AM

    agensi music dsl skill

    1

    This skill enables deterministic, symbolic music composition through Music-DSL, allowing you to write, validate, and render audio directly from plain-text files.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more
    AM

    agensi music dsl skill

    Example session with this skill installed

    Compose a short synthwave loop called 'Digital Sunset' in C minor at 100 BPM. Use a sawtooth bass and a square lead. Check it for errors and provide the code.

    • Read your context and instructions
    • Compiled the agensi music dsl

    I have composed the synthwave loop 'Digital Sunset' in Music-DSL. I have also run a syntax check to ensure it is valid and ready for rendering.

    Digital Sunset Composition

    tempo: 100   name: Digital Sunset   key: Cm
    
    -- lead: square 0.4 0.2 reverb:0.4 --
    C4 q  Eb4 q  G4 q  Bb4 q
    C5 h  Bb4 q  G4 q
    
    -- bass: sawtooth 0.5 -0.2 filter:lp 500 --
    C3 h  Ab2 h  Bb2 h  C3 h
    C3 q  C3 q  Ab2 q  Ab2 q  Bb2 q  Bb2 q  C3 h
    
    -- drums: @gen drums four --
    

    The syntax check returned: OK — no issues found. The composition uses a low-pass filter on the sawtooth bass to provide a warmer sub-frequency, while the square lead uses a 40% reverb mix for spatial depth.

    Next steps

    1. Save this code to a file named digital_sunset.music.
    2. Run music digital_sunset.music in your terminal to hear the loop.
    3. Use music --export digital_sunset.music digital_sunset.wav to generate a high-quality audio file.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Writing music with code often requires heavy DAWs or complex APIs that break the creative flow. This skill enables deterministic, symbolic music composition through Music-DSL, allowing you to write, validate, and render audio directly from plain-text files.

    What it does

    • Symbolic composition Write songs using a human-readable syntax for tempo, keys, tracks, and arrangements.
    • Local rendering Synthesize audio locally to WAV or export to standard MIDI files without external cloud APIs.
    • Built-in synthesis Access 45 distinct instruments and a suite of effects including reverb, delay, and filters.
    • Syntax validation Use the CLI to check .music files for errors in timing, track alignment, or instrument names.
    • Algorithmic generation Utilize built-in generators for drum patterns, basslines, and arpeggios to accelerate sketching.

    How it works

    1. Author Create a .music file defining global directives like tempo and key, followed by track-specific headers.
    2. Validate Run music --check to ensure the composition adheres to the parser rules and timing logic.
    3. Listen Execute music followed by the filename to play the composition through the local audio backend.
    4. Render Export the final track using --export for WAV files or --midi for MIDI sequences.

    Frameworks & tools

    This skill is built on Python 3.10 and utilizes NumPy for audio synthesis. It supports sounddevice or PyAudio for playback and soundfile or ffmpeg for compressed audio exports.

    Why this beats prompting it yourself

    Raw LLM prompts often hallucinate music notation or produce invalid MIDI structures that fail to load. This skill provides a rigid, validated DSL and a local execution environment that ensures every note generated is actually playable and mathematically consistent.

    Use cases

    • Generate original, royalty-free background loops for games or videos.
    • Prototyping song structures and chord progressions using text-based arrangement.
    • Rapidly sketching cinematic or chiptune cues via CLI without opening a GUI.
    • Automating music variations for procedural content through scriptable text files.

    Known limitations

    Does not support vocal synthesis or AI-generated audio samples. Compressed exports like MP3 or OGG require optional system dependencies like ffmpeg to be manually installed.

    No vocal synthesis or AI audio generation. MP3/OGG export requires external ffmpeg or soundfile. Requires Python 3.10+ and NumPy.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    This skill introduces a structured Domain Specific Language (DSL) that forces the AI to follow strict musical rules, preventing the broken files and timing errors common when asking LLMs to generate MIDI or music notation directly.

    The skill is designed for any Python-based AI agent environment and requires Python 3.10+; it uses standard audio libraries like NumPy and sounddevice for local synthesis without needing a DAW.

    You receive the full Music-DSL parser, the local synthesis engine with 45 built-in instruments, the CLI validation tool, and a library of algorithmic generators for drums and basslines.

    Yes, you can render your compositions to standard MIDI files for use in professional DAWs or export them as WAV files for immediate use in games or videos.

    The synthesis engine includes 45 distinct instruments and a suite of effects like reverb and filters, though it does not support external VSTs or vocal synthesis at this time.