dlazy

---
name: dlazy-imageseg
version: 1.0.3
description: "Image matting tool: separates foreground from background and returns transparent background URL, suitable for product image processing, character cutout, and composition."
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy imageseg -h for help."}}
---

# dlazy-imageseg

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Image matting tool: separates foreground from background and returns transparent background URL, suitable for product image processing, character cutout, and composition.

## Trigger Keywords

- imageseg

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**: 
Execute `dlazy imageseg` to get the result.

```bash
dlazy imageseg -h

Options:
  --image <image>                      Image (URL) [image: url or local path]
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## Examples

```bash
dlazy imageseg --prompt 'prompt content' 
```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-imageseg
version: 1.0.3
description: "图像抠图工具：将前景与背景分离并返回透明背景的 URL，适用于产品图片处理、人物抠图和合成。"
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy imageseg -h 查看帮助信息。"}}
---

# dlazy-imageseg

[English](./SKILL.md) · [中文](./SKILL-cn.md)




图像抠图工具：将前景与背景分离并返回透明背景的 URL，适用于产品图片处理、人物抠图和合成。

## 触发关键词

- imageseg

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**: 
执行 `dlazy imageseg` 命令获取结果。

```bash
dlazy imageseg -h

Options:
  --image <image>                      Image (URL) [image: url or local path]
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
dlazy imageseg --prompt '提示词内容' 
```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-image-generate
version: 1.0.3
description: Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When this skill is called, use dlazy <subcommand>."}}
---

# dlazy-image-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt.

## Trigger Keywords

- generate image
- draw picture
- text to image

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.



## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

This skill handles all image generation requests by selecting the best `dlazy` image model.

### Available Image Models
- `dlazy seedream-4.5`: High-quality realism/posters.
- `dlazy seedream-5.0-lite`: Fast, low-cost sketches.
- `dlazy banana2`, `dlazy banana-pro`: General text-to-image.
- `dlazy grok-4.2`: Minimalist.
- `dlazy recraft-v3`: Stylized (illustration).
- `dlazy recraft-v3-svg`: SVG/vector.
- `dlazy mj.imagine`: Midjourney style.
- `dlazy kling-image-o1`, `dlazy viduq2-t2i`, `dlazy jimeng-t2i`: High-fidelity generation.

**CRITICAL INSTRUCTION FOR AGENT**: 
1. Select the most appropriate image model.
2. Run \`dlazy <model_name> -h\` to check parameters.
3. Execute the command.


## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-image-generate
version: 1.0.3
description: 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，请自动选择对应的 dlazy 子命令执行。"}}
---

# dlazy-image-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。

## Trigger Keywords /## 触发关键词

- 生成图片
- 画图
- 文生图

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。



## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理 (How It Works)

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## Usage / 使用方法

此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。

### 可用的图片模型
- `dlazy seedream-4.5`: 高质量写实/海报。
- `dlazy seedream-5.0-lite`: 快速、低成本草图。
- `dlazy banana2`, `dlazy banana-pro`: 通用文生图。
- `dlazy grok-4.2`: 极简文生图。
- `dlazy recraft-v3`: 风格化（插画等）。
- `dlazy recraft-v3-svg`: SVG/矢量图。
- `dlazy mj.imagine`: Midjourney 风格。
- `dlazy kling-image-o1`, `dlazy viduq2-t2i`, `dlazy jimeng-t2i`: 高保真图片生成。

> **智能体关键指令**: 
1. 选择最合适的图片模型。
2. 运行 \`dlazy <model_name> -h\` 查看参数。
3. 执行命令。


## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-grok-4.2
version: 1.0.3
description: Efficient text generation, dialogue QA, and logical reasoning using Grok 4.2 text model.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy grok-4.2 -h for help."}}
---

# dlazy-grok-4.2

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Efficient text generation, dialogue QA, and logical reasoning using Grok 4.2 text model.

## Trigger Keywords

- grok 4.2
- generate text
- qa
- chat

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**: 
Run the `dlazy grok-4.2` command to get results.

