V-Sekai-fire

Voice Clone Maskscore Ladder — Design skill for Claude Code

Design community

Build a MaskScore-style 10-rank voice-clone gradient corpus from a set of speech recordings, with a multi-judge ASR panel and wavlm+wer scoring.

How to install Voice Clone Maskscore Ladder

Installs to ~/.claude/skills/v-sekai-fire-dot-claude-voice-clone-maskscore-ladder/SKILL.md

Terminal
mkdir -p ~/.claude/skills/v-sekai-fire-dot-claude-voice-clone-maskscore-ladder && curl -fsSL https://raw.githubusercontent.com/V-Sekai-fire/dot-claude/HEAD/skills/voice-clone-maskscore-ladder.md -o ~/.claude/skills/v-sekai-fire-dot-claude-voice-clone-maskscore-ladder/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Voice Clone Maskscore Ladder does


name: voice-clone-maskscore-ladder description: Build a MaskScore-style 10-rank voice-clone gradient corpus from a set of speech recordings, with a multi-judge ASR panel and wavlm+wer scoring. Use when a new speech dataset needs to enter the RFD 1173 MaskScore Speech stub (RFD 2164), when a new SpeakingFaces subject or similar CC-BY audio source needs to be processed, or when a downstream reward-model distillation (RFD 2167) needs training data. tools: Read, Write, Edit, Grep, Glob, Bash

Alternatives in Design

  • Vocab Init — Create a vocabulary skill for the target project — detect layout, extract literary warrant from the corpus, se 131 ★
  • Fireworks Design — Generate a world-class frontend page via fireworks-design (explore → judge → synthesize → refine → polish) 96 ★
  • Gan Design — Run a generator/evaluator design loop for frontend or visual work with bounded iterations and scoring 88 ★

Full documentation available on GitHub

View Source Repository