style-extractor
从参考剧本或参考素材中提取统一风格锚点(STYLE_BASE),确保全剧视觉一致性。当需要匹配参考风格、提取画风、建立风格基准、生成风格资产包时使用。
Why use this skill?
Use the OpenClaw Style Extractor to anchor your AI projects to professional visual standards. Ensure narrative and stylistic consistency across all scenes.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/hexiaochun/style-extractorWhat This Skill Does
The style-extractor skill is a specialized agent designed to enforce visual consistency across AI-generated video and image projects. By serving as the authoritative gatekeeper for visual aesthetics, it anchors every scene in a project to a pre-defined 'STYLE_BASE'. This ensures that disparate scenes—whether generated days apart or by different prompts—maintain a uniform artistic identity. The tool mandates the use of a curated, high-quality style library, eliminating visual drift and ensuring that stylistic variations (such as dream sequences or flash-backs) are treated as minimal 'delta' increments rather than full-blown stylistic departures.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/hexiaochun/style-extractor
Ensure that your OpenClaw runtime has the necessary permissions to access the upstream repository. Once installed, the skill will be available as an agent module for your script analysis pipelines.
Use Cases
- Project Standardization: Establishing a consistent 'look and feel' for a long-form animation or multi-scene video sequence.
- Script-to-Asset Translation: Automatically mapping script narrative tones to the appropriate visual style (e.g., matching a high-fantasy script to the 'Fantasy Cartoon' or 'Wuxia' style).
- Style Variation Management: Defining the master visual style while providing clear guidelines for scene-specific variations like flashbacks, UI overlays, or combat sequences.
- Visual Asset Planning: Generating structured style packages for downstream diffusion models or rendering engines.
Example Prompts
- "Analyze this script for a 3-minute romantic comedy: [Script Text]. Extract the STYLE_BASE and suggest any necessary style variants for the flashback scenes."
- "I am working on a fantasy project based in a medieval setting. Based on my script, extract the official style anchor using the predefined style library."
- "Evaluate the aesthetic requirements for this sci-fi thriller screenplay and generate the STYLE_BASE definition ensuring it adheres to the strict consistency rules."
Tips & Limitations
- Strict Adherence: The skill is designed with a 'Style Library Priority' principle. You cannot create custom styles; you must select from the official IDs 1-9. This is intentional to ensure rendering stability.
- Delta-Only Variants: When defining STYLE_VAR, focus only on the visual differences (e.g., 'apply sepia tint for memory sequence'). Do not re-describe the entire base style, as this often leads to prompt contamination.
- Context is Key: Provide the full script context, including scene descriptions and character actions. The more descriptive the input, the more accurate the style-to-narrative matching will be.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-hexiaochun-style-extractor": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
水浒传故事小人书
水浒传故事小人书创建。使用 Nano Banana Pro 模型生成手绘卡通风格的水浒传故事信息图。当用户想要创建水浒传故事插画、小人书、信息图时使用此 skill。
视频链接解析
解析视频分享链接,获取无水印视频下载地址。当用户想要下载视频、解析抖音/快手/小红书/B站链接、获取无水印视频时使用此 skill。
vidu-video
使用 Vidu Q3 Pro 模型生成视频。当用户想要文生视频、生成带音频的视频,或提到 vidu 时使用此 skill。
character-creator
创建AI角色的完整流程,包括生成详细角色描述、文生图肖像和多角度参考图。使用即梦4.5模型。当用户要求创建角色、生成人物立绘、制作角色参考图、或需要多角度人物图时使用此技能。
image-model-evaluation
评估图像生成模型的效果。对指定模型进行全面的文生图、图生图测试,包括不同参数、不同提示词、人物一致性等测试项,生成详细的HTML测试报告。当用户想要测试、评估、对比图像模型效果时使用此 skill。