audio
Skill0 starsChanged 42 days agoMITView on GitHub
Voice cleanup and level (conservative high-pass/denoise/de-ess/compression, static gain to a LUFS target), code-synthesized original music beds (100–120 BPM, first beat on frame one, fade ending at END) and SFX (click, key ticks, pop, chime, whip-aligned whoosh, intro riser) tied to visible events, unity-sum mixing, true-peak-safe AAC delivery, END-length stems and honest measurements.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- bmcszk/agent-skillstheir own version, first seen Oct 29, 2026
- autonomous-ai/lampOStheir own version, first seen Oct 15, 2026
- timelapsetech/mediaskillstheir own version, first seen Aug 15, 2026
- AlexeyPerov/Unity-Open-MCPtheir own version, first seen Jul 14, 2026
- qmertesdorf/GameForgetheir own version, first seen Jun 28, 2026
- rainday/smart-blog-skillstheir own version, first seen May 15, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- autonomous-ai/autonomous-os★ 552same name
- autonomous-ai/lampOS★ 552same name
- autonomous-ai/Physical-AI-Operating-System★ 552same name
- rainday/smart-blog-skills★ 35same name
- AlexeyPerov/Unity-Open-MCP★ 17same name
- bmcszk/agent-skills★ 2same name
- timelapsetech/mediaskills★ 1same name
- qmertesdorf/GameForge★ 0same name
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 repository19 other files it gives its agents.
- analyzeSkill
- captionsSkill
- clipSkill
- creator-editSkill
- designSkill
- directorSkill
- doctorSkill
- editSkill
- exportSkill
- graphicsSkill
- ingestSkill
- luxury-techSkill
- previewSkill
- quality-checkSkill
- reframeSkill
- reviseSkill
- studioSkill
- style-learningSkill
- transcribeSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
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 33
Every render writes stems/voice.wav, stems/music.wav, stems/sfx.wav, stems/riser.wav (those the plan uses), all exactly END samples at 48 …
- Distinctive: line 42
No stock audio, no source-music "separation" claims.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Audio
Rules: ${CLAUDE_PLUGIN_ROOT}/references/rules.md · CLI: ${CLAUDE_PLUGIN_ROOT}/references/cli.md.
ss = "${CLAUDE_PLUGIN_ROOT}/bin/shorts-studio". Input: $ARGUMENTS
0. Engine check
The commands below run the Shorts Studio engine. Installed as the Claude Code plugin it is already
present and shorts-studio is on the Bash PATH. If shorts-studio doctor is not found (for example,
this skill was added with npx skills add), ask the user before installing anything, then:
- Claude Code:
/plugin marketplace add bloxy-studios/shorts-studio→/plugin install shorts-studio@shorts-studio. - Other agents:
git clone --depth 1 https://github.com/bloxy-studios/shorts-studio ~/.shorts-studio/engineand read every${CLAUDE_PLUGIN_ROOT}path below as~/.shorts-studio/engine.
Then run shorts-studio doctor --setup once (project-local runtime; never sudo or global installs).
Steps
- Every render writes
stems/voice.wav,stems/music.wav,stems/sfx.wav,stems/riser.wav(those the plan uses), all exactly END samples at 48 kHz, plusmaster.wav; the report lists integrated LUFS, sample peak and true peak per stem (silent/gated stems are reported as such — never a fake number). - Changes:
music-gain(dB, voice untouched),voice-chain(denoise off/light/medium, de-ess, compress, high-pass), viass revise. Luxury SFX come from visible graphics events in the brief; remove a sound by changing the event, never the preset rule. Whooshes only on whips (≤ 1/run, ≤ 3/short, varied). - Targets (Luxury): voice ≈ −14 LUFS, music ≈ −24 LUFS with one flat gain (no ducking), master ≈ −14 LUFS,
≤ −1 dBTP measured on the delivered AAC. The combination is measured, not assumed; a limiter acts only when
needed and is logged;
ss repairraises the pre-encode headroom if the encoded file still overshoots. - No stock audio, no source-music "separation" claims.
Completion check
audio.true-peak, audio.stem-length pass; audio.loudness within tolerance or explained; for Luxury,
luxury.sfx-rules passes and the riser ends at the hook → first-point join.
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.