by Ceeon · Claude Skill · ★ 1.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Videocut Skills 用 Claude Code Skills 构建的视频剪辑 Agent,专为口播视频设计 为什么做这个? 剪映的"智能剪口播"有两个痛点: 无法理解语义:重复说的句子、说错后纠正的内容,它识别不出来 字幕质量差:专业术语(Claude Code、MCP、API)经常识别错误 这个 Agent 用 Claude 的语义理解能力解决第一个问题,用自定义词典解决第二个问题。 效果演示 输入:19 分钟口播原片(各种口误、卡顿、重复) 输出: 自动识别 608 处问题(静音 114 + 口误/重复 494) 剪辑后视频 72MB 全程 AI 辅助,人工只需确认 核心功能 快速开始 安装 Skills 配置 API Key 安装环境 打开 Claude Code,输入: AI 会自动: 检查 Python、FFmpeg、Node.js 安装 FunASR(口误识别模型,约 2GB) 安装 Whisper large-v3(字幕模型,约 3GB) 使用流程 ┌─────────────────────────────────────────────────────────┐ │ /videocut:安装 → 首次使用,安装环境和模型 │ └─────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────┐ │ /videocut:剪口播 视频.mp4 │ │ │ │ 1. 提取音频 → 上传云端 │ │ 2. 火山引擎转录 → 字级别时间戳
| Stars | 1,758 |
| Forks | 272 |
| Language | JavaScript |
| Category | Claude Skill |
| Quality Score | 32.2/100 |
| Open Issues | 17 |
| Last Updated | 2026-05-28 |
| Created | 2026-01-14 |
| Platforms | claude-code, node |
| Est. Tokens | ~5k |
Looking for a videocut-skills alternative? If you're comparing videocut-skills with other claude skill tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quali
My personal Claude Code and OpenAI Codex setup with battle-tested skills, plugins, hooks and agents that I use
Explore other popular claude skill tools:
videocut-skills is 用 Claude Code Skills 做的视频剪辑 Agent. It is categorized as a Claude Skill with 1.8k GitHub stars.
videocut-skills is primarily written in JavaScript.
You can find installation instructions and usage details in the videocut-skills GitHub repository at github.com/Ceeon/videocut-skills. The project has 1.8k stars and 272 forks, indicating an active community.
The top alternatives to videocut-skills on Agent Skills Hub include pilot-shell, claude-codex-settings. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.