Local voice cloning director

Skill yjin5562-dev/local-voice-cloning-director/skills/local-voice-cloning-director

Create and quality-check local voiceovers from a voice the user owns or is licensed to use, without a per-generation API fee. Use when the user asks for local or free voice cloning, offline TTS, narration in their own voice, pronunciation fixes for English names, tone or pacing control, source-style retelling without copying the source speaker, or a validated audio track for video production. Require explicit voice authorization, keep reference audio local, prefer CosyVoice2, and never clone or impersonate an unconsenting third party.From its SKILL.md

Install

npx -y skills add yjin5562-dev/local-voice-cloning-director --skill local-voice-cloning-director

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.1 KB, 100 tokens by cl100k_base, as published. Nobody here has run it

Local Voice Cloning Director plugin entry

Read ../../SKILL.md completely and follow it as the authoritative workflow. Resolve every scripts/, references/, and examples/ path from the plugin root two directories above this file.

Keep the same consent, privacy, provenance, human-listening, and honest-status gates. Do not copy the root implementation into this compatibility entry; the root files are the single source of truth for both traditional Skill installation and plugin installation.

What ships with it: 1 file

318 B alongside SKILL.md

agents/

openai.yaml318 B

Gives 0 of the 12 instructions most video audio skills give in 100 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

Read individual rule files for detailed explanationsin 21 of 622, across 10 files
Render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
Save generated audio to a WAV filein 11 of 622, across 4 files
Handle conversion errors gracefullyin 10 of 622, across 6 files
Add captions to videos alwaysin 10 of 622, across 4 files
Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
Do not skip pipeline layersin 9 of 622, across 3 files
Do not make one tool do everythingin 9 of 622, across 3 files
Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

read the authoritative skill file completely
resolve relative paths from the plugin root
maintain consent gates
maintain provenance gates
maintain human-listening gates
maintain honest-status gates

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.