video-workflow
Skill27 starsChanged 38 days agoMITView on GitHub
Resume or plan a video project from its current artifacts, route only missing stages, and track delivery status and revision impact.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- evanmaranzano/Skillstheir own version, first seen Nov 4, 2026
- ArcReel/ArcReeltheir own version, first seen Oct 8, 2026
- ArcReel/skillstheir own version, first seen Oct 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ArcReel/ArcReel★ 6.3ksame name
- ArcReel/skills★ 6same name
- evanmaranzano/Skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- cover-art-directionSkill
- cover-independent-reviewSkill
- evidence-story-scriptSkill
- explainer-motionSkill
- generated-brollSkill
- video-reference-studySkill
- video-release-qaSkill
- video-shot-plannerSkill
- video-source-indexSkill
- voice-subtitle-syncSkill
The file
Files
English instructions · 简体中文
For English-language tasks, read SKILL.en.md and its English reference templates before proceeding. Both editions use the same tools and authorization boundaries.
视频制作总控
从用户指定版本和已有产物进入。先明确是新片、续作、原采访拆条、字幕修复还是只改封面;不重启已经稳定的阶段。
输入与决策
确定目标观众、用途、画幅、已有稿件/音频/素材、当前版本、工具与授权范围。采用用户给出的路径、声音、模型和风格;缺项做可逆假设并记录,费用或外发等依赖必要授权的部分保持待执行。
参考 项目卡与状态。记录当前文件与具体待项,不要求先建空表格。原片只读,新版本保留旧产物;重用已有项目状态文件即可。
按缺失工序路由,已安装时使用下列同名 skills;未安装时依据本节输入输出自行推进,或明确所需工具能力,不假称调用了不存在的技能:
- 已有采访/录屏:video-source-index 建立来源和可用区间。
- 新故事:evidence-story-script 核验主张与开头承诺,再用 video-shot-planner 检查镜头覆盖。
- 可解释的机制:explainer-motion 演示状态变化;概念镜头才考虑 generated-broll。
- 原声/授权配音:voice-subtitle-sync 建立实测时间与字幕。
- 封面:cover-art-direction 制作,cover-independent-review 用独立上下文实际看图。
- 成片:video-release-qa 检查当前输出,按目标平台准备文案。
- 用户只想学参考片:video-reference-study,不自动生产视频。
推进与验收
真实素材、简短证据卡、2D 关系图与 3D 实体按内容需要组合;不固定占比。开场首图与首句提出同一问题,正文回答。AI 开场仅在本次选择生成路线时安排,并计入已有预算。
锁稿后先验证最容易出错的完整事件或开场衔接,带实际音频,再扩展同类镜头。工具检测只能证明覆盖到的技术项。缺播放/听辨/读图能力时继续可独立工序,当前状态写待验收。
把内容、技术、静态画面、连续运动、声音、封面、权利及外发条件分别记录。审阅版可交付具体待项;必要制作验收齐备才称制作包完成。公开发布依用户已有明确授权处理。
修改影响与交付
声音变化重算受影响字幕和镜头;分镜变化重检运动、衔接与相关封面承诺;封面变化重做对应审图;纯字幕/Logo改动只复查有关部分。 交付列当前版本、成片/工程/字幕/封面/文稿/来源的可点击路径、实际状态和下一动作。不要默认压缩包,也不要在索引中暴露密钥。
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.

