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

23 stars

Best use case

videocut-install is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using videocut-install 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

$curl -o ~/.claude/skills/videocut-install/SKILL.md --create-dirs "https://raw.githubusercontent.com/christophacham/agent-skills-library/main/skills/media-production/videocut-install/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/videocut-install/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How videocut-install Compares

Feature / Agentvideocut-installStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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

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: 无
output: 环境就绪
pos: 前置 skill,首次使用前运行

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
-->

# 安装

> 首次使用前的环境准备

## 快速使用

```
用户: 安装环境
用户: 初始化
用户: 下载模型
```

## 依赖清单

| 依赖 | 用途 | 安装命令 |
|------|------|----------|
| funasr | 口误识别 | `pip install funasr` |
| modelscope | 模型下载 | `pip install modelscope` |
| openai-whisper | 字幕生成 | `pip install openai-whisper` |
| ffmpeg | 视频剪辑 | `brew install ffmpeg` |

## 模型清单

### FunASR 模型(口误识别用)

首次运行自动下载到 `~/.cache/modelscope/`:

| 模型 | 大小 | 用途 |
|------|------|------|
| paraformer-zh | 953MB | 语音识别(带时间戳) |
| punc_ct | 1.1GB | 标点预测 |
| fsmn-vad | 4MB | 语音活动检测 |
| **小计** | **~2GB** | |

### Whisper 模型(字幕生成用)

首次运行自动下载到 `~/.cache/whisper/`:

| 模型 | 大小 | 用途 |
|------|------|------|
| large-v3 | 2.9GB | 字幕转录(质量最好) |

### 总计

约 **5GB** 模型文件

## 安装流程

```
1. 安装 Python 依赖
       ↓
2. 安装 FFmpeg
       ↓
3. 下载 FunASR 模型(口误识别)
       ↓
4. 下载 Whisper 模型(字幕生成)
       ↓
5. 验证环境
```

## 执行步骤

### 1. 安装 Python 依赖

```bash
pip install funasr modelscope openai-whisper
```

### 2. 安装 FFmpeg

```bash
# macOS
brew install ffmpeg

# Ubuntu
sudo apt install ffmpeg

# 验证
ffmpeg -version
```

### 3. 下载 FunASR 模型(约2GB)

```python
from funasr import AutoModel

model = AutoModel(
    model="paraformer-zh",
    vad_model="fsmn-vad",
    punc_model="ct-punc",
)
print("FunASR 模型下载完成")
```

### 4. 下载 Whisper 模型(约3GB)

```python
import whisper

model = whisper.load_model("large-v3")
print("Whisper 模型下载完成")
```

### 5. 验证环境

```python
from funasr import AutoModel

model = AutoModel(
    model="paraformer-zh",
    vad_model="fsmn-vad",
    punc_model="ct-punc",
    disable_update=True
)

# 测试转录(用任意音频/视频)
result = model.generate(input="test.mp4")
print("文本:", result[0]['text'][:50])
print("时间戳数量:", len(result[0]['timestamp']))
print("✅ 环境就绪")
```

## 常见问题

### Q1: 模型下载慢

**解决**:使用国内镜像或手动下载

### Q2: ffmpeg 命令找不到

**解决**:确认已安装并添加到 PATH

```bash
which ffmpeg  # 应该输出路径
```

### Q3: funasr 导入报错

**解决**:检查 Python 版本(需要 3.8+)

```bash
python3 --version
```

Related Skills

videocut-subtitle

23
from christophacham/agent-skills-library

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

23
from christophacham/agent-skills-library

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-clip

23
from christophacham/agent-skills-library

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

videocut-clip-oral

23
from christophacham/agent-skills-library

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

microsoft-code-reference

23
from christophacham/agent-skills-library

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

23
from christophacham/agent-skills-library

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

23
from christophacham/agent-skills-library

Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.

crossing-the-chasm

23
from christophacham/agent-skills-library

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

23
from christophacham/agent-skills-library

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

23
from christophacham/agent-skills-library

Systematic Fishbone analysis exploring problem causes across six categories

beautiful-prose

23
from christophacham/agent-skills-library

Hard-edged writing style contract for timeless, forceful English prose without AI tics

qiskit

23
from christophacham/agent-skills-library

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.