What is vocello-design?

A design guide and user-interface kit for Vocello, a local-first macOS app that creates speech from text and runs mainly on the user’s computer.

Use it to create Vocello interface mockups, marketing pages, slide materials, visual assets, or related production screens.

It keeps new screens and visual materials consistent with Vocello’s colors, fonts, assets, and Apple-style interface patterns. It also provides guidance for working on either prototypes or the Swift application.

vocello-design — Skill for Claude Code by PowerBeef/Vocello

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add PowerBeef/Vocello --skill vocello-design-system

Clone the repo

git clone --depth 1 https://github.com/PowerBeef/Vocello

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/powerbeef/vocello/vocello-design-system/github.svg)](https://agentmods.dev/skills/powerbeef/vocello/vocello-design-system)

Your own site

<a href="https://agentmods.dev/skills/powerbeef/vocello/vocello-design-system"><img src="https://agentmods.dev/badge/skills/powerbeef/vocello/vocello-design-system/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/powerbeef/vocello/vocello-design-system"><img src="https://agentmods.dev/badge/skills/powerbeef/vocello/vocello-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 469 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00469
Opus 5.5	$0.00010	$0.00188
Sonnet 5.5	$0.00005	$0.00094
Haiku 4.5	$0.00002	$0.00047

Measured 29d ago against content hash ee492aaac75a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vocello-design 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 29d 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.

design_references/Vocello Design System/SKILL.md · 38 lines

What it actually says

Historical reference only. This retained prototype/review is not the current app, release procedure, acceptance evidence, or asset-licensing authority. Follow root CLAUDE.md, the current platform guide and source; do not apply its older layout or font-distribution advice.

Read README.md first — it sets the brand voice, the visual foundations, the iconography rules, and where to find every asset. Browse colors_and_type.css for the tokens, preview/ for review cards, and ui_kits/mac-app/ for the SwiftUI-faithful recreation of the macOS app shell.

If you are creating visual artifacts (slides, mocks, marketing pages, throwaway prototypes), copy what you need from assets/ and ui_kits/ into the new file and produce static HTML. Honor the dark-first canvas, gold brand accent, mode-tinted Liquid Glass cards, and quiet SF Pro / SF Rounded typography. Never use emoji, neon accents, gradient hero CTAs, or terminal aesthetics — those are explicitly anti-brand for Vocello.

If you are working on production code (the Swift app, or a derivative web surface), trust the live repo at PowerBeef/Vocello over anything in this skill — Vocello's source of truth is the SwiftUI codebase, and this skill compresses that into web-friendly tokens.

If the user invokes this skill without other guidance, ask what they want to build (a marketing page, a feature mock, a slide, a brand asset), confirm the target surface, and act as an expert Vocello designer who outputs polished HTML artifacts or production-ready code. Keep copy in the voice described in README.md — warm, clear, confident, verbs over nouns, no celebration, no exclamation points.

Files

What ships with it

50 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed de4f3404c53d
1mo ago Changed · -3 tokens per session ee492aaac75a
1mo ago Changed · -1 lines 0b0ada75d1b2
1mo ago Changed · +8 lines · -42 tokens per session f62b301ff595
1mo ago First seen · 31 lines · 69 tokens per session scan A eb4e29704222

Subscribe to this mod's changes

vocello-design is a skill published in the GitHub repository PowerBeef/Vocello (382 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 469 once invoked, about $0.0001 per session on Opus 5.5. 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.

Apple Silicon Design and UX macos mlx qwen swiftui text-to-speech

benchmark

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.

soniqo/speech-swift · 0 tokens

review-pr

Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…

soniqo/speech-swift · 71 tokens

localvoxtral-doctor

Use when the user's localvoxtral dictation misbehaves, for example a dictation did not join this session, its text was not inserted, or speech or polish failed. Names the localvoxtral commands that check the setup and read the app's log.

T0mSIlver/localvoxtral · 59 tokens

start-talking

Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.

michael-L-i/cadence-code · 57 tokens

vox-voice-alerts

Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…

kohlhofer/vox · 117 tokens

voice-settings

Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.

michael-L-i/cadence-code · 47 tokens