环境准备。安装依赖、配置 API Key、验证环境。触发词:安装、环境准备、初始化
Scanned 9/5/2026
Install to Claude Code
npx -y skills add aAAaqwq/AGI-Super-Skills --skill videocut-setup --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Videocut Setup?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aaaaqwq-videocut-setup)More formats (shields.io, HTML) on the badges page.
---
name: videocut:安装
description: 环境准备。安装依赖、配置 API Key、验证环境。触发词:安装、环境准备、初始化
---
<!--
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
```
## 依赖清单
| 依赖 | 用途 | 安装命令 |
|------|------|----------|
| Node.js | 运行脚本 | `brew install node` |
| FFmpeg | 视频剪辑 | `brew install ffmpeg` |
| curl | API 调用 | 系统自带 |
## API 配置
### 火山引擎语音识别
控制台:https://console.volcengine.com/speech/new/experience/asr?projectName=default
1. 注册火山引擎账号
2. 开通语音识别服务
3. 获取 API Key
配置到项目目录 `.claude/skills/.env`:
```bash
# 文件路径:剪辑Agent/.claude/skills/.env
VOLCENGINE_API_KEY=your_api_key_here
```
## 安装流程
```
1. 安装 Node.js + FFmpeg
↓
2. 配置火山引擎 API Key
↓
3. 验证环境
```
## 执行步骤
### 1. 安装依赖
```bash
# macOS
brew install node ffmpeg
# 验证
node -v
ffmpeg -version
```
### 2. 配置 API Key
```bash
# 在项目 .claude/skills/ 目录下创建 .env 文件
echo "VOLCENGINE_API_KEY=your_key" >> .claude/skills/.env
```
### 3. 验证环境
```bash
# 检查 Node.js
node -v
# 检查 FFmpeg
ffmpeg -version
# 检查 API Key(在项目目录下执行)
cat .claude/skills/.env | grep VOLCENGINE
```
## 常见问题
### Q1: API Key 在哪获取?
火山引擎控制台 → 语音技术 → 语音识别 → API Key
### Q2: ffmpeg 命令找不到
```bash
which ffmpeg # 应该输出路径
# 如果没有,重新安装:brew install ffmpeg
```
### Q3: 文件名含冒号报错
FFmpeg 命令需加 `file:` 前缀:
```bash
ffmpeg -i "file:2026:01:26 task.mp4" ...
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.