Smart Video Editor
把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用，再决定取舍、顺序、时长、调色和 BGM，最后用 ffmpeg 渲染。适用于"我给你几段视频，帮我剪一条小红书/朋友圈/vlog"这类需求。当用户提供视频文件并希望剪辑、拼接、配乐、调色、转成竖屏时使用。不做 AI 生成视频。
Install
npx skills add Fagan1024/smart-video-editor --skill smart-video-editorgit clone --depth 1 https://github.com/Fagan1024/smart-video-editor.git /tmp/smart-video-editor
mkdir -p ~/.claude/skills
cp -r /tmp/smart-video-editor/. ~/.claude/skills/smart-video-editorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Smart Video Editor
纯剪辑。核心区别在于**先看懂素材再动手**，而不是按文件名顺序机械拼接。
## 三个阶段
### 阶段一：看懂素材
```bash
python3 {baseDir}/scripts/probe.py <素材目录或文件列表>
```
拿到每段的时长、分辨率、朝向、帧率、有无音轨。
然后**对每一段抽帧，逐帧用 `vision_analyze` 看**：
```bash
python3 {baseDir}/scripts/extract_frames.py <video> /tmp/sve-frames --interval 1.5 --max 8
```
帧文件名形如 `clip1__t3.5.jpg`，`t` 后面就是它在原片中的秒数——视觉判断能直接映射回时间轴。
对每帧问这些（一次问清，不要分多次）：
> 这一帧里是什么内容（主体、场景、动作）？构图如何？是否存在下列问题：明显模糊/失焦、剧烈抖动、过曝或死黑、镜头遮挡、无内容的空镜、正在转场的中间态？给画面可用性打 1-5 分。
**素材多时用 `session_spawn` 并行分析**，每个子任务负责 1-2 段，让它把结论按 `{时间戳: 内容, 可用性, 问题}` 结构化返回。
### 阶段二：做剪辑决策
拿到全部画面信息后，自己判断这几件事——这是这个 skill 真正的价值所在，不要跳过：
**取舍**：可用性低于 3 分的时间段直接不要。一段 10 秒素材里只有 4 秒有内容，就只取那 4 秒。
**顺序**：按叙事逻辑排，不要按文件名。常用结构：
- 空间叙事：全景开场 → 中景 → 细节特写 → 人物/收尾
- 时间叙事：按事件发生顺序
- 情绪叙事：平静起 → 高潮 → 回落收尾
**节奏**：短视频（15-30 秒）单段 1.5-3 秒；慢节奏 vlog 可以 4-6 秒。同类画面连续出现要缩短，避免观感重复。有 BGM 时让切点尽量落在节拍上。
**调性**：根据画面内容选 `look`，不要默认套一个。
**竖屏处理**：横屏素材进竖屏成片时，主体在中间用 `crop`，主体偏移或不能裁的用 `blur_pad`。
把决策写成 EDL（JSON）：Details
- Skill name
smart-video-editor- Repository
- Fagan1024/smart-video-editor
- License
- MIT
- Repo updated
- 26 July 2026
FAQ
What does the Smart Video Editor skill do?
把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用，再决定取舍、顺序、时长、调色和 BGM，最后用 ffmpeg 渲染。适用于"我给你几段视频，帮我剪一条小红书/朋友圈/vlog"这类需求。当用户提供视频文件并希望剪辑、拼接、配乐、调色、转成竖屏时使用。不做 AI 生成视频。
How do I install the Smart Video Editor skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Fagan1024/smart-video-editor --skill smart-video-editor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Smart Video Editor popular?
It lives in Fagan1024/smart-video-editor, which has 10 GitHub stars and 1 forks.
Related skills
Talking Head Video
10Vibetool/talking-head-video
Turn a raw 口播 / talking-head selfie video plus its script into a finished explainer, vertical 9:16 or landscape 横屏 16:9 — synced burned-in subtitles, animated knowledge graphics in three selectable styles (darkcard 深色科技卡 default, watercolor 纸上水彩, inkline 白纸简笔; both style and orientation are confirmed with the user first), and a circular picture-in-picture avatar that shrinks the speaker to the top-left while a graphic or B-roll fills the screen during explanations. THE pipeline whenever someone has a clip of a person talking to camera and wants it "剪成成片", subtitles auto-added from a 逐字稿/脚本, th
Openclaw Genpark Video Creator
10alphaparkinc/openclaw-genpark-video-creator
OpenClaw GenPark Video Creator - SMPTE timecode drop-frame/non-drop-frame converter, Ken Burns cubic Bezier camera pan/zoom trajectory solver, and multi-track EDL timeline reconciler with zero dependencies.
Youtube Advisor
10AlexanderAbramovPav/youtube-advisor
Build or update a Claude Code advisor skill from any YouTube channel. Use when the user pastes a YouTube channel URL or handle, names a creator, or says "make an advisor on …", "build a skill from …", "обнови … advisor", "refresh that advisor". Triggers on bare URLs like https://youtube.com/@channel, @handles, or creator-name mentions.
Layered Holo Card
10JamesonZGJ/layered-holo-card-skill
Turn an existing photo or artwork into a layered 2.5D holographic collectible card while preserving its composition and subject pixels. Use for floating subjects, layered photo cards, or 把照片做成主体浮起的全息闪卡; not for redesigning the image or flat whole-card tilt alone.
Folio
11Ramakm/folio-anatomy
Build a museum-style exhibition plate that explains a technical idea - an invented scientific instrument drawn as a live, engraved isometric figure in three views (SVG, WebGL light, and a 3D bench you can turn through 360 degrees) with internal parts that really rotate and interact, with numbered specimen pins, a catalogue key, a working model behind every number, and wall texts that walk through the formula term by term. Use for explanatory figures, interactive explainers, "how does X work" visuals, or technical illustrations for docs, courses, posts and landing pages, even when the request n
Podcast From Research
9Easternguy/podcast-from-research
Research-to-podcast pipeline for learning new topics: 20-angle full-coverage research (with blind-spot discovery) → steered NotebookLM audio overview → MP3 delivered to you, with everything ingested into a local GBrain knowledge base for permanent recall. When the user says "create a podcast on X", this handles it end-to-end. Installs its own dependencies (notebooklm-py, GBrain) if missing.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.