agentleFS
evanmaranzanoevanmaranzano/Skills/video-workflow/SKILL.md

video-workflow

Skill1 starsChanged 8 days agoNo licenceView on GitHub

从一个主题出发,经深度调研(含事实核查与合规软化)→ 解说稿 → 视频分镜 → H3 AI 画面(工作台批量)→ edge-tts 旁白 → Remotion 矢量合成(全程持续动画)→ 探针渲染 低成本 QA → 15 服务器终渲,端到端产出一条 60–180 秒的 1080p 科普/讲解 MP4。 两种模式:单人解说(默认,一个声音讲到底)与双人对谈(晓晓主持 + 云希专家)。 当用户要"做一条讲解视频/科普视频/复盘片",或已有调研素材要转成视频时使用。 依赖:15 服务器 jszx-tl(10.10.127.15)SSH 与工作台 admin 通道(脚本 om_ssh.py、 h3_batch.py 均 skill 自带;凭据运行时读桌面「服务器信息整理」最新日期版)、 本地 python3 + edge-tts + ffmpeg + scrapling(选 BGM 用),渲染在 15 上完成 (Remotion 4.x + Playwright chromium-1234)。 不适用于:纯口播无画面、竖屏短视频(需改 composition)。

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.