菜单
Identify songs from audio files using ShazamIO. Use when the user asks to recognize a song, identify music from an audio file, find what song is playing, or Shazam an audio clip.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/remorses/opencode-config --skill song-recognition命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Authentication and authorization with better-auth in Spiceflow and TypeScript apps. Covers server config with Drizzle adapter (Postgres and SQLite), Spiceflow middleware for forwarding auth requests, client setup, session middleware, social and email/password auth, server-side session checks, and React client hooks (useSession, signIn, signOut, signUp). Also covers device authorization (CLI device flow), bearer token auth, and server actions with auth. ALWAYS load this skill when a project uses better-auth.
Search X (Twitter) for posts, users, and threads using the grok CLI's native X search tools. Use when the user wants to find tweets, search for what people are saying about a topic, look up X users, or read full threads. Covers x_keyword_search, x_semantic_search, x_user_search, and x_thread_fetch with precise prompt templates and the full set of X search operators.
Use to debug why a specific package has duplicate dependencies in a pnpm project's node_modules, which can cause type-checking and bundler errors or duplicate singleton instances such as React contexts. Also use for pnpm workspace dependency updates. NEVER use package.json overrides to update or align versions; use `pnpm update -r <package>` instead.
基于 SOC 职业分类
正在显示 SKILL.md
| name | song-recognition |
| repo | remorses/opencode-config |
| description | Identify songs from audio files using ShazamIO. Use when the user asks to recognize a song, identify music from an audio file, find what song is playing, or Shazam an audio clip. |
Identify songs from audio files using ShazamIO (reverse-engineered Shazam API). Free, unlimited, no API key needed. Uses the full Shazam catalog.
Run the bundled script with uv run:
uv run --with shazamio ~/.config/opencode/skills/song-recognition/recognize.py /path/to/audio.mp3
The script tries multiple offsets through the file (every 5 seconds) because Shazam often fails on intros, quiet sections, or ambient parts. It stops at the first match.