晶拼接声

【登基定格】（16-20秒）
画面：全景。【@图1】小怪兽（穿戴冰甲）手持【@图2】圣剑，站在【@图4】冰封王座上，双眼亮起冰蓝光芒，远处【@图5】冰峰堡垒在背景中矗立
音效：余音回荡

【注意事项】：
- 角色设定：黄色小怪兽严格保持无鼻设计，头顶小橘子
- 氛围：全程冷色调，突出寒冰、冰晶质感，与角色暖黄色形成强烈视觉对比
- 动作节奏：每个镜头一个简单动作，拔剑 → 冰甲覆身 → 戴王冠 → 登基
- 细节还原：头顶小橘子、冰封圣剑蓝光、王冠冰晶拼接纹路等关键细节必须清晰呈现

Save

After generation, save to <project>/videos/<video>/storyboard/text_storyboard.md

Interactive Confirmation

Use AskUserQuestion to ask the user:

"This is the generated storyboard, are you satisfied with it?"

Options:

  • Satisfied → continue to the next step
  • Modify → ask specifically what needs to be changed
  • Regenerate → Retry directly without making changes

Common mistakes

❌ Arranging too much content for each shot: a video generation model absolutely cannot execute this much in 4 seconds; arrange only one simple action per shot

✅ Keep the content of each shot concise, describing only one action or change

❌ Confusing material references: not specifying what is referenced

✅ Use the 【@Image 1】【Image 2】 format to clearly reference materials

❌ Ignoring sound effects: sound effect design can greatly improve quality

✅ Add sound effects: background music + sound effects

❌ Missing notes: the ending does not emphasize key elements

✅ Add notes: character settings, atmosphere, action pacing, detail restoration

❌ Too few shots: 1-2 shots cannot present a complete story

✅ Using more shots is fine; refine the content of each shot, but keep the total duration to about 30 seconds (6-8 shots)

❌ Extra blank lines between paragraphs: no blank lines are needed between each paragraph or shot

✅ Write everything continuously, with no blank lines

Negative example：

剧情梗概

大法师安东尼达噜想要在小镇广场展示法术。

镜头1
阳光明媚的小镇广场...

Positive example：

剧情梗概
大法师安东尼达噜想要在小镇广场展示法术。
镜头1
阳光明媚的小镇广场...