```bash
dlazy grok-4.2 -h

Options:
  --prompt <prompt>                    Prompt
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```




## Command Examples

```bash
# basic call:
dlazy grok-4.2 --prompt 'prompt text'

# complex call:
dlazy grok-4.2 --prompt 'prompt text'
```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-grok-4.2
version: 1.0.3
description: 使用 Grok 4.2 文本大模型，进行高效的文本生成、对话问答与逻辑推理。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy grok-4.2 -h 查看帮助信息。"}}
---

# dlazy-grok-4.2

[English](./SKILL.md) · [中文](./SKILL-cn.md)




使用 Grok 4.2 文本大模型，进行高效的文本生成、对话问答与逻辑推理。

## 触发关键词

- grok 4.2
- 生成文本
- 问答
- 聊天

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**: 
执行 `dlazy grok-4.2` 命令获取结果。

```bash
dlazy grok-4.2 -h

Options:
  --prompt <prompt>                    Prompt
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
# 基础调用：
dlazy grok-4.2 --prompt '提示词内容'

# 复杂调用：
dlazy grok-4.2 --prompt '提示词内容'
```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-generate
version: 1.0.4
description: A comprehensive generation skill. Can generate images, videos, and audio by automatically selecting the appropriate dlazy CLI model.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When this skill is called, use dlazy <subcommand>."}}
---

# dlazy-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

A comprehensive generation skill. Can generate images, videos, and audio by automatically selecting the appropriate dlazy CLI model.

## Trigger Keywords

- generate
- create image, video, audio
- multimodal generation

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.



## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

This is a comprehensive skill that routes generation requests to the appropriate `dlazy` model based on the user's intent.

### Available Models by Category

**Image Generation:**
- `dlazy seedream-4.5`: High-quality realism/posters.
- `dlazy seedream-5.0-lite`: Fast, low-cost sketches.
- `dlazy banana2`, `dlazy banana-pro`: General text-to-image.
- `dlazy grok-4.2`: Minimalist.
- `dlazy recraft-v3`: Stylized (illustration).
- `dlazy recraft-v3-svg`: SVG/vector.
- `dlazy mj.imagine`: Midjourney style.
- `dlazy kling-image-o1`, `dlazy viduq2-t2i`, `dlazy jimeng-t2i`: Other specific high-quality image models.

**Video Generation:**
- `dlazy veo-3.1`, `dlazy veo-3.1-fast`: High-quality cinematic sequences.
- `dlazy sora-2`, `dlazy sora-2-pro`: Narrative clips.
- `dlazy kling-v3`, `dlazy kling-v3-omni`: General short clips.
- `dlazy seedance-1.5-pro`: Narrative shorts with transitions.
- `dlazy wan2.6-r2v`, `dlazy wan2.6-r2v-flash`: General/fast video production.
- `dlazy viduq2-i2v`, `dlazy jimeng-i2v-first`, `dlazy jimeng-i2v-first-tail`, `dlazy jimeng-dream-actor`, `dlazy jimeng-omnihuman-1.5`: Image-to-video, digital human, action transfer.

**Audio Generation:**
- `dlazy gemini-2.5-tts`, `dlazy doubao-tts`, `dlazy keling-tts`: Text-to-speech.
- `dlazy suno.music`: Music generation.
- `dlazy keling-sfx`: Sound effects.

**CRITICAL INSTRUCTION FOR AGENT**: 
1. Determine the media type (image, video, or audio) requested by the user.
2. Select the most appropriate model from the list above.
3. Run \`dlazy <model_name> -h\` to check the required parameters for that specific model.
4. Execute the command (e.g., \`dlazy seedream-4.5 --prompt "..."\`).


## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | \`ok: false, code: "unauthorized", message: "API key is missing or invalid"\`                                                              |
| 501  | Missing required parameter         | \`error: required option '--prompt <prompt>' not specified\`                                                              |
| 502  | Local file read error              | \`Error: Image file/Video file not found: C:\\path\\to\\your\\file\`                                                          |
| 503  | API request failed (no balance)    | \`ok: false, code: "insufficient_balance"\` |
| 503  | API request failed (server error)  | \`HTTP status code error (500 server crash)\`                                                                             |
| 504  | Asynchronous task execution failed | \`=== Generation Failed ===\` / \`{Specific error reason returned by backend, for example "Prompt violates safety policy"}\` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns \`code: "insufficient_balance"\`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns \`code: "unauthorized"\` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using \`dlazy auth set <key>\` and resume the task.

## Tips

Visit https://dlazy.com for more information.

