An articulated wooden performer follows an editable score, touching the keys that trigger its notes. Every score event supplies a key, hand and time. Inverse kinematics connects each shoulder to its moving fingertip, and the same event depresses the key and synthesizes a pitched tone. The two pedals and body response follow the note sequence. Optional new music can be quoted through PopNow after the picture is approved.

Uses PopNow for
Music & voice
Needs
Node.js · FFmpeg · Chrome · Python 3

Generation is optional when you have suitable input material.

v1.0.0 · Updated Oct 26, 2026 · 134 KB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. A 20-second native landscape or portrait MP4 and editable composition.

  2. Every score event supplies a key, hand and time. Inverse kinematics connects each shoulder to its moving fingertip, and the same event depresses the key and synthesizes a pitched tone. The two pedals and body response follow the note sequence.

  3. A poster, contact sheet and local render receipt.

Good for

  • Original music-box greetings
  • Short educational rhythm and melody demonstrations

Not for

  • The sound is local synthetic tones, not a sampled piano. The rig is a constrained two-arm illustration, not a general character animation or MIDI importer.
  • This version supports seven diatonic keys and an explicit JSON score, not arbitrary polyphonic music.

How it works

Includes a local renderer

  1. Write a playable phrase

    Edit the note array, assign hands and leave at least 0.55 seconds between contacts by the same hand.

  2. Bind contact and sound

    Use the same scheduled notes for fingertip targets, key depression, pedal response and locally synthesized triangle tones.

  3. Listen and inspect

    Watch hand contacts with sound, then compare the portrait staging. Add a quiet approved music bed only if it preserves the contact notes.

How the workflow runs

How Musical Puppet Stage works

Every score event supplies a key, hand and time. Inverse kinematics connects each shoulder to its moving fingertip, and the same event depresses the key and synthesizes a pitched tone. The two pedals and body response follow the note sequence.

What's inside the skill

What you can change

  • score: 8–24 ordered notes with time, key 0–6, hand 0–1 and note length.
  • tempoScale: 0.85–1.05 changes event times together; the score must finish before 18.6 seconds.
  • The title and native aspect can be changed without altering the note mapping.

What to review before delivery

  • The validator rejects invalid keys, overlapping hand travel and an overlong slowed score.
  • The domain test checks that each event places its assigned hand on the matching key.
  • Listen for note/contact alignment and inspect elbow reach and string attachments.

See the package files

These are selected working files from this edition, with their actual role. The complete download also contains instructions and applicable license notices.

  • The scene model, input validation and actual animation.

    scripts/composition.mjs
  • A complete working scene brief.

    examples/project.json
  • Protected project assembly and external HyperFrames export.

    scripts/render.mjs
  • Supported controls, asset placement and limits.

    references/inputs.md

Why use this skill

Start with this package

The score controls both the visible rig and the audio events. The package supplies an editable performance mechanism, rather than unrelated puppet footage with a soundtrack placed underneath.

What PopNow adds

Use PopNow for the missing Music & voice in this workflow. Keep adequate material you already own, then bring new assets back into the editing and assembly steps described here.

Compare the options

A prompt, your own skill, or this workflow?

Start with a prompt

Your agent can create from a plain request. The brief, visual rules, asset choices, output format and review process still need to be established for that project.

Write your own skill

You choose and maintain the reusable instructions, defaults, file structure and checks. This is useful when your process needs different rules or integrations.

A workflow created for PopNow

This workflow was built for PopNow. Its source files, included dependencies and applicable notices are part of the package; the scope described below belongs to this edition.

Guide reviewed Oct 25, 2026

What will this cost?

The supplied scene renders locally without generated media. A new music or ambience bed is optional and requires its own PopNow quote and approval; sufficient owned audio can be reused. Local rendering still uses your computer and installed tools.

Generation is optional when you have suitable input material. Free skill. New media is quoted before it runs.

The skill package

Free to install under your account's download allowance. The package license covers your own and client work; redistribution is excluded.

Existing assets and local work

Reusing suitable assets, editing files and running local assembly do not call a PopNow generation model. Your computer and any required runtime still do the work.

New AI images, clips or sound

Quoted for the actual model, inputs, count, duration and resolution. Extra alternatives, revisions or optional enhancement passes can add generation requests.

Your agent and hosting

Any subscription, hosted computer, deployment or other provider fee belongs to that service. Installing this skill does not include those services.

Check the cost of your version first

Your assistant can inspect the available models and quote the exact request first. You choose which optional passes to include and approve spending before generation.

Ask your assistant

  • Use the PopNow skill "Musical Puppet Stage" for my project. List the inputs you can reuse, quote only the missing media, show the quoted total and flag any unpriced steps. Separate optional enhancements, and wait for my approval before starting anything paid.

How PopNow billing works

Connections using a PopNow API key, including API-key MCP connections, spend from the separate API balance in USD. A ChatGPT or Claude connection authorized through OAuth spends website credits. These balances are separate; the quote shown by your connection is the approval basis.

Download allowances and current account conditions apply. A free package does not mean unlimited free generation.

How to use it

You say

  • Use the PopNow skill "Musical Puppet Stage" (musical-puppet-stage) for this: Render the wooden performer using the supplied score, then move the first note to key 2 and increase tempoScale to 1.05. Keep the visible contacts tied to the notes. Quote any optional new media first.

Then try

  • Give the left hand a different opening phrase within the documented travel limits.

  • Render the vertical stage and let me hear the complete synthetic performance.

What to have ready

  • Node.js 22.12+, the pinned dependencies, Chrome and FFmpeg.
  • A short original story and the documented JSON inputs.
  • The new film examples use ASCII text. Accents and other scripts need a suitable font plus input and layout adjustments.

Similar skills

View all →

Ratings

No ratings yet. Installed it? Be the first to rate it.

Rate this skill

Questions

Are the sounds tied to the visible keys?

Yes. Both the key contact and synthesized frequency use the same score event and tempo conversion.

Can I load a MIDI recording?

No. This version takes the documented JSON score with seven diatonic key positions and explicit hand assignments.

Is the performer rendered from a character image?

No. The wooden head, cloth coat, limbs and strings are drawn locally. Character-image retargeting is not included.

What is already packaged in Musical Puppet Stage?

The scene model, input validation and actual animation. A complete working scene brief. Protected project assembly and external HyperFrames export. Supported controls, asset placement and limits.

Which parts of Musical Puppet Stage can add a charge?

The supplied scene renders locally without generated media. A new music or ambience bed is optional and requires its own PopNow quote and approval; sufficient owned audio can be reused. Local rendering still uses your computer and installed tools. Connections using a PopNow API key, including API-key MCP connections, spend from the separate API balance in USD. A ChatGPT or Claude connection authorized through OAuth spends website credits. These balances are separate; the quote shown by your connection is the approval basis.

How does Musical Puppet Stage differ from writing a prompt or my own skill?

The score controls both the visible rig and the audio events. The package supplies an editable performance mechanism, rather than unrelated puppet footage with a soundtrack placed underneath.