← 返回 Skills 市场
68
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install music-school
功能描述
create video clips into polished promo videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. music school owners and instructors use it f...
安全使用建议
This skill appears to implement what it claims (cloud-based AI video composition) but it will upload your video files to a third-party backend and may create anonymous auth tokens automatically if you don't provide NEMO_TOKEN. Before installing or using it: (1) decide whether you are comfortable uploading student or customer videos to an external service; (2) provide your own NEMO_TOKEN if you want explicit control over credentials rather than allowing the skill to request anonymous tokens; (3) ask the publisher to clarify the config-path and persistence behavior (~/.config/nemovideo/ vs registry metadata) and whether session tokens are ever written to disk; (4) verify the service domain and privacy/retention policy for uploaded media; and (5) require explicit user consent before the skill performs any automatic backend connection or upload. If any of these are unacceptable, do not enable the skill or only use it with non-sensitive test content.
功能分析
Type: OpenClaw Skill
Name: music-school
Version: 1.0.0
The music-school skill is a legitimate integration for an AI video processing service hosted at nemovideo.ai. It facilitates video uploads, timeline management, and cloud rendering via a structured API. The instructions include standard security practices, such as hiding raw API tokens from the user and using specific attribution headers. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the skill's behavior is entirely consistent with its stated purpose of creating promotional videos.
能力评估
Purpose & Capability
The skill's name/description (video promo creation) aligns with the APIs and headers described in SKILL.md and the single required env var (NEMO_TOKEN). However, registry metadata provided earlier indicated no required config paths while the SKILL.md frontmatter explicitly lists a config path (~/.config/nemovideo/). That mismatch is an incoherence in metadata vs runtime instructions and should be clarified.
Instruction Scope
SKILL.md instructs the agent to automatically connect to a remote backend, generate an anonymous token if NEMO_TOKEN is not present, upload user-supplied media, stream SSE events, and poll status endpoints. Those operations are coherent with a cloud video-processing service, but they involve automatic network calls and uploading of user files to an external domain (mega-api-prod.nemovideo.ai). The doc also expects the runtime to derive attribution headers from an 'install path' (e.g., ~/.clawhub/) — that implies examining local paths/config which is broader than simply accepting a file and calling an API. The instructions are fairly prescriptive about token handling and state persistence (store session_id) but do not specify where or how session state/token persistence occurs on disk versus memory.
Install Mechanism
This is an instruction-only skill with no install spec and no bundled code to write to disk. That minimizes install-time risk (no external archives or packages are pulled by the skill itself).
Credentials
Only one credential is required (NEMO_TOKEN), which matches the declared primary credential and the service being used. The skill will create an anonymous token if NEMO_TOKEN is missing; that behavior is functionally consistent but means the skill will perform network-auth operations automatically. The SKILL.md also references a config path (~/.config/nemovideo/) that could be used for storage, which wasn't declared elsewhere — this should be clarified.
Persistence & Privilege
always is false (no force-inclusion). The skill tells the agent to 'store the returned session_id for all subsequent requests' and references a config directory in the frontmatter. That suggests some persistence of session state (likely in memory or a skill-scoped config), but the doc does not clearly state whether tokens or session data are written to disk or only kept in-memory. No automatic modification of other skills or agent-wide settings is described.
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 music-school - 安装完成后，直接呼叫该 Skill 的名称或使用
/music-school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
v1.0.0
Music School — Create and Export School Promo Videos v1.0.0
- Initial release: Create polished promo and enrollment videos for music schools using AI-powered cloud rendering.
- Supports uploading video/audio/image files up to 500MB in common formats (MP4, MOV, AVI, WebM, etc).
- Generate 1080p MP4 exports with fast, cloud-based processing (1-2 minutes per video).
- Includes workflows for uploading, editing, previewing, and downloading finished videos.
- Credits system and free-trial authentication built in; anonymous token gives 100 free credits for 7 days.
- Handles text overlays, BGM, and multi-track timelines to create professional school promos easily.
元数据
常见问题
Music School 是什么？
create video clips into polished promo videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. music school owners and instructors use it f... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 68 次。
如何安装 Music School？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install music-school」即可一键安装，无需额外配置。
Music School 是免费的吗？
是的，Music School 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Music School 支持哪些平台？
Music School 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 Music School？
由 mory128（@mory128）开发并维护，当前版本 v1.0.0。
推荐 Skills