Skip to content
Get packs

Music Taste Assistant

Builds playlists and recommends music from your own written taste notes, checked against Spotify or the web.

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
6 files

What it does

Once installed, the agent keeps a plain-text list of the music you love and music you were told to try, and uses that list as the starting point for playlists, song suggestions and new artist ideas. It reads your taste profile before answering, labels each suggestion by how closely it matches your favourites, and adds new music to your list in dated batches without rewriting your existing entries. It can check that suggested artists and tracks exist, using Spotify if that skill is installed or a fetched web page otherwise.

Great for

  • Music listeners who keep notes on their taste and want suggestions grounded in it rather than generic charts
  • People who want a playlist for a mood or activity, such as focus or driving, drawn from songs they already own in their list
  • Users of the LifeOS system who want music tracking inside their personal knowledge base

Skip it if

  • Generating new songs or editing audio, since the skill covers recommendations and list-keeping only (the SKILL.md excludes song generation and audio editing)
  • Anyone expecting guaranteed-accurate artist facts without checking: suggestions that could not be confirmed are meant to be marked unverified, but you should still verify before relying on them
  • Users who do not want their music preferences stored in local files, since the taste corpus is a plain markdown file kept on their machine

Try asking

  • “Build me a focus playlist for deep work using my favourite tracks”
  • “What new bands would I like, based on the artists I already have?”
  • “Recommend music that sounds like the album I just added”
  • “Add these three artists and this album to my music list”
Step-by-step guide: how to use Music Taste AssistantInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    Music.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip Music.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Music.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Fill in the Taste Profile section with anchor artists and clear dislikes first, since suggestions follow it
  • Only mark tracks as favourites (star) if you genuinely love them, because favourites can drive live tour-date searches
  • Ask for a specific mood, activity or artist when you want Recommend, and use DiscoverArtists when you want to grow from your existing roster

What's inside

  • Intents/AddMusic.md
  • Intents/BuildPlaylist.md
  • Intents/DiscoverArtists.md
  • Intents/Recommend.md
  • Setup.md
  • SKILL.md

Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.