Skip to content
cccskills
FreePublished on GitHubEnglish overview

music-midi

Extract MIDI or a score from an already generated music production using pitch tracking. The skill checks that MIDI is available and directs users to the dashboard for downloading it for transcription, arranging, or music software import.

OriginalShow the original description

Extract MIDI/score from an existing production

AI rating90/ 100See how to install

Good for

  • Transcribing a previously generated track
  • Using extracted MIDI for arranging
  • Importing generated music into a DAW
  • Checking MIDI availability and finding the download

Overview

What it does

This skill uses pitch tracking to extract MIDI or a score from music that has already been generated. It takes a production-id, which identifies an existing production, and runs extraction through mcp__cogmusic__extract_midi. It then checks the production with mcp__cogmusic__get_production and confirms that has_midi, the field indicating MIDI availability, has become true.

When it helps

Use it when you want to transcribe a generated track or use MIDI as material for an arrangement. It also helps when you want to import generated music into a DAW, or digital audio workstation, for further music production. The process covers running extraction, checking the result, and explaining where to obtain the file.

Example requests

  • “Extract MIDI from the track with this production-id.”
  • “Extract a score from my generated track so I can use it for an arrangement.”

Notes

You need an existing production id and the listed MCP tools. Extraction involves actual GPU processing. One retry is suggested for a temporary failure. The MIDI file itself is not included in the MCP response; download it from the dashboard.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly describes extracting MIDI or scores from generated tracks and requiring an existing production id.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodThree steps specify extraction, checking has_midi, and download guidance, with the tools identified.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt explicitly identifies GPU processing for the specified id and suggests one retry for transient failures.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingAn existing id and two MCP tools are required, but MCP connection setup steps are absent.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md945 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Music MIDI

Runs pitch-tracked MIDI/score extraction on an already-generated production.

When to use

The user wants a MIDI file or score from a track they've already generated (transcription, arranging, DAW import). Needs an existing production id.

Steps

  1. Call mcp__cogmusic__extract_midi({ id: "<production-id>" }). Real GPU work, same reliability profile as music-stems and music-generate — one retry on a transient failure is reasonable before treating it as broken.
  2. Confirm via mcp__cogmusic__get_production that has_midi is now true.
  3. Like stems, the MIDI file itself isn't returned inline over MCP today — point the user at the dashboard to download it. See ADR-0001.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

add-model-descriptions

FreeSummaryAI rating 80

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo78.4KUpdated Oct 22, 2026

adr-create

FreeSummaryAI rating 80

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo78.4KUpdated Oct 22, 2026

adr-index

FreeSummaryAI rating 90

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo78.4KUpdated Oct 22, 2026

adr-reindex

FreeSummaryAI rating 70

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo78.4KUpdated Oct 22, 2026

adr-review

FreeSummaryAI rating 80

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo78.4KUpdated Oct 22, 2026

adr-verify

FreeSummaryAI rating 90

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo78.4KUpdated Oct 22, 2026

See all skills by ruvnet

Report a problem with this skill