Self media short video
Skill yanhua1010/self-media-content-workflow/skills/self-media-short-video
把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的短视频方案。用于视频号、抖音、小红书视频和其他竖屏短视频的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、BGM 建议和发布文案。只有用户提供原片并明确要求剪辑时才制作成片。From its SKILL.md
npx -y skills add yanhua1010/self-media-content-workflow --skill self-media-short-videoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.9 KB, 559 tokens by cl100k_base, as published. Nobody here has run it
短视频脚本
原则
- 一条视频只讲一个核心判断。
- 前 3 秒给出冲突、结果、利益或具体场景。
- 口播必须说得出口，不把长文章切成字幕。
- 画面承担证明、演示、对比或情绪任务，不重复字幕。
- 优先使用真实人物声音、产品录屏和真实证据，不默认数字人。
确认输入
检查：目标平台、受众、内容目标、时长、出镜方式、可用素材、核心判断、行动和不能展示的内容。缺少会改变方案的信息时最多问 3 个问题。
结构
选择一种主体结构：
- 问题 → 方法 → 例证。
- 结果 → 过程 → 教训。
- 冲突 → 选择 → 后果。
- 演示 → 解释 → 适用边界。
结尾给一个记忆点和一个主要行动。
分镜
使用 storyboard-template.md。每个镜头写清：
- 时间和时长。
- 景别、画面、人物动作或录屏操作。
- 口播、字幕和屏幕文字。
- 证据、B-roll、音效、BGM 和转场。
所有镜头时长之和必须等于目标时长。字幕与口播事实必须一致。
输出包
交付：
- 3 个钩子和推荐版本。
- 完整口播稿。
- 分镜表或录屏清单。
- 字幕稿。
- 封面标题和画面说明。
- 发布标题、正文、话题和 BGM 建议。
- 拍摄或素材缺口。
用户没有提供原片时，停在可拍摄方案。用户提供原片并明确要求剪辑时，再发现并调用当前环境的视频、字幕和音频工具。
What ships with it: 2 files
953 B alongside SKILL.md
agents/
- openai.yaml253 B
assets/
Gives 0 of the 12 instructions most video audio skills give in 559 tokens
Counted across 619 of the 725 authors here whose files we hold, read 2026-09-06
- Read product marketing context firstin 13 of 619, across 7 files
- Define the core visual thesis in one sentencein 11 of 619, across 3 files
- Break the concept into 3 to 6 scenesin 11 of 619, across 3 files
- Render the smallest working version firstin 11 of 619, across 3 files
- Start with a low-quality smoke test renderin 11 of 619, across 3 files
- Add captions for accessibility and engagementin 11 of 619, across 5 files
- Write the scene outline before writing codein 11 of 619, across 3 files
- Specify subject, action, camera, style, and moodin 11 of 619, across 5 files
- Decide what each scene provesin 10 of 619, across 2 files
- Export one clean thumbnail framein 10 of 619, across 2 files
- Pick the right tool for the jobin 10 of 619, across 4 files
- Run the test suite before proposing a fixin 8 of 619, across 7 files
Said here and by no other author read
- Focus each video on one core judgment.
- Deliver conflict or results in first three seconds.
- Ensure voiceover sounds natural when spoken.
- Check input parameters before starting.
- Use shootable plan mode by default.
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.