Plan a film score as dramatic cues with entry, exit, duration, energy curve, instrumentation, tempo, key, motif rules, hit points, silence, and model targets.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add badgids/Story-Film-Skills --skill score-plan --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Score Plan?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-score-plan)More formats (shields.io, HTML) on the badges page.
---
name: score-plan
description: Plan a film score as dramatic cues with entry, exit, duration, energy curve, instrumentation, tempo, key, motif rules, hit points, silence, and model targets.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Score Plan
## Workflow
1. Read core contract, style rules, screenplay, director book if present, and edit intent.
2. Define motif rules before individual cue prompts. State where a motif must not appear as clearly as where it should.
3. Write `04_generation/music_cues.jsonl` using stable `MUS-###` IDs.
4. Each cue needs a dramatic job, start and end logic, estimated duration, energy curve, instrumentation, tempo or tempo range, key only if useful, hit points, transition behavior, and avoid list.
5. Choose ACE-Step XL for structured local control or MiniMax Music 3 for a rich musical brief. Stable Audio 3 may be used for instrumental beds or textures.
## Done
Every music cue has a reason to exist and does not duplicate ambience or emotional information the scene already carries by itself.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.