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 agentmods add skills/mxslr/mlcraft/domain-audio-speechnpx skills add mxslr/mlcraft --skill domain-audio-speechgit clone --depth 1 https://github.com/mxslr/mlcraftWrote 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/mxslr/mlcraft/domain-audio-speech)<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-audio-speech"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-audio-speech.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.00512 |
| Opus 5 | $0.00053 | $0.00256 |
| Sonnet 5 | $0.00021 | $0.00102 |
| Haiku 4.5 | $0.00011 | $0.00051 |
Grade A, and why
domain-audio-speech 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 6d 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.
What it actually says
Audio and Speech - Method Selection
Represent audio as a log-mel spectrogram for most classifiers, or feed the raw waveform to self-supervised speech models. Resample to the model's rate (16 kHz is common).
Decision table
| Sub-task | Recommended | Notes |
|---|---|---|
| Speech recognition (ASR) | Whisper (large-v3, or turbo for speed); wav2vec2 or HuBERT with CTC | Whisper is strong and multilingual zero-shot. Metric is WER, never accuracy. |
| Audio or sound classification and tagging | AST or PaSST (spectrogram transformers, AudioSet-pretrained); PANNs (CNN) | log-mel input. Multi-label tagging uses mAP; single-label uses accuracy or macro F1. |
| Keyword spotting | small CNN or MatchboxNet on log-mel | on-device. Track accuracy and false-alarm rate. |
| Speaker verification or ID | ECAPA-TDNN or x-vector embeddings + cosine similarity | metric-learning. Metrics are EER and minDCF. Split by speaker. |
| Sound event detection | CRNN or PaSST with framewise output | event-based F1, PSDS. |
Cross-cutting practice
- Augment with SpecAugment, time and pitch shift, and noise or room-impulse mixing. Normalize levels.
- Leakage: split by speaker, recording, or session, not by clip. The same speaker in train and test inflates results.
- Metrics: WER (and CER) for ASR; mAP for multi-label tagging; EER for verification. Do not report plain accuracy for ASR.
- Explainability: saliency or Grad-CAM on the spectrogram for classifiers; attention or confidence and alignment for ASR.
- Improve accuracy: use
accuracy-improvement-loop. Evaluate withrigorous-evaluationusing the metric that fits the sub-task.
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.
- 6d ago First seen · 25 lines · 105 tokens per session scan A 384086c2af5c
domain-audio-speech is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 512 once invoked, about $0.0005 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
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
chief-data-officer
Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
data-engineering
Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.