声音

数据 社区

技能解读

当前原文的自动摘译,尚未人工审校。

命令

命令 · 操作 /wordsmith:voices · 列出所有已保存的语音配置文件 /wordsmith:voices [name] · 显示特定语音的详细信息 /wordsmith:voices delete [name] · 删除语音配置文件

列出所有声音

读取~/.claude/voices/中的所有文件 显示为表格:名称|描述 |来源

应用语音

通过指定语音名称与/wordsmith:writing一起使用:“使用海明威语音编辑此内容”“以品牌语音风格编写”

创造新声音

将/wordsmith:writing与示例文本一起使用:“从该书写示例中提取语音”书写技能处理提取并保存到~/.claude/voices/。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
数据
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
94 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@majiayu000 · MIT
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Voice Library

Manage saved voice profiles for consistent writing style.

## Commands

| Command | Action |
|---------|--------|
| `/wordsmith:voices` | List all saved voice profiles |
| `/wordsmith:voices [name]` | Show details for specific voice |
| `/wordsmith:voices delete [name]` | Remove a voice profile |

## Voice Storage

Voices are stored in `~/.claude/voices/` as JSON files:

```
~/.claude/voices/
├── hemingway.json
├── technical-docs.json
└── brand-voice.json
```

## Voice Profile Schema

```json
{
  "name": "profile-name",
  "description": "Brief description of when to use",
  "extractedFrom": "Source material used for extraction",
  "characteristics": {
    "sentenceLength": "short/medium/long/varied",
    "vocabulary": "simple/technical/elevated/mixed",
    "tone": "formal/casual/authoritative/warm",
    "structure": "linear/nested/fragmented"
  },
  "patterns": [
    "Pattern 1 observed in source",
    "Pattern 2 observed in source"
  ],
  "avoids": [
    "Things this voice never does"
  ],
  "exampleTransform": {
    "before": "Generic sentence",
    "after": "Same idea in this voice"
  }
}
```

## Workflow

### List All Voices

1. Read all files in `~/.claude/voices/`
2. Display as table: Name | Description | Source

### Apply Voice

Use with `/wordsmith:writing` by specifying voice name:
- "edit this using hemingway voice"
- "write in brand-voice style"

### Create New Voice

Use `/wordsmith:writing` with sample text:
- "extract voice from this writing sample"

The writing skill handles extraction and saves to `~/.claude/voices/`.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。