Get Started: MIDI Chord Analyzer: Automating Song Transcriptions

The MIDI Chord Analyzer skill allows developers to automate song transcriptions. The tool splits files into beat segments, extracts pitch clusters, and queries THIRI to spell the chords.

This replaces tedious manual annotation with a clean JSON output of chord names, durations, and key modulations.

JSON Output Structure:

{
  "measure": 1,
  "chords": [
    { "symbol": "Fmaj7", "beats": 2 },
    { "symbol": "G7", "beats": 2 }
  ]
}

🤖 File an Issue for an Autonomous Coding Agent

This project requires setting up an external application or workflow environment. If you want an autonomous coding agent (like Claude Code) to implement it in your repository:

1. Click here to open a pre-filled GitHub Issue on the repository
2. Submit the issue to trigger your repository’s autonomous builder agent.

Alternatively, you can copy the raw agent prompt instruction below:

Task Context: Build a code project utilizing the THIRI Model Context Protocol (MCP) server. Prompt Instruction: Write a Python command-line tool that parses a local .mid file using mido. Extract note events, cluster pitches by musical beats, and query the THIRI MCP resolve_chord tool for each beat. Export the resolved progressions as a structured JSON file containing chord names, durations, and key centers.