digital-human-video
Skill1 starsChanged 4 months agoNo licenceView on GitHub
用抖音系服务(火山引擎·即梦AI)制作竖版短视频,两条路线:数字人口播(OmniHuman,对口型)与氛围画面配旁白(视频生成3.0 Pro,不对口型),动手前先选。先问清场景(给谁看/看完得到什么/要他做什么/片子类型),再定选题;输入=一段文本(主题或原始素材)+目标时长+人像或场景图;文案、生成的图片、分镜与成本表三处均须用户确认(成本确认可被用户常驻豁免),确认后才调计费 API 制作(TTS→数字人或视频生成→ffmpeg 竖版合成,含 AI 标识)。当用户要"做数字人视频/口播视频/宣传视频/AI 生成视频"时使用。首次使用前须先跑 digital-human-video-init 配置密钥。
In this repository12 other files it gives its agents.
- digital-human-video-initSkill
- five-sentence-briefSkill
- four-part-promptSkill
- marketingSkill
- prompt-optimizerSkill
- seo-analytics-reportingSkill
- seo-audit-remediationSkill
- seo-content-writingSkill
- seo-keyword-mappingSkill
- seo-keyword-researchSkill
- seo-tdk-page-elementsSkill
- zmh-short-video-pipelineSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

