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 GenRamzi/creative-agent-skills --skill voice-prompt-engineergit clone --depth 1 https://github.com/GenRamzi/creative-agent-skillsWrote 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/genramzi/creative-agent-skills/voice-prompt-engineer)<a href="https://agentmods.dev/skills/genramzi/creative-agent-skills/voice-prompt-engineer"><img src="https://agentmods.dev/badge/skills/genramzi/creative-agent-skills/voice-prompt-engineer/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/genramzi/creative-agent-skills/voice-prompt-engineer"><img src="https://agentmods.dev/badge/skills/genramzi/creative-agent-skills/voice-prompt-engineer.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 | $0.00047 | $0.00624 |
| Opus 5 | $0.00023 | $0.00312 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
voice-prompt-engineer 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice prompt engineer
Separate the voice's stable identity from the performance direction for a specific script. A good voice cannot compensate for a script that is hard to speak.
Choose the task
Classify the request as one or more of:
- Voice selection: choose an existing voice suited to the delivery.
- Voice design: describe a new synthetic voice.
- Performance direction: control emotion, pacing, emphasis, and reactions.
- Script preparation: rewrite text for speech while preserving meaning.
- Pronunciation: guide names, technical terms, numbers, or multilingual phrases.
- Dialogue: assign speakers and manage turns.
Load the ElevenLabs v3 reference when that is the target. For any other provider, use a portable brief and do not invent tags or controls.
Create a voice identity brief
Describe only relevant attributes:
- Language, region, and accent strength.
- Approximate adult age range and vocal presentation.
- Timbre, pitch range, resonance, texture, and brightness.
- Baseline pace, rhythm, articulation, and energy.
- Persona and recording context.
- Audio quality, microphone proximity, and artifact tolerance.
Use concrete acoustic and performance terms. Avoid vague praise such as perfect voice. Never request an identifiable person's voice without permission; translate the goal into non-identifying attributes.
Prepare the performance script
- Normalize symbols, abbreviations, dates, units, and numbers when they might be read incorrectly.
- Break long sentences at meaningful breath points.
- Use punctuation for natural phrasing before adding model-specific tags.
- Add the fewest supported direction tags needed at the moment they apply.
- Mark pronunciations only for words likely to fail.
- Give each dialogue speaker a consistent voice and a clean turn.
Do not cover every line in emotion tags. Over-direction reduces contrast and can create artifacts.
Test deliberately
Create a short preview that contains the target emotion, difficult pronunciation, dynamic range, and a natural sentence ending. Test one change at a time: voice, stability or equivalent setting, script punctuation, then tags.
What ships with it
2 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.
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.
- 10d ago First seen · 63 lines · 47 tokens per session scan A b89fed1c7ca4
voice-prompt-engineer is a skill published in the GitHub repository GenRamzi/creative-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 624 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.