Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

song-recognition

Étoiles40

Forks2

Mis à jour29 juin 2026 à 15:16

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.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

remorses

remorses/opencode-config

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

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.

Song Recognition

Identify songs from audio files using ShazamIO (reverse-engineered Shazam API). Free, unlimited, no API key needed. Uses the full Shazam catalog.

Usage

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.

Notes

Shazam returns one result per request, not a ranked list.
Short clips (under 5s) may not match. The script uses 15s clips.
If no offset matches, the song may not be in Shazam's catalog, or it could be a cover/remix that fingerprints differently.
Results include title, artist, genre, and a Shazam URL.

Plus depuis ce dépôt

même dépôt

transactional-email

remorses/opencode-config

How to write and send transactional emails (welcome, first-deploy, notifications) from Cloudflare Workers. Covers the preferred personal writing style (no headings, Gmail-default look, dark mode), building HTML with plain template strings, the send_email wrangler binding, previewing in light/dark mode with Playwriter, and test-sending real emails via a temp worker without deploying. ALWAYS load this skill when adding, editing, or testing transactional emails in a project.

2026-07-1040

better-auth

remorses/opencode-config

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.

2026-07-0740

cloudflare-workers

remorses/opencode-config

Cloudflare Workers and Durable Objects conventions for TypeScript projects. Covers wrangler.jsonc configuration, type-safe env via `wrangler types` and `import { env } from 'cloudflare:workers'`, secrets.required for typed secrets, custom_domain for routing, preview/production environments, deploy scripts, Durable Objects with SQLite, and Spiceflow as the web framework with Vite. ALWAYS load this skill when a project uses wrangler, Cloudflare Workers, Durable Objects, or deploys to Cloudflare. Load it before writing any wrangler config, worker code, or deploy scripts.

2026-07-0340

drizzle

remorses/opencode-config

Drizzle ORM conventions and best practices for TypeScript projects. Covers namespace imports, Prisma-like query API, object-style where filters, schema design (ULIDs, cascade deletes, indexes, enums over bools), Zod schema generation, type inference, transactions, migrations, and driver setup for Cloudflare Durable Objects (via sqlite-proxy), libSQL/Turso, Postgres via Hyperdrive, and Cloudflare D1. ALWAYS load this skill when a repo uses drizzle-orm.

2026-07-0340

stripe

remorses/opencode-config

Stripe billing patterns for spiceflow + Drizzle apps. Covers creating products and prices via the Stripe CLI with stable lookup keys, multi-currency USD+EUR pricing, monthly/yearly subscriptions, type-safe Checkout and Billing Portal integration in spiceflow routes, webhook handling, and the rules for preventing double customers and double subscriptions in the database. Load this skill whenever adding, modifying, or debugging any Stripe code (prices, checkout sessions, portal sessions, webhooks, subscription logic).

2026-06-2840

stripe-disputes

remorses/opencode-config

Stripe dispute and chargeback evidence workflow. Covers listing open disputes via CLI, collecting evidence from databases and APIs, generating evidence PDFs with react-pdf, capturing screenshots with Playwriter, rendering email images, and submitting evidence via Stripe CLI. Includes best practices for winning disputes on SaaS and digital products, Visa CE 3.0 prior undisputed transactions, per-reason-code evidence strategies, and file formatting rules. Load this skill when handling Stripe disputes, chargebacks, or generating evidence documents.

2026-06-2540

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.

Song Recognition

Identify songs from audio files using ShazamIO (reverse-engineered Shazam API). Free, unlimited, no API key needed. Uses the full Shazam catalog.

Usage

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.

Notes

Shazam returns one result per request, not a ranked list.
Short clips (under 5s) may not match. The script uses 15s clips.
If no offset matches, the song may not be in Shazam's catalog, or it could be a cover/remix that fingerprints differently.
Results include title, artist, genre, and a Shazam URL.