videocut-clip
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑,循环直到零口误,生成字幕。触发词:执行剪辑、开始剪、确认剪辑
Best use case
videocut-clip is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑,循环直到零口误,生成字幕。触发词:执行剪辑、开始剪、确认剪辑
Teams using videocut-clip should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/videocut-clip/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How videocut-clip Compares
| Feature / Agent | videocut-clip | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑,循环直到零口误,生成字幕。触发词:执行剪辑、开始剪、确认剪辑
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<!--
input: 删除任务 TodoList(口误+静音)
output: 剪辑后视频、字幕文件
pos: 执行 skill,用户确认删除任务后调用
架构守护者:一旦我被修改,请同步更新:
1. ../README.md 的 Skill 清单
2. /CLAUDE.md 路由表
-->
# 剪辑
> 执行删除 → 重新审查 → 循环直到零口误 → 生成字幕
## 快速使用
```
用户: 确认,执行剪辑
用户: 全删
用户: 保留静音3和5,其他都删
```
## 前置条件
需要先执行 `/videocut:剪口播` 生成删除任务 TodoList
## 流程
```
1. 读取用户确认的删除任务
↓
2. 计算保留时间段
↓
3. 生成 FFmpeg filter_complex
↓
4. 执行剪辑
↓
5. 重新转录 + 审查 ←───┐
↓ │
有口误? ──是─────────┘
↓ 否
6. 生成字幕(SRT)
↓
7. 完成
```
## 进度 TodoList
启动时创建:
```
- [ ] 确认删除任务
- [ ] 执行 FFmpeg 剪辑
- [ ] 重新转录审查
- [ ] 生成字幕
```
循环时更新版本号(v2→v3→...)
---
## 一、读取删除任务(时间戳驱动)
从 `/videocut:剪口播` 输出的 TodoList 读取。**直接使用时间戳,不要搜索文本**:
```
口误(N处):
- [x] 1. `(start-end)` 删"错误文本" → 保留"正确文本" ← 勾选=删除
语气词(N处):
- [x] 1. `(前字end-后字start)` 删"嗯" ← 勾选=删除
静音(N处):
- [x] 1. `(start-end)` 静音Xs ← 勾选=删除
- [ ] 2. `(start-end)` 静音Xs ← 未勾选=保留
```
### ⚠️ 关键规则
1. **直接用时间戳**:从 `(start-end)` 解析,不要搜索文本
2. **不要重新搜索**:审查稿已经计算好精确时间戳
3. 勾选 = 删除,未勾选 = 保留
---
## 二、FFmpeg 命令
```bash
ffmpeg -y -i input.mp4 \
-filter_complex_script filter.txt \
-map "[outv]" -map "[outa]" \
-c:v libx264 -crf 18 -c:a aac \
output.mp4
```
### filter.txt 格式
```
[0:v]trim=start=0:end=1.36,setpts=PTS-STARTPTS[v0];
[0:a]atrim=start=0:end=1.36,asetpts=PTS-STARTPTS[a0];
[0:v]trim=start=2.54:end=10.5,setpts=PTS-STARTPTS[v1];
...
[v0][a0][v1][a1]...concat=n=N:v=1:a=1[outv][outa]
```
---
## 三、重新转录审查
剪辑后必须:
1. 用 FunASR 重新转录
2. 检查是否还有口误
3. 有 → 回到 `/videocut:剪口播` 重新识别
4. 无 → 生成字幕
---
## 四、输出文件
```
01-xxx-v2.mp4 # 剪辑后视频
01-xxx-v2_transcript.json # 重新转录(验证用)
01-xxx-v2.srt # 字幕文件
```
版本递增:v1→v2→v3...
---
## 五、反馈记录
### 2026-01-15
- **语气词删除边界不精确**:删语气词时把前面的字也删了
- 原因:直接用语气词的时间戳删除
- 正确:从前一字 end 到后一字 start
- **语气词 + 静音要一起删**:`A [静音] 语气词 B` 要删整段 (A.end - B.start)
- **教训**:删除语气词时,边界是 `前一字.end` 到 `后一字.start`
### 2026-01-14
- 口误文字没删干净,只删了静音段
- 教训:直接从 TodoList 读取时间戳,不要重新查找
- **"拉满新"删成了"会的时候"**:搜索"拉满新"时间戳跨度7秒(含6秒静音),把"拉满"也删了
- 教训:对于"删前面保后面"的口误,只删差异部分
- **"AI就是AI"出现两次AI**:只删了"就是",没删第一个"AI"
- 教训:替换型口误必须删完整的第一个版本
- **系统性解决**:时间戳驱动,审查稿直接标注 `(start-end)`,剪辑脚本不再搜索文本Related Skills
videocut-subtitle
字幕生成与烧录。转录→词典纠错→审核→烧录。触发词:加字幕、生成字幕、字幕
videocut-self-update
自更新 skills。记录用户反馈,更新方法论和规则。触发词:更新规则、记录反馈、改进skill
videocut-install
环境准备。安装依赖、下载模型、验证环境。触发词:安装、环境准备、初始化
videocut-clip-oral
口播视频转录和口误识别。生成审查稿和删除任务清单。触发词:剪口播、处理视频、识别口误
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
microsoft-code-reference
Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.
eos-composition
Strunk & White composition review using the 11 principles from "Elements of Style" Chapter II. Use when analyzing structure, improving flow, or tightening prose.
enhance-cross-file
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
crossing-the-chasm
Navigate the technology adoption lifecycle from early adopters to mainstream market. Use when the user mentions "crossing the chasm", "beachhead segment", "whole product", "early adopters vs. mainstream", or "tech go-to-market". Covers D-Day analogy, bowling-pin strategy, and positioning against incumbents. For product positioning, see obviously-awesome. For new market creation, see blue-ocean-strategy.
cross-repo-plan
Creates and tracks implementation plans that span multiple repositories. Extends the single-repo plan model with a coordinator document that tracks per-repo progress, cross-repo dependencies, and execution order.
kaizen:cause-and-effect
Systematic Fishbone analysis exploring problem causes across six categories
beautiful-prose
Hard-edged writing style contract for timeless, forceful English prose without AI tics