agentleFS
Sign inStart free
PantaniPantani/ableton-mind/.agents/skills/recipe-authoring/SKILL.md

recipe-authoring

Skill9 starsChanged 5 months agoMITView on GitHub

How to author ableton-mind JSON music recipes for drums, bass, chords, racks, arrangements, mixing and live performance.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this skill when creating or reviewing files under recipes/.

    line 8
  2. Distinctive:

    verify checks for expected tracks, devices, clips or arrangement state.

    line 19
  3. Distinctive:

    Use named step results, top-level params, $next for the next free index and $last for the previous result.

    line 23
  4. Distinctive:

    Check every URI and device parameter against knowledge.

    line 29
  5. Distinctive:

    Test variations in tempo, key and intensity.

    line 32
  6. Distinctive:

    Keep descriptions in English.

    line 33
  7. Distinctive:

    Avoid generic all-purpose recipes, uncataloged URIs, hidden hardcoded assumptions, ignored intensity params and recipes that were never …

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Recipe Authoring

Use this skill when creating or reviewing files under recipes/.

What Makes a Good Recipe

A recipe is declarative JSON that creates a musically useful result in Live. It should sound recognizable for its genre, be reusable, be override-friendly and verify its own output.

Required Shape

  • id, title, description, category and tags.
  • params for tempo, key, length_bars, intensity or relevant user choices.
  • steps with tool names, inputs, optional let bindings and refs.
  • verify checks for expected tracks, devices, clips or arrangement state.

Variables and Refs

Use named step results, top-level params, $next for the next free index and $last for the previous result. Recipes are data, not code; do not add imperative JS logic.

Workflow

  1. Pick 2-3 references for the genre or technique.
  2. Draft the smallest useful JSON.
  3. Check every URI and device parameter against knowledge.
  4. Apply in Live or a faithful mock.
  5. Listen and adjust until it works musically.
  6. Test variations in tempo, key and intensity.
  7. Keep descriptions in English; localized docs belong under docs/pt.

Anti-Patterns

Avoid generic all-purpose recipes, uncataloged URIs, hidden hardcoded assumptions, ignored intensity params and recipes that were never auditioned.

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