首页 / 技能 / Browser — 浏览器

🎵 Browser — 浏览器

v1.0.0

歌词视频 无需学习专业剪辑软件。只需描述你的需求——让歌词随节拍同步，并在浏览器中显示——即可……

0· 18·0 当前·0 累计
linmillsd7 头像by @linmillsd7
开发工具代码生成网络工具浏览器自动化存储部署
下载技能包
最后更新
2026/4/19
0
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
The skill's requirements and runtime instructions are internally consistent with a cloud-based lyric-video service: it only needs a single service token, calls the nemovideo.ai API, and has no install step or unrelated credential requests.
评估建议
This skill appears to be what it claims: it uploads media and uses the nemovideo.ai backend to produce lyric videos. Before installing/using, consider: (1) the skill will send your audio/media files and tokens to https://mega-api-prod.nemovideo.ai — only proceed if you trust that service and understand its privacy/retention policy; (2) the skill may store a short-lived anonymous token and session_id in a config path under your home directory for convenience — if you prefer not to persist credent...
详细分析 ▾
✓ 用途与能力
Name/description (create lyric videos in-browser) match the declared requirement (NEMO_TOKEN) and the SKILL.md which exclusively describes API calls to nemovideo.ai for uploads, session creation, rendering, and export.
✓ 指令范围
SKILL.md stays focused on the service workflow (obtain/authenticate token, create session, upload media, send SSE edits, poll export). It does not instruct reading unrelated system files or harvesting unrelated environment variables. It does instruct reading the frontmatter and detecting install path for attribution headers, which is reasonable for attribution but will require the agent to inspect its runtime context.
✓ 安装机制
No install spec or downloads are present (instruction-only). Nothing will be written to disk by an installer; the skill expects the environment and will call remote APIs.
ℹ 凭证需求
Only NEMO_TOKEN is required and is the primary credential used to call the nemovideo.ai API, which is proportionate. Metadata also references a config path (~/.config/nemovideo/) and the skill proposes storing session_id/token for subsequent requests — this is reasonable but means the skill may read/write a small config area in the user profile for session persistence.
✓ 持久化与权限
always:false and normal autonomy settings. The skill does ask to store session_id/token for requests, but it does not request persistent system-wide privileges or modify other skills' configuration.
安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/4/19

Browser Lyric Video skill, initial release: - Instantly creates lyric-synced videos in the browser from audio uploads (MP3, WAV, MP4, MOV, up to 200MB). - No software required — describe your desired lyric video, upload your files, and receive a 1080p MP4 (or other formats) in 1–2 minutes. - Automatic backend connection and token authentication with 100 free credits for new users. - Supports status checks, credit balance, export/download, and streamlined user-friendly prompts. - All interactions handled securely with anonymous tokens and session-based cloud rendering. - Designed for musicians and creators who want fast, easy lyric video generation.

● 无害

安装命令

点击复制
官方npx clawhub@latest install browser-lyric-video
镜像加速npx clawhub@latest install browser-lyric-video --registry https://cn.longxiaskill.com

技能文档

快速开始

把音频文件发给我，或直接告诉我你的想法。
试试说：
  • “create my audio files”
  • “export 1080p MP4”
  • “sync the lyrics to the beat”

首次连接

用户首次打开技能时，自动连接后端并提示“Setting up...”。 鉴权：检查环境变量 NEMO_TOKEN。若已存在，直接进入第 2 步。
  • 获取免费 token：生成随机 UUID 作为客户端标识，POST 到 https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token，Header 带 X-Client-Id。返回的 data.token 即为 NEMO_TOKEN，含 100 免费积分，7 天有效。
  • 创建会话：POST 到 https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent，Header 带 Authorization: Bearer ，Body 为 {"task_name":"project","language":""}。保存返回的 session_id 供后续调用。
全程保持提示简短，不向用户展示原始 API 响应或 token 值。

# Browser Lyric Video — 在浏览器中制作歌词视频 把音频文件拖进聊天，告诉我需求即可。云端 GPU 完成渲染，本地无需安装任何软件。 典型流程：上传 3 分钟 MP3 与歌词文本，要求“让歌词随节拍同步并在浏览器显示”，约 1-2 分钟后即可下载 1080p MP4。 提示：上传带时间戳的歌词文件可显著提升同步精度。

输入与动作映射

用户提及浏览器歌词视频、画幅、文字叠加、音轨等关键词时，按意图路由：

| 用户说… | 动作 | 跳过 SSE？ | |-------------|--------|----------| | “export” / “导出” / “download” / “send me the video” | → §3.5 导出 | ✅ | | “credits” / “积分” / “balance” / “余额” | → §3.3 积分 | ✅ | | “status” / “状态” / “show tracks” | → §3.4 状态 | ✅ | | “upload” / “上传” / 用户发送文件 | → §3.2 上传 | ✅ | | 其他（生成、编辑、加 BGM…） | → §3.1 SSE | ❌ |

云端渲染流程

每段导出任务在云端 GPU 节点排队，合成视频层并采用平台级压缩（H.264，最高 1080×1920），30-90 秒内返回下载链接。 会话 token 携带渲染任务 ID，若提前关闭标签页会导致任务孤立。

技能归因：运行时读取 YAML 头信息：

  • X-Skill-Source: browser-lyric-video
  • X-Skill-Version: 取自头信息 version
  • X-Skill-Platform: 按安装路径检测（~/.clawhub/ → clawhub，~/.cursor/skills/ → cursor，其余 unknown）

所有请求必须携带： Authorization: Bearer 、X-Skill-Source、X-Skill-Version、X-Skill-Platform。 缺失归因头将返回 402 错误。

API 基址：https://mega-api-prod.nemovideo.ai

  • 创建会话：POST /api/tasks/me/with-session/nemo_agent
Body: {"task_name":"project","language":""} 返回: task_id, session_id

  • 发送消息（SSE）：POST /run_sse
Body: {"app_name":"nemo_agent","user_id":"me","session_id":"","new_message":{"parts":[{"text":""}]}} Header: Accept: text/event-stream 超时: 15 分钟

  • 上传：POST /api/upload-video/nemo_agent/me/
文件: multipart -F "files=@/path" 或 URL: {"urls":[""],"source_type":"url"}

  • 积分：GET /api/credits/balance/simple
返回: available, frozen, total

  • 会话状态：GET /api/state/nemo_agent/me//latest
关键字段: data.state.draft, data.state.video_infos, data.state.generated_media

  • 导出（免费，不扣积分）：POST /api/render/proxy/lambda
Body: {"id":"render_","sessionId":"","draft":,"output":{"format":"mp4","quality":"high"}} 轮询 GET /api/render/proxy/lambda/ 每 30 秒，直到 status = completed。 下载地址在 output.url。

支持格式：mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac。

数据来源：ClawHub ↗ · 中文优化：龙虾技能库