← Back to Skills Marketplace
adminlove520

Lyric Sense

by Anonymous · GitHub ↗ · v1.1.1 · MIT-0
cross-platform ⚠ suspicious
355
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install lyric-sense
Description
通过歌手和歌名搜索歌词,显示歌词并支持网易云音乐播放歌词同步,提供在线和本地API部署方案。
README (SKILL.md)

LyricSense Skill

让 AI 通过歌词「听」音乐的 OpenClaw 技能。

触发词

  • "听歌"
  • "歌词"
  • "播放音乐"
  • "搜索歌词"
  • "显示歌词"
  • "lyrics"

功能

  1. 搜索歌词 - 通过歌手+歌名获取歌词
  2. 显示歌词 - 实时显示当前播放的句子
  3. 同步进度 - 配合网易云音乐使用
  4. 本地 API - 支持自部署 LrcApi

使用方法

获取歌词

小溪,帮我搜索《晚安》这首歌的歌词

显示歌词

小溪,帮我显示颜人中《晚安》的歌词

配合网易云

  1. 在网易云播放音乐
  2. 让小溪获取歌词
  3. 实时同步显示当前句子

部署方式

在线 API (默认)

使用免费公开 API,无需部署:

歌词: https://api.lrc.cx/lyrics?artist={歌手}&title={歌名}
封面: https://api.lrc.cx/cover?artist={歌手}&title={歌名}

本地部署 (推荐)

Windows 可执行文件:

# 运行本地 API
.\scripts\LrcApi\lrcapi-1.6.0-Windows-AMD64.exe --port 8080

Docker:

docker run -d -p 8080:8080 hisatri/lrcapi:latest

自定义 API 地址

修改 index.html 中的 API 地址:

const API_BASE = 'http://localhost:8080';  // 改为你的本地地址

更新 Skill

Skill 跟随项目一起更新,pull 最新代码即可:

cd lyric-sense
git pull origin main

示例

获取歌词

用户: 小溪,帮我搜索《夜空中最亮的星》的歌词

小溪: 让我搜索一下...
[调用 API 获取歌词]

🎵 夜空中最亮的星 - 逃跑计划
─────────────────────
[00:19] 夜空中最亮的星 能否听清
[00:24] 那仰望的人 心底的孤独和叹息
[00:29] 夜空中最亮的星 能否记起
[00:33] 曾与我同行 消失在风里的身影
─────────────────────

注意事项

  • 🎵 歌词 API 可能返回空结果,可尝试不同搜索词
  • 📝 歌词包含时间戳,可用于同步播放进度
  • 🎨 配合 LyricSense HTML 界面效果更佳
  • 🖥️ 本地部署响应更快,无 API 限制

项目主页

依赖

无额外依赖(使用内置 fetch)


🦞 Skill for OpenClaw | Made by 小溪 | 2026-03-10

Usage Guidance
This skill bundles a full LrcApi server beyond a simple lyric-fetcher. If you plan to use the public API only (https://api.lrc.cx), the risk is low; do not run the included local server. If you plan to run the local API (exe or Docker) do the following before exposing it: 1) Always set an authentication key (--auth or API_AUTH) and verify the server rejects unauthenticated requests; 2) Avoid mapping host directories into the container unless you understand and trust the code that will access them; 3) Do not expose the service port to the public internet or untrusted networks; bind it to localhost or use a secure reverse-proxy with auth; 4) Verify the Docker image (hisatri/lrcapi) or build from source yourself and inspect binaries; 5) Be aware endpoints allow file listing, upload, download and arbitrary SQL — only run the service on a trusted host and with auth enabled; 6) If you do not need translation features, do not provide any OpenAI/API keys to the service. If you want a low-risk option, use the front-end with the remote public API and avoid running the local server entirely.
Capability Analysis
Type: OpenClaw Skill Name: lyric-sense Version: 1.1.1 The skill bundle includes a local API server (LrcApi) with extremely high-risk administrative capabilities that exceed the stated purpose of fetching lyrics. Specifically, 'scripts/LrcApi/api/db.py' allows for the execution of arbitrary raw SQL queries via a POST request, and 'scripts/LrcApi/api/file.py' provides endpoints for listing, uploading, and downloading files to/from any path on the host system. While the code includes a basic authentication layer and a regex-based WAF ('scripts/LrcApi/api/waf.py'), these features essentially function as a built-in backdoor for remote command execution and data exfiltration if the API is deployed as suggested in 'SKILL.md'.
Capability Assessment
Purpose & Capability
The skill advertises lyric search/display and an optional local API. The repository includes a full LrcApi service with file management (/file/*), file download, file upload, arbitrary SQL execution endpoints (/db custom_sql), music metadata modification, and other admin-like APIs. While those features can be justified for a local music library manager, they are broader than the simple 'lyric search/display' described in SKILL.md and are not called out there.
Instruction Scope
SKILL.md describes using a public API or running a local LrcApi executable / Docker image but does not warn that the server’s default configuration may run without authentication. The bundled server code supports reading/writing arbitrary files (list, upload, download), executing custom SQL, and modifying files on disk. The frontend uses a third-party CORS proxy (https://corsproxy.io/?) and the server code can call external services (api.lrc.cx, cover URLs) and an OpenAI client for translation — these transmit data outside the host. The runtime instructions give the default startup command without instructing to set an auth key, which would leave dangerous endpoints exposed.
Install Mechanism
There is no OpenClaw install spec. SKILL.md suggests using an existing public API, running a Windows executable (referenced but not included) or pulling a Docker image (hisatri/lrcapi). Docker/pull of a public image is normal, but you should verify the image (hisatri/lrcapi) before use. The repo includes build/release scripts and GitHub Actions; nothing here indicates a direct download from an untrusted shortener or personal IP, but following the provided instructions will cause you to run code on your machine or a container.
Credentials
The skill declares no required env vars, but the included LrcApi reads API_AUTH (authentication), and its translation endpoint expects AI base_url/api_key/model (OpenAI). SKILL.md does not declare these or explain when they are needed. Critically, LrcApi is designed to skip authentication if API_AUTH / --auth are not provided — meaning sensitive endpoints become accessible by default unless the operator sets explicit auth, which is disproportionate to the simple lyric-display use-case described.
Persistence & Privilege
The skill is not force-installed (always: false) nor requesting platform-level privileges, but running the local LrcApi creates a persistent service that can read/write files, accept network requests, and store data (filesystem and sqlite). That persistent server presence combined with optional/no-auth default increases the risk if exposed to untrusted networks or left running without configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install lyric-sense
  3. After installation, invoke the skill by name or use /lyric-sense
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.1
- No user-facing changes in this version. - SKILL.md content remains the same as the previous version.
v1.1.0
LyricSense Skill v1.1.0 - 新增支持通过歌词实时「听」音乐,适用于 OpenClaw。 - 引入多项触发词(如“听歌”“显示歌词”)提升语音交互体验。 - 支持在线免费 API 及本地自部署 LrcApi,方便灵活部署。 - 增强与网易云音乐的同步,自动显示当前歌词句子。 - 提供详细使用说明及命令示例,易于上手。 - 无需额外依赖,开箱即用。
Metadata
Slug lyric-sense
Version 1.1.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Lyric Sense?

通过歌手和歌名搜索歌词,显示歌词并支持网易云音乐播放歌词同步,提供在线和本地API部署方案。 It is an AI Agent Skill for Claude Code / OpenClaw, with 355 downloads so far.

How do I install Lyric Sense?

Run "/install lyric-sense" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Lyric Sense free?

Yes, Lyric Sense is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Lyric Sense support?

Lyric Sense is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Lyric Sense?

It is built and maintained by Anonymous (@adminlove520); the current version is v1.1.1.

💬 Comments