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.
npx skills add tatagoncalvesof/imperatriz-toolkit --skill skill-tts-naturalgit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkitWrote 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.
[](https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/skill-tts-natural)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/skill-tts-natural"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/skill-tts-natural/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.
<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/skill-tts-natural"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/skill-tts-natural.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00121 | $0.02514 |
| Opus 5 | $0.00060 | $0.01257 |
| Sonnet 5 | $0.00024 | $0.00503 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
skill-tts-natural 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill TTS Natural — Audio com Voz Clonada
Visao Geral
Transforma qualquer conteudo escrito (aulas, artigos, posts, scripts) em audio natural usando voz clonada do ElevenLabs. O segredo: Gemini reescreve o texto como roteiro falado ANTES de mandar pro TTS. Resultado: audio que soa como uma pessoa ensinando de verdade, nao como robo lendo texto.
Arvore de Decisao
Pedido
|
|-- "gerar audio de uma aula/conteudo"
| --> Fluxo 1: Audio Individual
|
|-- "gerar audio em lote/batch"
| --> Fluxo 2: Audio em Lote
|
|-- "criar audio-generator.js pro meu projeto"
| --> Fluxo 3: Implementacao Completa
|
|-- "melhorar qualidade do audio"
| --> Fluxo 4: Otimizacao de Voz
|
|-- "criar roteiro/script de audio"
| --> Fluxo 5: Apenas Roteiro (sem gerar audio)
Principio Fundamental: NAO USE SUBSTITUICOES FONETICAS
REGRA DE OURO: O ElevenLabs eleven_multilingual_v2 com voz clonada em PT-BR ja sabe pronunciar nomes de marcas, termos em ingles e siglas naturalmente.
NUNCA faca:
- "Claude" → "Clod" (o TTS le como "Clod" literal e fica horrivel)
- "ChatGPT" → "Tchet Ge Pe Te" (vira "Xati Gipiti")
- "GitHub" → "Guitrab"
- "Vercel" → "Verssel" (vira "Versal")
- Qualquer substituicao fonetica de marcas ou termos em ingles
SEMPRE faca:
- Escreva nomes de marcas NORMALMENTE: Claude Code, ChatGPT, GitHub, WhatsApp
- A voz sintetica clonada ja tem sotaque brasileiro natural
- Ela ja sabe pronunciar termos tech do jeito que brasileiros falam
O que FUNCIONA substituir:
- Numeros por extenso: "1000" → "mil", "2024" → "dois mil e vinte e quatro"
- Valores monetarios: "R$ 100" → "cem reais"
- Porcentagens: "50%" → "cinquenta por cento"
Stack Tecnica
| Componente | Tecnologia |
|---|---|
| Roteirista | Google Gemini gemini-2.5-flash via @google/genai |
| TTS | ElevenLabs SDK @elevenlabs/elevenlabs-js |
| Modelo de voz | eleven_multilingual_v2 |
| Runtime | Node.js (ES modules) |
| Audio format | MP3 44100Hz 128kbps |
What ships with it
1 file 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.
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.
- 9d ago First seen · 259 lines · 121 tokens per session scan A 830177c80926
skill-tts-natural is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 121 tokens to every session and 2,514 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
fp-brief
First-principles briefing from technical documents. Use when: understanding why decisions were made, onboarding to feature reasoning, reviewing decision chains, explaining doc from first principles. Not for: PM/CTO summary (use project-brief), pre-doc analysis (use feasibility-study), code explanation (use…
codex-explain
Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.
sharingan
Replicate knowledge from any source as sd0x-dev-flow skill definition. Use when: copying skills from repos, adapting patterns from articles/papers/code, converting knowledge to skill format. Not for: research without skill output (use deep-research), creating skills from scratch (use skill-creator), project onboarding…
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
explaining-codebases
Use when creating an interactive explainer about a codebase, repository, or source files. Handles onboarding overviews, architecture maps, and deep-dives on real implementation paths. Trigger phrases include "explain this codebase", "interactive guide to this repo", "walk through how X works in the code", or…
openehr-assistant
This skill should be used when a conversation touches openEHR outside a task owned by a dedicated skill — e.g. "what is an archetype?", "how do openEHR templates work?", "which composition category fits this data?", "find me a guide on X", "where do I start with openEHR modeling?" — or names openEHR concepts (ADL…