lyric-sense/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}&ti
npx skillsauth add adminlove520/xiaoxi-skills lyric-senseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
让 AI 通过歌词「听」音乐的 OpenClaw 技能。
小溪,帮我搜索《晚安》这首歌的歌词
小溪,帮我显示颜人中《晚安》的歌词
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}
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
修改 index.html 中的 API 地址:
const API_BASE = 'http://localhost:8080'; // 改为你的本地地址
Skill 跟随项目一起更新,pull 最新代码即可:
cd lyric-sense
git pull origin main
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
─────────────────────
无额外依赖(使用内置 fetch)
🦞 Skill for OpenClaw | Made by 小溪 | 2026-03-10
data-ai
Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
development
Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.
development
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
devops
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.