voice-training-ui: Skill for Claude Code

.claude/skills/analyze-voice/SKILL.md

analyze-voice is a skill for Claude Code from scratchyone/voice-training-ui. It costs 87 tokens per session (1,832 once invoked), scanned A, original, MIT.

A workflow for analyzing Rachel’s voice-training recordings and adding personalized guidance to a voice-feminization tracker. It combines automatic measurements with a written explanation of the main thing to practise.

In plain words
What is it for?
Use it for new voice recordings, especially when Rachel shares what she was practising and needs analysis plus tailored notes.
Why use it?
It turns recording data into one specific, actionable focus while keeping feedback supportive and avoiding judgment based only on numbers.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is scratchyone/voice-training-ui's own configuration. It tells Claude Code how to work on voice-training-ui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything voice-training-ui configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/rachel/Downloads/voice-training.

Reuse

Borrowing it

Nothing to install: this file belongs to scratchyone/voice-training-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/scratchyone/voice-training-ui/main/.claude/skills/analyze-voice/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/scratchyone/voice-training-ui

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for analyze-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/scratchyone/voice-training-ui/analyze-voice/github.svg)](https://agentmods.dev/skills/scratchyone/voice-training-ui/analyze-voice)
Your own site
<a href="https://agentmods.dev/skills/scratchyone/voice-training-ui/analyze-voice"><img src="https://agentmods.dev/badge/skills/scratchyone/voice-training-ui/analyze-voice/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for analyze-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/scratchyone/voice-training-ui/analyze-voice"><img src="https://agentmods.dev/badge/skills/scratchyone/voice-training-ui/analyze-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01832
Opus 5 $0.00044 $0.00916
Sonnet 5 $0.00017 $0.00366
Haiku 4.5 $0.00009 $0.00183

Measured 9d ago against content hash c2c024325606, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

analyze-voice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/analyze-voice/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Rachel's voice (Voice Garden)

Voice Garden is a voice-feminization training tracker. Rachel records herself (usually the Rainbow Passage), tells you what she was practicing, and you analyze it. There are two layers and your job spans both:

  1. Standard analysis → permanent, data-driven dashboard cards + the permanent "🎚️ Register & phrasing" visualizer. Fully automated by analyze.py — you just run it.
  2. Intelligent, per-recording annotations → you read the detailed data, find the single most important, specific, clockable thing to work on, and author it as custom UI: a big insight in the "🔍 Insights for this take" section, plus optional personalized woven notes.

Read CLAUDE.md for the full vibe/design. Keep everything warm, specific, and comforting ("Animal Crossing girliepop"). Numbers are a compass, not a judge. Be honest about weaknesses, always actionable and kind.


Step 1 — Run the standard analyzer

cd /Users/rachel/Downloads/voice-training
uv run analyze.py "<path to audio>" --label "<what she was practicing>" [--note "..."] [--register-floor 130]
  • Always pass --label (her stated focus). Ask if she didn't say.
  • Python is managed with uv, never pip. If you edit analyze.py, run uvx ruff check . and keep it clean.
  • Writes (additive, idempotent per id): recordings.json (+ mirror in dashboard-react/public/), public/analysis/<id>.json (heavy detail), public/audio/<id>.
  • Note the new id (printed as entry #N) — it's the annotation filename.

Step 2 — Read the detailed data

Read dashboard-react/public/analysis/<id>.json and the new entry in recordings.json. Shapes are in dashboard-react/src/types.ts:

  • Recording.register: in_register_pct, semitones_sd (raw, inflated), in_register_semitones_sd (honest melody), onset_sub_pct/mid_sub_pct/offset_sub_pct, phrases_landed_pct, n_phrases, floor_hz.
  • RecordingDetail: frames {t[],hz[]} (hz null when unvoiced), phrases[] (start/end/onset_hz/offset_hz/min_hz/started_in_register/ended_in_register/sub_register_pct).
  • Standard metrics: pitch, formants, voice_quality, intensity.
  • If there's history, read prior entries to compare trends.

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 118 lines · 87 tokens per session scan A c2c024325606

Subscribe to this mod's changes

analyze-voice is a skill published in the GitHub repository scratchyone/voice-training-ui (79 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,832 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens