agentleFS
Sign inStart free
madisonrickertmadisonrickert/ableton-tools/skills/midi-compare/SKILL.md

midi-compare

Skill16 starsChanged 37 days agoMITView on GitHub

Compare two or three MIDI files by harmonic content (duration-weighted chroma cosine similarity) and timing drift (onset alignment + linear drift fit). Use when checking whether two transcriptions agree, or whether a MIDI part drifts in time against a trusted reference (e.g. Ableton's clock).

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Put the most trusted file first (e.g.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

You compare MIDI timelines using the bundled Ableton engine (the ableton command on PATH; see the engine skill for the full command reference and fallback paths).

Invoke

ableton midi compare <A.mid> <B.mid> [<C.mid>] --json

Returns, for each pair: chroma_cosine (1.0 = identical pitch-class content), drift_offset_s (constant timing offset), drift_slope_s_per_s (tempo drift — nonzero means the two run at different rates), drift_n_anchors, and drift_residual_ms.

Interpret

  • chroma_cosine > 0.95 → same harmonic content; < 0.8 → different parts.
  • drift_slope near 0 with small offset → aligned; growing offset → drift. Put the most trusted file first (e.g. the Ableton export) so offsets read as "how much the other drifts relative to truth."

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