score
Skill2 starsChanged 29 days agoMITView on GitHub
Original music and sound design written in code (numpy synth — no samples, no licences) and locked to picture: cue sheet first, every hit on a cut. Phonk/trap, cinematic, felt-piano launch scores, risers, impacts, whooshes, UI ticks, typing, record scratch. Also beat-grid detection for a supplied track so cuts land on its beats, and delivery loudness (-14 LUFS).
16 other projects use a version of this.
Adopted by
Most recently taken up by
- XORwell/archeflowtheir own version, first seen Nov 15, 2026
- Hainrixz/claude-dbtheir own version, first seen Nov 1, 2026
- Hainrixz/claude-seo-aitheir own version, first seen Nov 1, 2026
- maroffo/claude-forgetheir own version, first seen Oct 25, 2026
- askoulwassim/perfect-placementtheir own version, first seen Oct 15, 2026
- gagoar/icebergtheir own version, first seen Oct 10, 2026
Used with
Projects with it also use audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- quantumaikr/quant.cpp★ 403same name
- Hainrixz/claude-seo-ai★ 81same name
- Hainrixz/claude-db★ 22same name
- maroffo/claude-forge★ 17same name
- gagoar/iceberg★ 10same name
- askoulwassim/perfect-placement★ 3same name
- stonegiantstudio/skills★ 3same name
- dcolclazier/skills★ 1same name
- santiment/skills★ 1same name
- automatewithuday/GTM-Public-Traded-AI-Accounts★ 0same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- art-stylesSkill
- caption-videoSkill
- chop-reelSkill
- explainerSkill
- launch-filmSkill
- product-demoSkill
- studioSkill
- ugc-actorSkill
- ugc-adsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write assets/audio/score.py in the project:
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Score & sound design
scripts/synth.py = shared instruments + stereo Mix + master bus + loudnorm. examples/ = three complete scores.
Workflow
- Cue sheet first — in the score file's docstring, list every picture event with its time (cuts, slams, freeze, VO in/out, end card). Choose BPM so sections land on bar lines (150 BPM: beat 0.4, bar 1.6; 120 BPM: beat 0.5, bar 2.0). Picture and score share these numbers.
- Write
assets/audio/score.pyin the project:import sys; sys.path.insert(0, "<studio>/.claude/skills/score/scripts") from synth import * m = Mix(45.0) for b in grid(150, 16, 3.2): m.add(kick(), b) # beats from 3.2 s m.add(riser(1.6), 1.6); m.add(impact(), 3.2) # drop on the cut m.write("assets/audio/score.wav") - Sound-design grammar that sells cuts: riser → silence (≈0.1 s) → impact on drops; whoosh on whips; record scratch + filtered loop on a freeze frame; full silence before a smash cut; pop/tick per staggered element; clack under folds; bell chord on the end card. Duck the bed ~10 dB under VO.
- Mix into HyperFrames as
<audio data-track-index="10">(VO on its own track). After rendering:ffmpeg -i film.mp4 -af loudnorm=I=-14:TP=-1:LRA=11 -c:v copy film_final.mp4.
Examples (copy one as a starting point; run python3 file.py out.wav)
phonk_150bpm_45s.py— trap/phonk, cowbell melody, 808 glides, break with scratch, delivery build. Chop reels.cinematic_120bpm_60s.py— plucks, marimba, pads, impacts, glitch section. Showreels / explainers.launch_piano_120bpm_40s.py— felt piano motif, warm pulse, fold clacks. Premium launch films.
Supplied music
python3 scripts/beats.py track.mp3 assets/audio → beats.json / beats.js (window.BEATS.beats, downbeats,
bpm). Snap cut times to the nearest beat; put big changes on downbeats. Check the residual it prints (< 20 ms good). BPM is folded into 75–140, so a 150 BPM track reports 75 — use half-beats.
For full music videos from a track use the HyperFrames music-to-video skill or the Fal music-video plugin.
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
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.

