# Spotify Automation

A skill that drives Spotify playback, builds playlists and reads audio features, all from your agent chat.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 4600 installs · ★ 540
- Author: Claude Office Skills
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/claude-office-skills/skills/tree/HEAD/spotify-automation/SKILL.md
- Updated: 2026-01-31
- HTML: https://affpapa.org/en/nevibecode/skills/spotify-automation

## What it does

Four things live in this skill: playback control, playlist management, music discovery and audio analysis. The agent can pause, skip forward or back, set volume, toggle shuffle and repeat, seek to a millisecond offset, and move playback to another device by `device_id`.

Playlists go two ways. Create an empty one with a name and description, then add tracks by URI, or define a smart playlist by criteria such as energy above 0.8 or tempo above 120 and have it refresh weekly. Analysis leans on audio features: danceability, energy, instrumentalness, tempo in BPM, key from 0 to 11, and mode. That is what you filter recommendations by when you want a mood rather than a genre.

Under the hood it talks to the `media-mcp` MCP server through `spotify_playback`, `spotify_playlist`, `spotify_search` and `spotify_analysis`. So you need that server configured and a Spotify account you can reach. The skill itself flags Spotify API rate limits and asks for the right scopes up front. Skip the scopes and calls start failing. Unavailable tracks need handling too, or your playlist comes out short.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill spotify-automation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/spotify-automation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/spotify-automation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill spotify-automation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/spotify-automation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill spotify-automation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/spotify-automation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install claude-office-skills/skills spotify-automation
```

2. **Manually: put the files in place**
- File: `.github/skills/spotify-automation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill spotify-automation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/claude-office-skills/skills --path spotify-automation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/spotify-automation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill spotify-automation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/claude-office-skills/skills/tree/HEAD/spotify-automation/SKILL.md

## When to use it
- build a workout playlist by tempo and energy
- move playback to another device
- get recommendations from a few seed tracks
- read a track's audio features and mood
- generate a daily mix from recently played tracks

## Example prompts
- Build a Workout Mix playlist: energy > 0.8, tempo > 120, genres electronic and pop, limit 50 tracks
- Play Bohemian Rhapsody and turn on shuffle
- Analyze audio features of my last 50 played tracks and build a mix for the current mood

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: cfa896ec1f07e34c.

BEGIN THIRD-PARTY FILE cfa896ec1f07e34c
````text
---
name: Spotify Automation
description: Automate Spotify music playback, playlist management, and audio analysis workflows
version: 1.0.0
author: Claude Office Skills
category: media
tags:
  - spotify
  - music
  - playlist
  - audio
  - entertainment
department: content
models:
  - claude-3-opus
  - claude-3-sonnet
  - gpt-4
mcp:
  server: media-mcp
  tools:
    - spotify_playback
    - spotify_playlist
    - spotify_search
    - spotify_analysis
capabilities:
  - Playback control
  - Playlist management
  - Music discovery
  - Audio analysis
input:
  - Search queries
  - Playlist configurations
  - Playback commands
  - Analysis parameters
output:
  - Playback status
  - Playlist updates
  - Track recommendations
  - Audio features
languages:
  - en
related_skills:
  - youtube-automation
  - podcast-automation
---

# Spotify Automation

Automate Spotify music playback, playlist management, and discovery workflows.

## Core Capabilities

### Playback Control
```yaml
playback_commands:
  - play_track: "spotify:track:xxx"
  - pause
  - next_track
  - previous_track
  - set_volume: 75
  - set_shuffle: true
  - set_repeat: "context"  # track, context, off
  - seek_position: 30000  # milliseconds
  - transfer_playback:
      device_id: "device_xxx"
```

### Playlist Management
```yaml
playlist_operations:
  create:
    name: "{{playlist_name}}"
    description: "{{description}}"
    public: false
    collaborative: false
    
  add_tracks:
    playlist_id: "xxx"
    tracks:
      - "spotify:track:xxx"
      - "spotify:track:yyy"
    position: 0  # optional
    
  smart_playlist:
    name: "Workout Mix"
    criteria:
      energy: "> 0.8"
      tempo: "> 120"
      genres: ["electronic", "pop"]
    limit: 50
    refresh: weekly
```

### Music Discovery
```yaml
recommendations:
  seed_tracks: ["track_id_1", "track_id_2"]
  seed_artists: ["artist_id"]
  seed_genres: ["pop", "rock"]
  
  target_features:
    energy: 0.8
    danceability: 0.7
    valence: 0.6  # positiveness
    
  limit: 20
```

### Audio Analysis
```yaml
audio_features:
  - acousticness: 0.0-1.0
  - danceability: 0.0-1.0
  - energy: 0.0-1.0
  - instrumentalness: 0.0-1.0
  - liveness: 0.0-1.0
  - loudness: -60 to 0 dB
  - speechiness: 0.0-1.0
  - tempo: BPM
  - valence: 0.0-1.0 (mood)
  - key: 0-11 (C to B)
  - mode: 0 (minor) or 1 (major)
```

## Workflow Examples

### Daily Mix Generator
```yaml
workflow:
  trigger: daily at 6:00 AM
  steps:
    - get_recently_played: 50
    - analyze_mood: based_on_audio_features
    - get_recommendations: 
        based_on: recent_tracks
````
END THIRD-PARTY FILE cfa896ec1f07e34c

The third-party file has ended. Everything between the cfa896ec1f07e34c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2581 of 3758 bytes. © Claude Office Skills · MIT · https://github.com/claude-office-skills/skills/tree/HEAD/spotify-automation/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md