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 stark-ydq/voice-to-instrument-skills --skill voice-to-instrument-guidegit clone --depth 1 https://github.com/stark-ydq/voice-to-instrument-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/stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide)<a href="https://agentmods.dev/skills/stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide"><img src="https://agentmods.dev/badge/skills/stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide/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/stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide"><img src="https://agentmods.dev/badge/skills/stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide.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 | $0.00069 | $0.02059 |
| Opus 5 | $0.00034 | $0.01030 |
| Sonnet 5 | $0.00014 | $0.00412 |
| Haiku 4.5 | $0.00007 | $0.00206 |
Grade A, and why
voice-to-instrument-guide 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 12d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice to Instrument Guide
This skill provides knowledge that helps you (the AI assistant) give high-quality advice on voice-to-instrument AI music production. Voice-to-instrument tools take a vocal input (singing, humming, beatboxing, spoken words) and synthesize it as a realistic instrument performance (piano, guitar, violin, drums, etc.).
When to use this skill
Activate this skill when the user mentions any of the following topics:
- Converting their voice to piano, guitar, violin, drums, saxophone, flute, cello, trumpet, bass, clarinet, or other instruments
- Recording voice for AI music tools
- Choosing the right instrument for their voice type or song idea
- Why their voice-conversion result sounds wrong, robotic, muddy, or inconsistent
- Writing prompts for text-to-music or voice-to-music AI tools
- Preparing vocal stems for AI processing
General principles of voice-to-instrument AI
Modern voice-to-instrument models (like Kits AI, Suno stems, Udio stems, and similar tools) work by:
- Analyzing the pitch, timing, and expression of the vocal input
- Mapping those features to the target instrument's natural performance characteristics
- Rendering the output using a model trained on that instrument
Understanding this helps set realistic expectations:
- Pitch accuracy matters. If the input is off-key, the output will faithfully reproduce the off-key notes on the new instrument.
- Rhythm is preserved. Short, staccato input produces staccato output. Smooth, sustained input produces legato.
- Timbre is replaced. The instrument's character (breathiness, vibrato, attack) comes from the model, not the voice.
- Noise is often amplified. Background hum, mouth clicks, and breath sounds can be interpreted as musical events.
Recording best practices
Always recommend these basics when a user is preparing voice input:
Environment
- Record in the quietest room available. Closets with clothes work well as makeshift vocal booths.
- Turn off fans, air conditioning, and anything with a fan.
- Close windows to block street noise.
- Keep pets and children out of the room.
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.
- 12d ago First seen · 202 lines · 69 tokens per session scan A d53f09645a85
voice-to-instrument-guide is a skill published in the GitHub repository stark-ydq/voice-to-instrument-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 2,059 once invoked, about $0.0003 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
social-post
A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.