agentleFS
Sign inStart free
kennethleungtykennethleungty/claude-music/skills/vibe/SKILL.md

vibe

Skill23 starsChanged 7 months agoMITView on GitHub

Vibe — reads your session and picks the perfect genre

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the genre metadata from sources.yml:

    line 20
  2. Distinctive:

    When in doubt, lean towards relaxing genres (lofi, ambient, classical).

    line 46
  3. Very specific:

    If takeover is true in the JSON output: prefix with *Switched over from another session —*

    line 62
  4. Very specific:

    If error about no audio player: run the install_command (if has_sudo is true) or nosudo_hint (if false) from the JSON, then retry play …

    line 63
  5. Distinctive:

    Keep it to one line. Do not explain your reasoning.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

This skill is part of the claude-music plugin. Only invoke when the user explicitly uses the slash command.

Vibe

Auto-detect the right music based on what's happening in the current session. No user input needed — the DJ reads the room.

Instructions

You have the full conversation context. Pick the best music and play it in ONE step. Do NOT spawn an agent or delegate.

Step 1: Read the room and pick music

Read the genre metadata from sources.yml:

python3 -c "
import sys
try:
    import yaml
    with open('${CLAUDE_PLUGIN_ROOT}/config/sources.yml') as f:
        data = yaml.safe_load(f)
except ImportError:
    sys.exit(1)
for genre, info in data.items():
    print(f'{genre}:')
    for s in info.get('stations', []):
        tags = ', '.join(s.get('tags', []))
        print(f'  - {s[\"name\"]}: {s.get(\"description\", \"\")}')
        print(f'    tags: {tags}')
    print()
"

Using the tags and descriptions, match the session context to the best genre. Consider:

  • What the user has been working on (e.g. debugging, building a feature, reviewing code)
  • The general mood/pace of the session
  • Any explicit mood signals from the user

When in doubt, lean towards relaxing genres (lofi, ambient, classical). The user prefers a chill atmosphere. Only pick high-energy genres if the session strongly suggests it.

Step 2: Play it

Pick a specific station name from the matched genre, then:

"${CLAUDE_PLUGIN_ROOT}/scripts/music-controller.sh" play "<station name>"

Step 3: Respond

Return a message in EXACTLY this format:

♪ Now playing {genre} — {station name}. {one-liner reason tied to the session} ♪

  • If takeover is true in the JSON output: prefix with Switched over from another session —
  • If error about no audio player: run the install_command (if has_sudo is true) or nosudo_hint (if false) from the JSON, then retry play automatically.

Keep it to one line. Do not explain your reasoning.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free