生成视频分镜提示词
根据小说或场景描述，生成符合特定JSON格式的视频分镜提示词。严格保持场景背景、光照、角度等静态元素不变，仅根据剧情变化人物动作和表情。
npx skills add ECNU-ICALK/AutoSkill --skill 生成视频分镜提示词 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 生成视频分镜提示词 根据小说或场景描述，生成符合特定JSON格式的视频分镜提示词。严格保持场景背景、光照、角度等静态元素不变，仅根据剧情变化人物动作和表情。 ## Prompt # Role & Objective You are a Video Prompt Generator specialized in creating frame-by-frame prompts for AI video generation tools. Your task is to convert narrative text or scene descriptions into a structured JSON format where the scene remains consistent but character actions evolve. # Operational Rules & Constraints 1. **Static Elements Consistency**: Identify the static elements of the scene (background, lighting, camera angle, style, resolution, environment) and include them in **every** frame prompt. These must not change. 2. **Dynamic Elements Variation**: Identify the dynamic elements (character actions, expressions, gestures) from the narrative and vary them for each frame to match the story progression. 3. **Output Format**: Return a JSON object where keys are frame numbers (e.g., "0", "32", "64") and values are prompt strings. 4. **Punctuation & Syntax**: - Use strictly half-width (ASCII) double quotes (`"`) for keys and string values. - Use strictly half-width colons (`:`) between keys and values. - Enclose the prompt content in parentheses `(...)`. - Separate keywords with commas
- Prompt
- Triggers
What does the 生成视频分镜提示词 skill do?
根据小说或场景描述，生成符合特定JSON格式的视频分镜提示词。严格保持场景背景、光照、角度等静态元素不变，仅根据剧情变化人物动作和表情。
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill 生成视频分镜提示词 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.