← Back to Skills Marketplace
视频生成提示词优化
by
王新平（Wang-Xin-ping）
· GitHub ↗
· v1.0.0
· MIT-0
145
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install video-prompt-craft
Description
引导用户通过结构化问答，逐步写出专业的 AI 视频生成提示词。当用户提到"视频提示词""视频prompt""video prompt""写提示词""帮我描述一个场景""生成视频描述""创作大师""创作助手""帮我构思一个画面""帮我设计一个镜头""帮我写一段场景描述""视频场景描述""画面描述"以及含义相近的词汇...
Usage Guidance
This skill is instruction-only and appears internally consistent with its purpose: it uses only the included templates and references to generate 120–150 word English prompts and formatted output. It does not request credentials or install software. Before installing, note: (1) the agent may automatically use this skill when the user mentions trigger phrases—if you want tighter control, disable automatic invocation in your agent settings; (2) do not submit sensitive personal or secret data as part of prompt text (names, private images, credentials), since the skill will store the conversation content like any other agent interaction; (3) review the example outputs and the templates to ensure the wording and stylistic defaults match your needs. If you need the skill to call external video-generation APIs or produce files, request an explicit change because the current version is strictly a local prompt-crafting assistant.
Capability Analysis
Type: OpenClaw Skill
Name: video-prompt-craft
Version: 1.0.0
The 'video-prompt-craft' skill bundle is a well-structured tool designed to guide users through a multi-step process for creating professional AI video generation prompts. It contains comprehensive reference guides for cinematography and lighting (e.g., reference/cinematography.md, reference/lighting_mood.md) and various style templates (e.g., templates/cinematic.md, templates/3d_animation.md). The instructions in SKILL.md are strictly focused on the stated task, with no evidence of data exfiltration, malicious execution, or harmful prompt injection attempts.
Capability Assessment
Purpose & Capability
The skill's name and description (video prompt crafting) match the packaged templates, references, and runtime instructions. It only uses internal template/reference files to produce prompts; nothing requested or required is unrelated to crafting video prompts.
Instruction Scope
SKILL.md stays within the stated purpose: it describes a guided Q&A workflow, uses local templates/reference files, and assembles English prompts with a fixed output format. It does not instruct the agent to read arbitrary system files, access environment variables, or send data to external endpoints.
Install Mechanism
No install spec or code is present; this is instruction-only and therefore does not download or write code to disk. That minimizes installation risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The content and templates it needs are bundled with the skill, so requested privileges are proportionate to its purpose.
Persistence & Privilege
always:false and no unusual persistence. The bundled agents/openai.yaml includes a default_prompt which means the agent may choose to use this skill when user queries match the trigger; autonomous invocation is the platform default and not itself a problem, but be aware the skill is intended to be used automatically when users ask for prompt-writing help.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-prompt-craft - After installation, invoke the skill by name or use
/video-prompt-craft - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
**Initial release of AI video prompt crafting skill with structured guidance and rich templates/reference.**
- Introduces a structured Q&A workflow that guides users step-by-step to create professional 120–150 word English video prompts, suitable for AI tools like Runway or Sora.
- Provides extensive reference materials and templates covering cinematography, lighting/mood, narrative techniques, and 9 video styles (e.g., photorealistic, cinematic, 3D animation, aerial, stop-motion, commercial, fashion).
- Replaces previous workflow-oriented files with new files focused on creative video prompt composition.
- Features default values and expert guidance for dimensions like style, lens, depth of field, lighting, and narrative, reducing the need for repeated user queries.
- Includes a detailed output format: concise Chinese scene introduction, decision table (with options and reasoning), and the complete English prompt, plus 5 precise, scenario-specific improvement suggestions.
- Designed to activate not only on explicit prompt-writing requests but also when video ideas are vague or incomplete.
Metadata
Frequently Asked Questions
What is 视频生成提示词优化?
引导用户通过结构化问答，逐步写出专业的 AI 视频生成提示词。当用户提到"视频提示词""视频prompt""video prompt""写提示词""帮我描述一个场景""生成视频描述""创作大师""创作助手""帮我构思一个画面""帮我设计一个镜头""帮我写一段场景描述""视频场景描述""画面描述"以及含义相近的词汇... It is an AI Agent Skill for Claude Code / OpenClaw, with 145 downloads so far.
How do I install 视频生成提示词优化?
Run "/install video-prompt-craft" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 视频生成提示词优化 free?
Yes, 视频生成提示词优化 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 视频生成提示词优化 support?
视频生成提示词优化 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 视频生成提示词优化?
It is built and maintained by 王新平（Wang-Xin-ping） (@showtimewalker); the current version is v1.0.0.
More Skills