FILE:SKILL-cn.md
---
name: dlazy-generate
version: 1.0.4
description: 综合生成技能。能够根据用户意图自动选择合适的 dlazy CLI 模型来生成图片、视频或音频。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，请自动选择对应的 dlazy 子命令执行。"}}
---

# dlazy-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

综合生成技能。能够根据用户意图自动选择合适的 dlazy CLI 模型来生成图片、视频或音频。

## Trigger Keywords / 触发关键词

- 生成
- 创建图片、视频、音频
- 多模态生成

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。



## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理 (How It Works)

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## Usage / 使用方法

这是一个综合技能，它会根据用户的意图，自动将生成请求路由到合适的 `dlazy` 模型。

### 按分类可用的模型

**图片生成 (Image):**
- `dlazy seedream-4.5`: 高质量写实/海报。
- `dlazy seedream-5.0-lite`: 快速、低成本草图。
- `dlazy banana2`, `dlazy banana-pro`: 通用文生图。
- `dlazy grok-4.2`: 极简文生图。
- `dlazy recraft-v3`: 风格化（插画等）。
- `dlazy recraft-v3-svg`: SVG/矢量图。
- `dlazy mj.imagine`: Midjourney 风格。
- `dlazy kling-image-o1`, `dlazy viduq2-t2i`, `dlazy jimeng-t2i`: 其他高质量图片模型。

**视频生成 (Video):**
- `dlazy veo-3.1`, `dlazy veo-3.1-fast`: 高质量电影级片段。
- `dlazy sora-2`, `dlazy sora-2-pro`: 叙事片段。
- `dlazy kling-v3`, `dlazy kling-v3-omni`: 通用短视频。
- `dlazy seedance-1.5-pro`: 带转场的叙事短片。
- `dlazy wan2.6-r2v`, `dlazy wan2.6-r2v-flash`: 通用/快速视频制作。
- `dlazy viduq2-i2v`, `dlazy jimeng-i2v-first`, `dlazy jimeng-i2v-first-tail`, `dlazy jimeng-dream-actor`, `dlazy jimeng-omnihuman-1.5`: 图生视频、数字人、动作迁移。

**音频生成 (Audio):**
- `dlazy gemini-2.5-tts`, `dlazy doubao-tts`, `dlazy keling-tts`: 文本转语音 (TTS)。
- `dlazy suno.music`: 音乐生成。
- `dlazy keling-sfx`: 音效生成。

> **智能体关键指令**: 
1. 确定用户请求的媒体类型（图片、视频或音频）。
2. 从上述列表中选择最合适的模型。
3. 运行 \`dlazy <model_name> -h\` 查看该特定模型所需的参数。
4. 执行命令（例如 \`dlazy seedream-4.5 --prompt "..."\`）。


## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | \`ok: false, code: "unauthorized", message: "API key is missing or invalid"\`                                                              |
| 501  | 缺少必填参数                     | \`error: required option '--prompt <prompt>' not specified\`                                                               |
| 502  | 本地文件读取失败                 | \`Error: Image file/Video file not found: C:\\path\\to\\your\\file\`                                                           |
| 503  | API 请求失败（余额不足）         | \`ok: false, code: "insufficient_balance"\` |
| 503  | API 请求失败（服务端错误）       | \`HTTP status code error (500 server crash)\`                                                                              |
| 504  | 异步任务执行失败                 | \`=== Generation Failed ===\` / \`{后端返回的具体失败原因，比如 "Prompt violates safety policy"}\`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 \`code: "insufficient_balance"\` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 \`code: "unauthorized"\` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 \`dlazy auth set <key>\` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-gemini-2.5-tts
version: 1.0.3
description: Generate multilingual, highly natural audio using Gemini 2.5 text-to-speech.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy gemini-2.5-tts -h for help."}}
---

# dlazy-gemini-2.5-tts

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Generate multilingual, highly natural audio using Gemini 2.5 text-to-speech.

## Trigger Keywords

- gemini tts
- text to speech
- generate speech

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**: 
Run the `dlazy gemini-2.5-tts` command to get results.

```bash
dlazy gemini-2.5-tts -h

Options:
  --prompt <prompt>                    Prompt
  --voice_language <voice_language>    Voice Language [default: cmn] (choices: "cmn", "en")
  --voiceName <voiceName>              Voice Name [default: Kore]
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```




## Command Examples

```bash
# basic call:
dlazy gemini-2.5-tts --prompt 'prompt text'

# complex call:
dlazy gemini-2.5-tts --prompt 'prompt text'
```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-gemini-2.5-tts
version: 1.0.3
description: 使用 Gemini 2.5 强大的文本转语音能力，生成多语言、高自然度的音频。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy gemini-2.5-tts -h 查看帮助信息。"}}
---

# dlazy-gemini-2.5-tts

[English](./SKILL.md) · [中文](./SKILL-cn.md)




使用 Gemini 2.5 强大的文本转语音能力，生成多语言、高自然度的音频。

## 触发关键词

- gemini tts
- 文本转语音
- 生成语音

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**: 
执行 `dlazy gemini-2.5-tts` 命令获取结果。

```bash
dlazy gemini-2.5-tts -h

Options:
  --prompt <prompt>                    Prompt
  --voice_language <voice_language>    Voice Language [default: cmn] (choices: "cmn", "en")
  --voiceName <voiceName>              Voice Name [default: Kore]
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
# 基础调用：
dlazy gemini-2.5-tts --prompt '提示词内容'

# 复杂调用：
dlazy gemini-2.5-tts --prompt '提示词内容'
```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-doubao-tts
version: 1.0.3
description: Synthesize text into natural and fluent speech using Doubao TTS.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy doubao-tts -h for help."}}
---

# dlazy-doubao-tts

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Synthesize text into natural and fluent speech using Doubao TTS.

## Trigger Keywords

- doubao tts
- text to speech
- generate speech
- voice broadcast

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**: 
Run the `dlazy doubao-tts` command to get results.

```bash
dlazy doubao-tts -h

Options:
  --prompt <prompt>                    Prompt
  --voice_language <voice_language>    Voice Language [default: zh-cn] (choices: "zh-cn", "en")
  --voiceId <voiceId>                  Voice ID [default: zh_female_shuangkuaisisi_uranus_bigtts]
  --speed_ratio <speed_ratio>          Speed Ratio [default: 1.0] (choices: "0.8", "1.0", "1.2", "1.5", "2.0")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```




## Command Examples

```bash
# basic call:
dlazy doubao-tts --prompt 'prompt text'

# complex call:
dlazy doubao-tts --prompt 'prompt text'
```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-doubao-tts
version: 1.0.3
description: 使用豆包 (Doubao) TTS 文本转语音模型，将文字合成为自然流畅的语音播报。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy doubao-tts -h 查看帮助信息。"}}
---

# dlazy-doubao-tts

[English](./SKILL.md) · [中文](./SKILL-cn.md)




使用豆包 (Doubao) TTS 文本转语音模型，将文字合成为自然流畅的语音播报。

## 触发关键词

- 豆包 tts
- 文本转语音
- 生成语音
- 语音播报

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**: 
执行 `dlazy doubao-tts` 命令获取结果。

```bash
dlazy doubao-tts -h

Options:
  --prompt <prompt>                    Prompt
  --voice_language <voice_language>    Voice Language [default: zh-cn] (choices: "zh-cn", "en")
  --voiceId <voiceId>                  Voice ID [default: zh_female_shuangkuaisisi_uranus_bigtts]
  --speed_ratio <speed_ratio>          Speed Ratio [default: 1.0] (choices: "0.8", "1.0", "1.2", "1.5", "2.0")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
# 基础调用：
dlazy doubao-tts --prompt '提示词内容'

# 复杂调用：
dlazy doubao-tts --prompt '提示词内容'
```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-banana2
version: 1.0.3
description: Generate/edit high-quality images with Nano Banana 2.0. Supports text-to-image and image-to-image.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy banana2 -h for help."}}
---

# dlazy-banana2

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Generate/edit high-quality images with Nano Banana 2.0. Supports text-to-image and image-to-image.

## Trigger Keywords

- nano banana 2.0
- nano banana
- generate image, edit image
- text to image, image to image

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**: 
Run the `dlazy banana2` command to get results.

```bash
dlazy banana2 -h

Options:
  --prompt <prompt>                    Prompt
  --images <images...>                 Images [image: url or local path] (max 1) [default: ]
  --aspectRatio <aspectRatio>          Aspect Ratio [default: auto] (choices: "auto", "1:1", "4:3", "3:4", "16:9", "9:16", "21:9")
  --imageSize <imageSize>              Image Size [default: 512] (choices: "512", "1K", "2K", "4K")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```




## Command Examples

```bash
# basic call:
dlazy banana2 --prompt 'prompt text' --image '/path/to/image.png'

# complex call:
dlazy banana2 --prompt 'prompt text' --image 'https://oss.dlazy.com/image.png'
```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-banana2
version: 1.0.3
description: 使用 Nano Banana 2.0 生成/编辑高质量图片，支持文生图与图生图。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy banana2 -h 查看帮助信息。"}}
---

# dlazy-banana2

[English](./SKILL.md) · [中文](./SKILL-cn.md)




使用 Nano Banana 2.0 生成/编辑高质量图片，支持文生图与图生图。

## 触发关键词

- nano banana 2.0
- nano banana
- 生成图片、编辑图片
- 文生图、图生图

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**: 
执行 `dlazy banana2` 命令获取结果。

```bash
dlazy banana2 -h

Options:
  --prompt <prompt>                    Prompt
  --images <images...>                 Images [image: url or local path] (max 1) [default: ]
  --aspectRatio <aspectRatio>          Aspect Ratio [default: auto] (choices: "auto", "1:1", "4:3", "3:4", "16:9", "9:16", "21:9")
  --imageSize <imageSize>              Image Size [default: 512] (choices: "512", "1K", "2K", "4K")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
# 基础调用：
dlazy banana2 --prompt '提示词内容' --image '/path/to/image.png'

# 复杂调用：
dlazy banana2 --prompt '提示词内容' --image 'https://oss.dlazy.com/image.png'
```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-banana-pro
version: 1.0.3
description: Generate/edit images with Nano Banana Pro. Supports text-to-image and image-to-image.
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy banana-pro -h for help."}}
---

# dlazy-banana-pro

[English](./SKILL.md) · [中文](./SKILL-cn.md)




Generate/edit images with Nano Banana Pro. Supports text-to-image and image-to-image.

## Trigger Keywords

- nano banana pro, nano banana
- generate image, edit image
- text to image, image to image

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.

## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage

**CRITICAL INSTRUCTION FOR AGENT**:
Run the `dlazy banana-pro` command to get results.

```bash
dlazy banana-pro -h

Options:
  --prompt <prompt>                    Prompt
  --images <images...>                 Images [image: url or local path] (max 1) [default: ]
  --aspectRatio <aspectRatio>          Aspect Ratio [default: auto] (choices: "auto", "1:1", "4:3", "3:4", "16:9", "9:16", "21:9")
  --imageSize <imageSize>              Image Size [default: 1K] (choices: "1K", "2K", "4K")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## Output Format

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```




## Command Examples

```bash
# text to image:
dlazy banana-pro --prompt 'prompt text' --image '/path/to/image.png'

# image to image:
dlazy banana-pro --prompt 'prompt text' --image 'https://oss.dlazy.com/image.png'

```

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-banana-pro
version: 1.0.3
description: 使用 Nano Banana Pro 生成/编辑图片，支持文生图与图生图。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，可以使用 dlazy banana-pro -h 查看帮助信息。"}}
---

# dlazy-banana-pro

[English](./SKILL.md) · [中文](./SKILL-cn.md)




使用 Nano Banana Pro 生成/编辑图片，支持文生图与图生图。

## 触发关键词

- nano banana pro, nano banana
- 生成图片、编辑图片
- 文生图、图生图

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。

## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**:
执行 `dlazy banana-pro` 命令获取结果。

```bash
dlazy banana-pro -h

Options:
  --prompt <prompt>                    Prompt
  --images <images...>                 Images [image: url or local path] (max 1) [default: ]
  --aspectRatio <aspectRatio>          Aspect Ratio [default: auto] (choices: "auto", "1:1", "4:3", "3:4", "16:9", "9:16", "21:9")
  --imageSize <imageSize>              Image Size [default: 1K] (choices: "1K", "2K", "4K")
  --input <spec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command
```

## 输出格式

```json
{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}
```





## 命令示例

```bash
# 文生图：
dlazy banana-pro --prompt '提示词内容' --image '/path/to/image.png'

# 图生图：
dlazy banana-pro --prompt '提示词内容' --image 'https://oss.dlazy.com/image.png'

```

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.

---
name: dlazy-audio-generate
version: 1.0.3
description: Audio generation skill. Automatically selects the best dlazy CLI audio/TTS model based on the prompt. 音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"When this skill is called, use dlazy <subcommand>."}}
---

# dlazy-audio-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

Audio generation skill. Automatically selects the best dlazy CLI audio/TTS model based on the prompt. 音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。

## Trigger Keywords / 触发关键词

- generate audio
- text to speech, TTS
- generate music, sound effect

## Authentication

All requests require a dLazy API key, configured through the CLI:

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.



## About & Provenance

- **CLI source code**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **Maintainer**: dlazyai
- **npm package**: `@dlazy/cli` (pinned to `1.0.6` in this skill's install spec)
- **Homepage**: [dlazy.com](https://dlazy.com)

You can install on demand without persisting a global binary by running:

```bash
npx @dlazy/[email protected] <command>
```

Or, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/[email protected]`). Review the GitHub source before installing.

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.
- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`oss.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.
- Generated output URLs returned by the API are hosted on `oss.dlazy.com`.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.

## Usage / 使用方法

This skill handles all audio generation requests by selecting the best `dlazy` audio model.

### Available Audio Models
- `dlazy gemini-2.5-tts`, `dlazy doubao-tts`, `dlazy keling-tts`: Text-to-speech.
- `dlazy suno.music`: Music generation.
- `dlazy keling-sfx`: Sound effects.
- `dlazy vidu-audio-clone`, `dlazy kling-audio-clone`: Voice cloning.

**CRITICAL INSTRUCTION FOR AGENT**: 
1. Select the most appropriate audio model.
2. Run \`dlazy <model_name> -h\` to check parameters.
3. Execute the command.


## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
| 502  | Local file read error              | `Error: Image file/Video file not found: C:\path\to\your\file`                                                          |
| 503  | API request failed (no balance)    | `ok: false, code: "insufficient_balance"` |
| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |
| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example "Prompt violates safety policy"}` |

> **AGENT CRITICAL INSTRUCTION**: 
> 1. If the execution result returns `code: "insufficient_balance"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. If the execution result returns `code: "unauthorized"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.

## Tips

Visit https://dlazy.com for more information.
FILE:SKILL-cn.md
---
name: dlazy-audio-generate
version: 1.0.3
description: 音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/[email protected]","installAlternative":"npx @dlazy/[email protected]","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","oss.dlazy.com"]},"openclaw":{"systemPrompt":"当调用此技能时，请自动选择对应的 dlazy 子命令执行。"}}
---

# dlazy-audio-generate

[English](./SKILL.md) · [中文](./SKILL-cn.md)

音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。

## Trigger Keywords / 触发关键词

- 生成音频
- 文本转语音, TTS
- 生成音乐, 音效

## 身份验证 (Authentication)

所有请求都需要 dLazy API key，通过 CLI 配置：

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 获取你的 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。



## 关于与来源 (Provenance)

- **CLI 源代码**: [github.com/dlazyai/cli](https://github.com/dlazyai/cli)
- **维护者**: dlazyai
- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.6` 版本）
- **官网**: [dlazy.com](https://dlazy.com)

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

```bash
npx @dlazy/[email protected] <command>
```

如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/[email protected]`。安装前建议先到 GitHub 仓库审阅源码。

## 工作原理 (How It Works)

此技能是 dLazy 托管 API 的轻量封装。调用时：

- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。
- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`oss.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。
- API 返回的生成结果 URL 由 `oss.dlazy.com` 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。

## Usage / 使用方法

此技能处理所有音频生成请求，通过选择最佳的 `dlazy` 音频模型。

### 可用的音频模型
- `dlazy gemini-2.5-tts`, `dlazy doubao-tts`, `dlazy keling-tts`: 文本转语音 (TTS)。
- `dlazy suno.music`: 音乐生成。
- `dlazy keling-sfx`: 音效生成。
- `dlazy vidu-audio-clone`, `dlazy kling-audio-clone`: 声音克隆。

> **智能体关键指令**: 
1. 选择最合适的音频模型。
2. 运行 \`dlazy <model_name> -h\` 查看参数。
3. 执行命令。


## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\path\to\your\file`                                                           |
| 503  | API 请求失败（余额不足）         | `ok: false, code: "insufficient_balance"` |
| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |
| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 "Prompt violates safety policy"}`                             |

> **智能体关键指令**: 
> 1. 如果执行结果返回 `code: "insufficient_balance"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)
> 2. 如果执行结果返回 `code: "unauthorized"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。

## Tips

Visit https://dlazy.com for more information.