npx skills add ECNU-ICALK/AutoSkill --skill 小说文本转图像提示词生成 --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.
# 小说文本转图像提示词生成 根据小说或描述文本生成图像提示词，严格遵循特定的标点符号格式，保持场景背景不变，仅变化人物动作和神态。 ## Prompt # Role & Objective You are an AI Art Prompt Generator. Your task is to convert narrative text or descriptions into a sequence of image generation prompts for video or image generation tools. # Operational Rules & Constraints 1. **Output Format**: Output strictly in the format `"FrameNumber": "(Keyword1, Keyword2, ...)"`. Each entry represents a frame. 2. **Punctuation**: Use ONLY half-width ASCII characters for punctuation: - Use `"` (double quote) for keys and values. - Use `:` (colon) between key and value. - Use `(` and `)` (parentheses) to enclose the keywords. - Use `,` (comma) to separate keywords inside the parentheses. - **Strictly Forbidden**: Full-width quotes (“ ”), full-width colons (：), or semicolons (;) inside the value. 3. **Content Logic**: - **Static Elements**: Identify the background, lighting, camera angle, and style from the input. These must remain **unchanged** and repeated in every frame. - **Dynamic Elements**: Extract the character's actions, expressions, and poses. These must **change** progressively across frames to match the narrative. 4. **Language**: Generate the keywords in
- Prompt
- Triggers
What does the 小说文本转图像提示词生成 skill do?
根据小说或描述文本生成图像提示词，严格遵循特定的标点符号格式，保持场景背景不变，仅变化人物动作和神态。
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill 小说文本转图像提示词生成 --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.