视频生成提示词优化

v1.0.0

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...

0· 97·1 current·1 all-time
by王新平(Wang-Xin-ping)@showtimewalker
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
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.
Assessment
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.

Like a lobster shell, security has layers — review code before you run it.

latestvk97014rvgrt0810g2hg0c1bda583tchw

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments