← 返回 Skills 市场
339
总下载
1
收藏
0
当前安装
8
版本数
在 OpenClaw 中安装
/install ohyesai-music
功能描述
Generate custom music tracks (vocal or instrumental) via OhYesAI asynchronously.
安全使用建议
This skill appears coherent, but before installing consider: (1) You must provide your OHEYSAI_API_KEY — only use a key you trust and consider limiting/rotating it. (2) The skill runs curl/grep/sleep and will save MP3 files to the agent's current working directory and then send those files to the user; ensure you are okay with those filesystem and network actions. (3) Verify the API/download domains (ohyesai.com and the returned storage URL domain) are legitimate and acceptable for your data/privacy needs. (4) Be aware of potential costs or rate limits from the external service and copyright/usage implications for generated audio. (5) If you want tighter safety, run the script in a restricted environment or sandbox and test with a throwaway API key first.
功能分析
Type: OpenClaw Skill
Name: ohyesai-music
Version: 1.0.7
The skill facilitates music generation via the OhYesAI API using a standard asynchronous workflow (submit, poll, download). It utilizes common system utilities like `curl`, `grep`, and `sleep` within `SKILL.md` to manage API interactions and retrieve generated MP3 files. The logic is transparent, aligns strictly with the stated purpose, and contains no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力标签
能力评估
Purpose & Capability
Name/description map to the declared requirements: it needs an OHEYSAI_API_KEY and curl/grep/sleep to call an external API, poll status, and download MP3 files. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md prescribes an explicit asynchronous flow (submit -> poll -> extract MP3 URL -> curl download -> deliver). This stays within the music-generation purpose. It does require the agent to write MP3 files to the current working directory and to present/send those local files to the user — that is expected for file delivery but is worth noting because it involves local filesystem access and sending binary files back to the user.
Install Mechanism
Instruction-only skill with no install spec or archive downloads. Lowest-risk install posture: nothing is written to disk by an installer beyond the agent executing the provided runtime commands.
Credentials
Only one environment variable is required (OHEYSAI_API_KEY), which is appropriate for an API-backed music-generation service. No extra or unrelated secrets/config paths are requested.
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or system-wide agent settings. The skill requires the agent to perform network and filesystem actions at runtime but does not request elevated or persistent platform privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ohyesai-music - 安装完成后，直接呼叫该 Skill 的名称或使用
/ohyesai-music触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.7
- Removed the file: _meta.json.
- Updated the setup section to use an OhYesAI homepage link with a source parameter.
- No functional or workflow changes to the music generation or delivery process.
- Documentation clarified; all usage and example instructions remain the same.
v1.0.6
No significant code or logic changes; SKILL.md documentation update only.
- Added an additional customer service QR code image at the end of the documentation.
- No functional or behavioral changes to the skill.
v1.0.5
- Initial release to clawdbot skill store.
- Added _meta.json file for skill metadata.
- No changes to functionality or documentation—core usage and workflow remain the same.
v1.0.4
- Removed the "联系客服" (Contact customer service) section from the top and placed it at the end of the document.
- No changes to core features or implementation instructions.
- Documentation content remains functionally unchanged except for the re-ordering of customer service info.
v1.0.3
- Added a customer service contact image (20260323-174006.jpeg) to the documentation.
- Included a “联系客服” section with the image in the skill readme.
v1.0.2
- Changed all OhYesAI API URLs from "https://dev.ohyesai.com" to "https://ohyesai.com".
- Updated the API key application link in the setup instructions to match the new domain.
v1.0.1
**Asynchronous music generation workflow update:**
- Music generation now uses an async workflow: submit task → poll status → download file.
- Requires extraction and storage of `taskId` from the submit API before polling.
- Adds usage of `sleep` and continuous polling until the status is “已完成” or failed.
- Updated examples and scripts to reflect the asynchronous task handling process.
- Delivery instructions remain strict: download the real audio file and send a true file link or file, never reply with plain text only.
v1.0.0
- Initial release of the ohyesai-music skill.
- Generate custom music tracks (vocal or instrumental) via the OhYesAI API in Clawdbot.
- Multi-turn conversation collects user input for prompt, style, and instrumental/vocal options.
- Automatically generate a suitable song title; do not ask the user for it.
- Strictly download and deliver the actual audio file to the user (not just a link or text).
- Requires the OHEYSAI_API_KEY environment variable for authentication.
元数据
常见问题
音乐生成 是什么？
Generate custom music tracks (vocal or instrumental) via OhYesAI asynchronously. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 339 次。
如何安装 音乐生成？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ohyesai-music」即可一键安装，无需额外配置。
音乐生成 是免费的吗？
是的，音乐生成 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
音乐生成 支持哪些平台？
音乐生成 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 音乐生成？
由 bajie-git（@bajie-git）开发并维护，当前版本 v1.0.7。
推荐 Skills